Sample Design in TIMSS and PIRLS

Size: px
Start display at page:

Download "Sample Design in TIMSS and PIRLS"

Transcription

1 Sample Desgn n TIMSS and PIRLS Introducton Marc Joncas Perre Foy TIMSS and PIRLS are desgned to provde vald and relable measurement of trends n student achevement n countres around the world, whle keepng to a mnmum the burden on schools, teachers, and students. Both programs employ rgorous school and classroom samplng technques so that achevement n the student populaton as a whole may be estmated accurately by assessng ust a sample of students from a sample of schools. TIMSS assesses mathematcs and scence achevement at two grade levels and so TIMSS has two target populatons all students enrolled at the fourth grade and all students enrolled at the eghth grade. Countres may assess ether or both student populatons. As an assessment of readng comprehenson n prmary school, the target populaton for PIRLS s all students enrolled at the fourth grade. TIMSS and PIRLS both employ the same two-stage random sample desgn, wth a sample of schools drawn as a frst stage and one or more ntact classes of students selected from each of the sampled schools as a second stage. Intact classes of students are sampled rather than ndvduals from across the grade level or of a certan age because TIMSS and PIRLS pay partcular attenton to students currcular and nstructonal experences, and these typcally are organzed on a classroom bass. Samplng ntact classes also has the operatonal advantage of less dsrupton to the school s day to day busness than ndvdual student samplng. Natonal Samplng Plan Each country partcpatng n TIMSS or PIRLS needs a plan for defnng ts natonal target populaton and applyng the TIMSS and PIRLS samplng methods to acheve a natonally representatve sample of schools and students. The development and mplementaton of the natonal samplng plan s a collaboratve exercse nvolvng the country s Natonal Research Coordnator (NRC) and the TIMSS and PIRLS samplng experts. Statstcs Canada s responsble for advsng the Natonal Research Coordnator on all samplng matters and for ensurng that the natonal samplng plan conforms to the TIMSS and PIRLS standards. In cooperaton SAMPLING IMPLEMENTATION 1

2 METHODS AND PROCEDURES 2 SAMPLING IMPLEMENTATION wth samplng staff from the IEA Data Processng and Research Center (DPC), Statstcs Canada works wth the Natonal Research Coordnator to select the natonal school sample(s) and produce all supportng documentaton for trackng the sampled schools. Ths ncludes ensurng that the school samplng frame (the school populaton lst from whch the school sample s drawn) provded by the Natonal Research Coordnator s complete and satsfactory; checkng that categores of excluded students are clearly defned, ustfed, and kept to a mnmum; assstng the Natonal Research Coordnator n determnng the sample sze and a stratfcaton plan that wll meet both nternatonal and natonal obectves; and drawng a natonal sample of schools. When samplng has been completed and all data collected, Statstcs Canada documents populaton coverage and school and student partcpaton rates and constructs approprate samplng weghts for use n analyzng and reportng the results. The TIMSS & PIRLS Internatonal Study Center, n cooperaton wth Statstcs Canada and the IEA DPC, provdes Natonal Research Coordnators wth a seres of manuals to gude them through the samplng process. More specfcally, TIMSS & PIRLS Survey Operatons Procedures Unt 1: Samplng Schools and Obtanng ther Cooperaton (TIMSS & PIRLS Internatonal Study Center, 2008) descrbes the steps nvolved n defnng the natonal target populaton and selectng the school sample, and TIMSS & PIRLS Survey Operatons Procedures Unt 3: Contactng Schools and Samplng Classes (TIMSS & PIRLS Internatonal Study Center, 2010) descrbes the procedure for samplng classes wthn the sampled schools and makng preparatons for conductng the assessments. Wthn-school samplng procedures for the feld test are documented n TIMSS & PIRLS Survey Operatons Procedures Unt 2: Preparng for and Conductng the Feld Test (TIMSS & PIRLS Internatonal Study Center, 2009). The TIMSS or PIRLS Natonal Research Coordnator s responsble for provdng Statstcs Canada wth all nformaton and documentaton necessary to conduct the natonal samplng, and for conductng all samplng operatons n the country. In partcular, the NRC s expected to dentfy the grade(s) that correspond to the nternatonal target populaton(s); create a samplng frame by lstng all schools n the populaton that have classes wth students n the target grade(s); determne natonal populaton coverage and exclusons, n accordance wth the TIMSS and PIRLS nternatonal gudelnes; work wth Statstcs Canada to develop a natonal samplng plan and dentfy sutable stratfcaton varables, ensurng that these varables are present and correct

3 for all schools; contact all sampled schools and secure ther partcpaton; keep track of school partcpaton and the use of replacement schools; and conduct all wthn-school samplng of classes. Each NRC s requred to complete a seres of samplng forms documentng the completon of each of these tasks. A crucal feature of each nternatonal meetng of Natonal Research Coordnators s a one-to-one meetng between each NRC and samplng staff at Statstcs Canada and the IEA DPC. At these meetngs, each step of the samplng process s documented and revewed n detal, and NRCs have the opportunty to rase ssues and ask questons about ther natonal stuaton and any challenges they face. Statstcs Canada consults wth the TIMSS & PIRLS Internatonal Study Center or the Internatonal Samplng Referee, as necessary, to resolve ssues and questons. Fnal approval of TIMSS and PIRLS natonal samplng plans s the responsblty of the TIMSS & PIRLS Internatonal Study Center, based upon the advce of Statstcs Canada and the Internatonal Samplng Referee. Defnng the Target Populaton As nternatonal studes of the comparatve effects of educaton on student achevement n mathematcs, scence, and readng, TIMSS and PIRLS defne ther nternatonal target populatons n terms of the amount of schoolng students have receved. The number of years of formal schoolng s the bass of comparson among partcpatng countres. Thus, the nternatonal target populaton for PIRLS and TIMSS at the lower grade s all students n ther fourth year of formal schoolng, and for TIMSS at the upper grade, all students n ther eghth year of formal schoolng. UNESCO s Internatonal Standard Classfcaton of Educaton (ISCED) provdes an nternatonally accepted classfcaton scheme for descrbng levels of schoolng across countres. The ISCED system descrbes the full range of schoolng, from pre-prmary (Level 0) to the second level of tertary educaton (Level 6). ISCED Level 1 corresponds to prmary educaton or the frst stage of basc educaton. The frst year of Level 1 should mark the begnnng of systematc apprentceshp of readng, wrtng, and mathematcs (UNESCO, 1999). Four years after ths would be the target grade for PIRLS and fourth grade TIMSS, and s the fourth grade n most countres. Smlarly, eght years after the frst year of ISCED Level 1 s the target grade for eghth grade TIMSS and s the eghth grade n most countres. However, gven the cogntve demands of the SAMPLING IMPLEMENTATION 3

4 assessments, TIMSS and PIRLS want to avod assessng very young students. Thus, TIMSS and PIRLS recommend assessng the next hgher grade (.e., ffth grade for PIRLS or fourth grade TIMSS and nnth grade for eghth grade TIMSS) f, for fourth grade students, the average age at the tme of testng would be less than 9.5 years and, for eghth grade students, less than 13.5 years. The fourth-grade and eghth-grade target populatons of students are defned as follows: Fourth grade (PIRLS and TIMSS): All students enrolled n the grade that represents four years of schoolng countng from the frst year of ISCED Level 1, provdng the mean age at the tme of testng s at least 9.5 years. Eghth grade (TIMSS only): All students enrolled n the grade that represents eght years of schoolng countng from the frst year of ISCED Level 1, provdng the mean age at the tme of testng s at least 13.5 years. All students enrolled n the target grade, regardless of ther age, belong to the nternatonal target populaton and should be elgble to partcpate n TIMSS and PIRLS. Because students are sampled n two stages, frst by randomly selectng a school and then randomly selectng a class from wthn the school, t s necessary to dentfy all schools n whch elgble students are enrolled. Essentally, elgble schools for TIMSS or PIRLS are those that have any students enrolled n the target grade, regardless of type of school. All schools of all educatonal sub-systems that have students learnng full-tme n the target grade are part of the nternatonal target populaton, ncludng schools that are not under the authorty of the natonal Mnstry of Educaton. Natonal Target Populatons For most countres, the target grade for PIRLS or TIMSS s the fourth and/ or eghth grade. However, because educatonal systems vary n structure and n polces and practces wth regard to age of startng school and promoton and retenton, there are dfferences across countres n how the target grades are labelled and n the average age of students. To ensure that the approprate natonal target grades are selected, each NRC completes Samplng Form 1, whch dentfes the target grades, the country s name for those grades, and the average age of students n those grades at the tme of data collecton. (To vew an example of a completed Samplng Form 1 for TIMSS and PIRLS n 2011, please clck here.) METHODS AND PROCEDURES 4 SAMPLING IMPLEMENTATION

5 Natonal Coverage and Exclusons TIMSS and PIRLS are desgned to descrbe and summarze student achevement across the entre target grade (fourth or eghth), and so t s very mportant that natonal target populatons am for comprehensve coverage of elgble students. However, n some cases, poltcal, organzatonal, or operatonal factors make complete natonal coverage dffcult to attan. Thus, n some rare stuatons, certan groups of schools and students may have to be excluded from the natonal target populaton. For example, t may be that a partcular geographcal regon, educatonal sub-system, or language group cannot be covered. Such excluson of schools and students from the target populaton s referred to as reduced populaton coverage. Even countres wth complete populaton coverage fnd t necessary to exclude at least some students from the target populaton because they attend very small schools, have ntellectual or functonal dsabltes, or are non-natve language speakers. Such students may be excluded at the school level (.e., the whole school s excluded) or wthn the school on an ndvdual bass. SCHOOL LEVEL EXCLUSIONS Although t s expected that very few schools wll be excluded from the natonal target populaton, NRCs are permtted to exclude schools on the followng grounds when they consder t necessary: Inaccessblty due to ther geographcally remote locaton; Extremely small sze (e.g., four or fewer students n the target grade); Offerng a grade structure, or currculum, radcally dfferent from the manstream educatonal system; or Provdng nstructon solely to students n the student-level excluson categores lsted below (.e., caterng only to specal needs students). STUDENT LEVEL EXCLUSIONS The nternatonal wthn-school excluson rules are specfed as follows: Students wth functonal dsabltes These are students who have physcal dsabltes such that they cannot perform n the PIRLS and/ or TIMSS testng stuaton. Students wth functonal dsabltes who are able to perform should be ncluded n the testng. Students wth ntellectual dsabltes These are students who are consdered, n the professonal opnon of the school prncpal or by SAMPLING IMPLEMENTATION 5

6 other qualfed staff members, to have ntellectual dsabltes or who have been tested as such. Ths ncludes students who are emotonally or mentally unable to follow even the general nstructons of the test. Students should not be excluded solely because of poor academc performance or normal dscplnary problems. It should be noted that students wth dyslexa, or other such learnng dsabltes, should be accommodated n the test stuaton f possble, rather than excluded. Non-natve language speakers These are students who are unable to read or speak the language(s) of the test and would be unable to overcome the language barrer n the test stuaton. Typcally, a student who has receved less than one year of nstructon n the language(s) of the test should be excluded. Because dsablty crtera vary from country to country, NRCs are asked to translate the TIMSS and PIRLS nternatonal excluson standards nto the local equvalent. Students should be consdered for excluson strctly n accordance wth the nternatonal standards. If a sampled school contans a class consstng entrely of students from one of the excluson categores, such a class s excluded pror to classroom samplng. NRCs understand that excluson rates must be kept to a mnmum n order that natonal samples accurately represent the natonal target populaton. The overall number of excluded students must not account for more than 5% of the natonal target populaton of students n a country. The overall number ncludes both school-level and wthn-school exclusons. The number of students excluded because they attend very small schools must not account for more than 2% of the natonal target populaton of students. To document populaton coverage and exclusons, each NRC completes Samplng Form 2, whch lsts the number of students n the natonal target populaton and the number of students excluded at both the school level and wthn the school for each populaton to be assessed. (To vew an example of a completed Samplng Form 2 for TIMSS and PIRLS n 2011, please clck here.) Requrements for Samplng the Target Populaton TIMSS & PIRLS set hgh standards for samplng precson, partcpaton rates and sample mplementaton n order to acheve natonal samples of the hghest qualty and survey estmates that are unbased, accurate and nternatonally comparable. METHODS AND PROCEDURES 6 SAMPLING IMPLEMENTATION

7 SAMPLING PRECISION AND SAMPLE SIZE Because TIMSS and PIRLS are fundamentally studes of student achevement, the precson of estmates of student achevement s of prmary mportance. To meet the TIMSS & PIRLS standards for samplng precson, natonal student samples should provde for a standard error no greater than.035 standard devaton unts for the country s mean achevement. Wth a standard devaton of 100 on the TIMSS and PIRLS achevement scales, ths standard error corresponds to a 95% confdence nterval of ± 7 score ponts for the achevement mean and of ± 10 score ponts for the dfference between achevement means from successve cycles (e.g., the dfference between a country s achevement mean on TIMSS 2007 and TIMSS 2011). Sample estmates of any student-level percentage estmate (e.g., a student background characterstc) should have a confdence ntervals of ± 3.5%. For most countres, the TIMSS and PIRLS precson requrements are met wth a school sample of 150 schools and a student sample of 4,000 students for each target grade. Dependng on the average class sze n the country, one class from each sampled school may be suffcent to acheve the desred student sample sze. For example, f the average class sze n a country were 27 students, a sngle class from each of 150 schools would provde a sample of 4,050 students (assumng full partcpaton by schools and students). Some countres choose to sample more than one class per school, ether to ncrease the sze of the student sample or to provde a better estmate of school-level effects. A school sample larger than the mnmum of 150 schools may be requred under the followng crcumstances: The average class sze n a country s so small that, even when samplng more than one classroom per school, t s not possble to reach the student sample sze requrements by selectng only 150 schools. Prevous cycles of TIMSS and/or PIRLS showed that the samplng precson requrements cannot be met unless a larger school sample s selected. Classes wthn schools are tracked by student performance (more common at eghth grade than at fourth grade). Ths ncreases varaton between classes n student achevement and can reduce samplng precson. In ths stuaton, t s advsable to sample at least two classrooms per school whenever possble, n addton to samplng more schools. A hgh level of non-response s antcpated, leadng to sample attrton and reduced sample sze. Note that whle a larger school sample helps to SAMPLING IMPLEMENTATION 7

8 mantan sample sze n the face of non-response, t does not compensate for non-response bas. Feld Test Sample The school sample for the feld test for TIMSS and PIRLS s drawn at the same tme and from the same populaton of schools as the full sample. The feld test sample sze requrement s 200 students per feld test achevement booklet. The total feld test sample sze s a functon of the number of achevement booklets beng feld tested. Typcally, PIRLS has four feld test booklets and so requres a feld test sample of 800 students, whereas TIMSS wth sx booklets requres a sample of 1200 students at each grade. PARTICIPATION RATES To mnmze the potental for non-response bas, PIRLS and TIMSS am for 100% partcpaton by sampled schools, classrooms and students, whle recognzng that some degree of non partcpaton may be unavodable. For a natonal sample to be fully acceptable t must have ether: A mnmum school partcpaton rate of 85%, based on orgnally sampled schools; AND A mnmum classroom partcpaton rate of 95%, from orgnally sampled schools and replacement schools; AND A mnmum student partcpaton rate of 85%, from sampled schools and replacement schools; OR A mnmum combned school, classroom and student partcpaton rate of 75%, based on orgnally sampled schools (although classroom and student partcpaton rates may nclude replacement schools). Classrooms wth less than 50% student partcpaton are deemed to be not partcpatng. Developng and Implementng the Natonal Samplng Plan Although Natonal Research Coordnators are responsble for developng and mplementng natonal samplng plans, Statstcs Canada and the IEA DPC work closely wth NRCs to help ensure that these samplng plans fully meet the standards set by the TIMSS & PIRLS Internatonal Study Center, whle also adaptng to natonal crcumstances and requrements. Natonal samplng plans must be based on the nternatonal two-stage sample desgn (schools METHODS AND PROCEDURES 8 SAMPLING IMPLEMENTATION

9 as the frst stage and classes wthn schools as the second stage) and must be approved by Statstcs Canada. (For more nformaton about the TIMSS & PIRLS nternatonal sample desgn, please clck here.) Stratfcaton Stratfcaton conssts of arrangng the schools n the target populaton nto groups, or strata, that share common characterstcs such as geographc regon or school type. Examples of stratfcaton varables used n TIMSS and PIRLS nclude regon of the country (e.g., states or provnces); school type or source of fundng (e.g., publc or prvate); language of nstructon; level of urbanzaton (e.g., urban or rural area); soco-economc ndcators; and school performance on natonal examnatons. In TIMSS and PIRLS, stratfcaton s used to: Improve the effcency of the sample desgn, thereby makng survey estmates more relable; Apply dfferent sample desgns, such as dsproportonate sample allocatons, to specfc groups of schools (e.g., those n certan states or provnces); Ensure proportonal representaton of specfc groups of schools n the sample. School stratfcaton can take two forms: explct and mplct. In explct stratfcaton, a separate school lst or samplng frame s constructed for each stratum and a sample of schools s drawn from that stratum. In TIMSS and PIRLS, the maor reason for consderng explct stratfcaton s dsproportonate allocaton of the school sample across strata. For example, n order to produce equally relable estmates for each geographc regon n a country, explct stratfcaton by regon may be used to ensure the same number of schools n the sample for each regon, regardless of the relatve populaton sze of the regons. Implct stratfcaton conssts of sortng the schools by one or more stratfcaton varables wthn each explct stratum, or wthn the entre samplng frame f explct stratfcaton s not used. The combned use of mplct strata and systematc samplng s a very effectve and smple way of ensurng a proportonal sample allocaton of students across all mplct strata. Implct stratfcaton also can lead to mproved relablty of achevement estmates, provded the mplct stratfcaton varables are correlated wth student achevement. (To SAMPLING IMPLEMENTATION 9

10 vew a summary of the stratfcaton varables used by countres n TIMSS & PIRLS n 2011, please clck here.) Natonal Research Coordnators consult wth Statstcs Canada and the IEA DPC to dentfy the stratfcaton varables to be ncluded n ther samplng plans. The school samplng frame s sorted by the stratfcaton varables pror to samplng schools so that adacent schools are as smlar as possble. Regardless of any other explct or mplct varables that may be used, the school sze s always ncluded as an mplct stratfcaton varable. To document the stratfcaton varables used n ther samplng plans, each NRC completes Samplng Form 3, whch lsts the varables to be used for explct and mplct stratfcaton, and the number of levels of each stratfcaton varable. (To vew an example of a completed Samplng Form 3 for TIMSS and PIRLS n 2011, please clck here.) School Samplng Frame One of the Natonal Research Coordnator s most mportant samplng tasks s the constructon of a school samplng frame for the target populaton. The samplng frame s a lst of all schools n the country that have students enrolled n the target grade, and s the lst from whch the school sample s drawn. A wellconstructed samplng frame provdes complete coverage of the natonal target populaton wthout beng contamnated by ncorrect or duplcate entres or entres that refer to elements that are not part of the defned target populaton. If the natonal samplng plan calls for explct stratfcaton, there should be a separate samplng frame for each explct stratum. A sutable school measure of sze (MOS) s a crtcal aspect of the natonal samplng plan, because the sze of the school determnes the school s probablty of selecton. The most approprate school measure of sze s an up-to-date count of the number of students n the target grade. If the number of students n the target grade s not avalable, the total student enrolment n the school may be the best avalable substtute. Samplng Form 4 provdes some basc nformaton about the school samplng frame, ncludng the average class sze at the target grade, the number of classrooms to be sampled per school, the school measure of sze (MOS) to be used for school samplng, and the school year for whch the frame was constructed. (To vew an example of a completed Samplng Form 4 for TIMSS and PIRLS n 2011, please clck here.) The school samplng frame s usually a spreadsheet contanng a sngle METHODS AND PROCEDURES 10 SAMPLING IMPLEMENTATION

11 entry for each school. Ths entry ncludes a unque dentfcaton number and contact nformaton (f approprate gven the country s prvacy laws), the values of the stratfcaton varables for the school, and the school measure of sze. It s useful f the school entry also ncludes the number of classes n the school n the target grade because ths provdes a mechansm for predctng n advance the sze of the eventual student sample. Ths predcted sample sze may be compared wth the eventual student sample sze as a check on the samplng process. For an example of a partal samplng frame for a country assessng TIMSS 2011 at the eghth grade, please clck here. In ths example, regon and urbanzaton could be used as stratfcaton varables. Samplng Schools Once the school samplng frame s structured to meet all nternatonal and natonal requrements, Statstcs Canada can draw the school sample. If the samplng frame s explctly stratfed, t s necessary to decde how the school sample s to be allocated among the explct strata (.e., the number of schools to be sampled n each stratum.) When ths has been decded, a sample of schools s selected wthn each explct stratum usng systematc samplng wth probabltes proportonal to sze. (For a descrpton of the school samplng procedure, please clck here.) The PPS technque means that the larger schools, those wth more students, have a hgher probablty of beng sampled than the smaller schools. However, ths dfference n the selecton probabltes of larger and smaller schools s largely offset at the second stage of samplng by selectng a fxed number of classes (usually one or two) wth equal probablty from the sampled school. Classes n large schools wth many classes at the target grade have a lower probablty of selecton than classes n smaller schools that have ust one or two classes. Even though the feld test s scheduled n the school year before the year of data collecton n most countres, the preferred approach n TIMSS and PIRLS s to select both samples of schools at the same tme. Ths ensures that both the feld test and data collecton samples consttute random samples representatve of all schools n the country, and that no school s selected for both samples. Replacement Schools Although deally all schools sampled for TIMSS and PIRLS should partcpate n the assessments, and although NRCs work hard to acheve ths goal, t s antcpated that a 100 percent partcpaton rate may not be possble n all countres. To avod sample sze losses, the samplng plan dentfes, a pror specfc replacement schools for each sampled school. Each SAMPLING IMPLEMENTATION 11

12 orgnally sampled school has two pre-assgned replacement schools, usually the school mmedately precedng the orgnally sampled school on the school samplng frame and the one mmedately followng t. Replacement schools always belong to the same explct stratum as the orgnal, but although they may come from dfferent mplct strata f the school they are replacng s ether the frst or last school of an mplct stratum. The man ustfcaton for replacement schools n TIMSS and PIRLS s to ensure adequate sample szes for analyss of subpopulaton dfferences. Although the use of replacement schools does not elmnate the rsk of bas due to school nonpartcpaton, employng mplct stratfcaton and orderng the school samplng frame by school sze ncreases the chances that a sampled school s replacements would have smlar characterstcs. Ths approach mantans the desred sample sze whle restrctng replacement schools to strata where nonresponse occurs. Snce the school frame s ordered by school sze, replacement schools also tend to be smlar n sze to the school they are desgnated to replace. NRCs understand that they should make every effort to secure the partcpaton of all of the sampled schools and that only after all attempts to persuade a sampled school to partcpate have faled should the use of ts replacement school be consdered. Samplng Classes Wthn each sampled school, all classes wth students at the target grade are lsted, and one or more ntact classes are selected wth equal probablty of selecton usng systematc random samplng. Ths procedure s mplemented usng the WnW3S samplng software. The selecton of classes wth equal probablty, combned wth the PPS samplng method for schools, n general results n a self-weghtng student sample. If the school has mult-grade classes (.e., the class contans students from more than one grade level), only students from the target grade are elgble for samplng. Because small classes tend to ncrease the rsk of unrelable survey estmates and can lead to reduced overall student sample sze, t s necessary to avod samplng too many small classes. Based on consderaton of the sze dstrbuton of classes and the average class sze, a lower class sze lmt or mnmum class sze (MCS) s specfed for each country. Pror to samplng classes n a school, any class smaller than the MCS s combned wth another class n the school to form a pseudoclass for samplng purposes. The procedure for samplng classes METHODS AND PROCEDURES 12 SAMPLING IMPLEMENTATION

13 wthn schools s descrbed n more detal n Survey Operatons and Qualty Assurance. Samplng Weghts Natonal student samples n TIMSS and PIRLS are desgned to accurately represent the target populatons wthn a specfed margn of samplng error, as descrbed prevously. After the data have been collected and processed, sample statstcs such as means and percentages that descrbe student characterstcs are computed as weghted estmates of the correspondng populaton parameters, where the weghtng factor s the samplng weght. A student s samplng weght s essentally the nverse of the student s probablty of selecton, wth approprate adustments for nonresponse. In prncple, the stratfed two-stage samplng procedure used n TIMSS and PIRLS, where schools are sampled wth probablty proportonal to school sze and classes are sampled wth probablty nversely proportonal to school sze, provdes student samples wth equal selecton probabltes. However, n practce dsproportonate samplng across explct strata varyng the number of classes selected, and dfferental patterns of nonresponse can result n varyng selecton probabltes, requrng a unque samplng weght for the students n each partcpatng class n the study. The student samplng weght n TIMSS and PIRLS s a combnaton of weghtng components reflectng selecton probabltes and samplng outcomes at three levels school, class, and student. At each level, the weghtng component conssts of a basc weght that s the nverse of the probablty of selecton at that level, together wth an adustment for nonpartcpaton. The overall samplng weght for each student s the product of the three weghtng components: school, class (wthn school), and student (wthn class). School Weghtng Component Gven that schools n TIMSS and PIRLS are sampled wth probablty proportonal to school sze, the basc school weght for the th sampled school (.e., the nverse of the probablty of the th School beng sampled) s defned as: BW sc M n m where n s the number of sampled schools, m s the measure of sze for the th school, and N M m 1 SAMPLING IMPLEMENTATION 13

14 where N s the total number of schools n the explct stratum. 1 School Nonpartcpaton Adustment If a sampled school does not partcpate n TIMSS or PIRLS and nether does ether of ts two desgnated replacement schools, t s necessary to adust the basc school weght to compensate for the reducton n sample sze. The school-level nonpartcpaton adustment s calculated separately for each explct stratum, as follows: A sc n + n 1 + n 2 + n n + n + n s r r nr s r1 r2 where n s s the number of orgnally sampled schools that partcpated, n r1 and n r2 the number of frst and second replacement schools, respectvely, that partcpated, and n nr s the number of schools that dd not partcpate. Sampled schools that are found to be nelgble 2 are not ncluded n the calculaton of ths adustment. In countres where the TIMSS or PIRLS sample s a census of all schools n the target grades (e.g., Bahran, Cyprus, Kuwat, Malta, and Qatar), the followng school-level adustment s used: A sc m s + m m where m s s the sum of the measures of sze (number of students) from schools that partcpated and m nr the sum of the measures of sze from schools that dd not partcpate. Combnng the basc school weght and the school nonpartcpaton adustment, the fnal school weghtng component for the th school becomes: s nr FWsc Asc BWsc It should be noted that, as well as beng a crucal component of the overall student weght, the fnal school weghtng component s a samplng weght n ts own rght, and should be used n analyses where the school s the analytc unt. Class Weghtng Component The class weghtng component reflects the class-wthn-school selecton 1 For countres such as the Russan Federaton that nclude a prelmnary samplng stage, the basc school weght also ncorporates the probablty of selecton n ths prelmnary stage. The basc school weght n such cases s the product of the prelmnary stage weght and the school weght. 2 A sampled school s nelgble f t s found to contan no elgble students (.e., no students n the target grade). Such schools usually are n the samplng frame by mstake or are schools that recently have closed. METHODS AND PROCEDURES 14 SAMPLING IMPLEMENTATION

15 probablty. After a school has been sampled and has agreed to partcpate n TIMSS or PIRLS, one or two classes are sampled wth equal probablty from the lst of all classes n the school at the target grade. Because larger schools have more classes from whch to sample than smaller schools, the probablty of class selecton vares wth school sze, wth students n small schools more lkely to have ther class selected than students n large schools. Ths relatvely greater selecton probablty for students n small schools offsets ther lower selecton probablty at the frst stage, where probablty-proportonal-to-sze school samplng results n hgher selecton probabltes for larger schools. The basc class-wthn-school weght for a sampled class s the nverse of the probablty of the class beng selected from all of the classes n ts school. For the th sampled school, let C be the total number of elgble classes and c the number of sampled classes. Usng equal probablty samplng, the basc class weght for all sampled classes n the th school s: BW cl C c For most TIMSS or PIRLS partcpants, c takes the values 1 or 2. Class Nonpartcpaton Adustment Basc class weghts are calculated for all sampled classes n the sampled and replacement schools that partcpate n TIMSS or PIRLS. A class-level nonpartcpaton adustment s appled to compensate for classes that do not partcpate or where the student partcpaton rate s below 50 percent. Such sampled classes are assgned a weght of zero. Class nonpartcpaton adustments are appled at the explct stratum level rather than at the school level to mnmze the rsk of bas. The adustment s calculated as follows: A cl s+ r1+ r2 s+ r1+ r2 δ / c where c s the number of sampled classes n the th school, as defned earler, and d gves the number of partcpatng classes n the th school. Combnng the basc class weght and the class nonpartcpaton adustment, the fnal class weghtng component, assgned to all sampled classes n the th school, becomes: 1 SAMPLING IMPLEMENTATION 15

16 FWcl Acl BWcl Student Weghtng Component The student weghtng component represents the student-wthn-class selecton probablty. The basc student weght s the nverse of the probablty of a student n a sampled class beng selected. In the typcal TIMSS and PIRLS stuaton where ntact classes are sampled, all students n the class are ncluded, and so ths probablty s unty. However, under certan crcumstances, students may be sampled wthn the class, wth probablty less than unty. For an ntact class wth no student subsamplng, the basc student weght for the th class n the th school s computed as follows: BW st For classes wth student subsamplng, the basc student weght for the th class n the th school s: BW n n st rg bs 2 + n, where n rg s the number of students n the th class of the th school selected to partcpate n TIMSS or PIRLS and n bs s the number of students n the class not selected. Adustment for Student Nonpartcpaton The student nonpartcpaton adustment for the th classroom n the th school s calculated as: A s A,, st1 st2 rg rs, + snr srs, where s rs s the number of partcpatng students (.e., students that partcpated n TIMSS or PIRLS and have assessment scores) n the th class of the th school, and s nr s the number of students sampled n ths class and expected to have assessment scores but dd not partcpate n the assessment (for ntact classes, ths wll be the total number of students lsted n the class, not countng excluded students). The fnal student weghtng component for students n the th classroom of the th school s: st std std FW A BW METHODS AND PROCEDURES 16 SAMPLING IMPLEMENTATION

17 where equals 1 when there was no student subsamplng (ntact classes) and 2 when a sample of students was drawn from the students n the class. Overall Student Samplng Weght The overall student samplng weght s the product of the fnal weghtng components for schools, classes, and students, as follows:, sc cl st W FW FW FW All student data reported n the TIMSS or PIRLS nternatonal reports are weghted by the overall student samplng weght, known as TOTWGT n the TIMSS and PIRLS nternatonal databases. Partcpaton Rates Because nonpartcpaton can result n sample bas and msleadng results, t s mportant that the schools, classes, and students that are sampled to partcpate n TIMSS or PIRLS actually take part n the assessments. To show the level of samplng partcpaton n each country, TIMSS and PIRLS calculate both unweghted partcpaton rates (.e., based on smple counts of schools, classes, and students) and weghted partcpaton rates based on the samplng weghts descrbed n the prevous secton. Unweghted partcpaton rates provde a prelmnary ndcator that may be used to montor progress n securng the partcpaton of schools and classes, whereas weghted partcpaton rates are the ultmate measure of samplng partcpaton. TIMSS and PIRLS report weghted and unweghted partcpaton rates for schools, classes, and students, as well as overall partcpaton rates that are a combnaton of all three. To dstngush between partcpaton based solely on orgnally sampled schools and partcpaton that also reles on replacement schools, school and overall partcpaton rates are computed separately for orgnally sampled schools only and for orgnally sampled together wth replacement schools. Unweghted School Partcpaton Rates The unweghted school partcpaton rate s the rato of the number of partcpatng schools to the number of orgnally sampled schools, excludng any sampled schools found to be nelgble. A school s consdered to be SAMPLING IMPLEMENTATION 17

18 a partcpatng school f at least one of ts sampled classes has a student partcpaton rate of at least 50 percent. The two unweghted school partcpaton rates are calculated as follows: sc s unweghted school partcpaton rate for orgnally sampled R unw schools only sc R r unw unweghted school partcpaton rate, ncludng orgnally sampled and frst and second replacement schools. R R sc s unw ns n + n + n + n s r1 r2 nr n + n 1 + n 2 n + n + n + n sc r s r r unw s r1 r2 nr UNWEIGHTED CLASS PARTICIPATION RATE The unweghted class partcpaton rate s the rato of the number of sampled classes that partcpated to the number of classes sampled, as follows: R cl unw s+ rl+ r2 s+ rl+ r2 where c s the number of sampled classes n the th school, and c* s the number of partcpatng classes n the th school. Both summatons are across all partcpatng schools. UNWEIGHTED STUDENT PARTICIPATION RATES The unweghted student partcpaton rate s the rato of the number of students that partcpated n TIMSS or PIRLS to the total number of students n the partcpatng schools and classes. Classes where less than 50 percent of the students partcpate are consdered to be not partcpatng, and so students n such classes also are consdered to be nonpartcpants. The unweghted student partcpaton rate s computed as follows: R st unw s c c * srs, rs, + snr METHODS AND PROCEDURES 18 SAMPLING IMPLEMENTATION

19 OVERALL UNWEIGHTED PARTICIPATION RATES The overall unweghted partcpaton rate s the product of the unweghted school, class, and student partcpaton rates. Because TIMSS and PIRLS compute two versons of the unweghted school partcpaton rate, one based on orgnally sampled schools only and the other ncludng replacements as well as orgnally sampled schools, there also are two overall unweghted partcpaton rates: ov s unweghted overall partcpaton rate for orgnally sampled R unw schools only ov R r unw unweghted overall partcpaton rate, ncludng orgnally sampled and frst and second replacement schools. ov s sc s cl st Runw Runw Runw Runw ov r sc r cl st R R R R unw unw unw unw WEIGHTED SCHOOL PARTICIPATION RATES The weghted school partcpaton rate s the rato of two estmates of the sze of the target student populaton. The numerator s derved from the measure of sze of those sampled schools that partcpated n TIMSS or PIRLS and the denomnator s the weghted estmate of the total student enrollment n the populaton. Weghted school partcpaton rates are computed for orgnally sampled schools and for orgnally sampled and replacement schools combned, as follows: sc R s wtd weghted school partcpaton rate for orgnally sampled schools only sc R r wtd weghted school partcpaton rate, ncludng orgnally sampled and frst and second replacement schools. R R sc s wtd, s+ rl+ r 2 sc r wtd s s+ rl+ r2 s+ rl+ r2 BW FW FW sc FW BW FW sc sc sc cl, FW FW FW cl cl, cl, st, FW FW st, st, FW st Summatons n both the numerator and denomnator are over all respondng students and nclude approprate class and student samplng weghts SAMPLING IMPLEMENTATION 19

20 were used. Note that the basc school weght appears n the numerator, whereas the fnal school weght appears n the denomnator. WEIGHTED CLASS PARTICIPATION RATES The weghted class partcpaton rate s computed as follows: R cl wtd s+ rl+ r2 s+ rl+ r 2 BW BW FW BW sc sc FW cl, cl FW where both the numerator and denomnator were summatons over all respondng students from classes wth at least 50 percent of ther students partcpatng n the study, and the approprate student-level samplng weghts were used. In ths formula, the basc class weght appears n the numerator, whereas the fnal class weght appears n the denomnator. And, the denomnator n ths formula s the same quantty that appears n the numerator of the weghted school partcpaton rate for all schools, whether orgnally sampled or replacement. WEIGHTED STUDENT PARTICIPATION RATES The weghted student partcpaton rate s computed as follows: R st wtd s+ rl+ r2 s+ rl+ r 2 BW BW BW BW sc sc BW cl, cl FW where both the numerator and denomnator are summatons over all respondng students from partcpatng schools. In ths formula, the basc student weght appears n the numerator, whereas the fnal student weght appears n the denomnator. Also, the denomnator n ths formula s the same quantty that appears n the numerator of the weghted class partcpaton rate for all partcpatng schools, whether orgnally sampled or replacement. WEIGHTED OVERALL PARTICIPATION RATES The overall weghted partcpaton rate s the product of the weghted school, class, and student partcpaton rates. Because there are two versons of the weghted school partcpaton rate, one based on orgnally sampled schools st, st, st, st, METHODS AND PROCEDURES 20 SAMPLING IMPLEMENTATION

21 only and the other ncludng replacement as well as orgnally sampled schools, there also are two overall weghted partcpaton rates: ov R s wtd weghted overall partcpaton rate for orgnally sampled schools only ov R r wtd weghted overall partcpaton rate, ncludng sampled, frst and second replacement schools. ov s ov s cl st Rwtd Rwtd Rwtd Rwtd ov r sc r cl st R R R R wtd wtd Weghted school, class, student, and overall partcpaton rates are computed for each TIMSS and PIRLS partcpant usng these procedures. wtd wtd References TIMSS & PIRLS Internatonal Study Center. (2008). TIMSS and PIRLS 2011 survey operatons procedures unt 1: Samplng schools and obtanng ther cooperaton. Chestnut Hll, MA: TIMSS & PIRLS Internatonal Study Center, Boston College. TIMSS & PIRLS Internatonal Study Center. (2009). TIMSS and PIRLS 2011 survey operatons procedures unt 2: Preparng for and conductng the PIRLS 2011 and TIMSS 2011 feld test. Chestnut Hll, MA: TIMSS & PIRLS Internatonal Study Center, Boston College. TIMSS & PIRLS Internatonal Study Center. (2010). TIMSS and PIRLS 2011 survey operatons procedures unt 3: Contactng schools and samplng classes for the TIMSS & PIRLS 2011 data collecton. Chestnut Hll, MA: TIMSS & PIRLS Internatonal Study Center, Boston College. UNESCO. (1999). Operatonal manual for ISCED-1997 (nternatonal standard classfcaton of educaton). Pars: UNESCO Insttute of Statstcs. SAMPLING IMPLEMENTATION 21

Calculation of Sampling Weights

Calculation of Sampling Weights Perre Foy Statstcs Canada 4 Calculaton of Samplng Weghts 4.1 OVERVIEW The basc sample desgn used n TIMSS Populatons 1 and 2 was a two-stage stratfed cluster desgn. 1 The frst stage conssted of a sample

More information

Demographic and Health Surveys Methodology

Demographic and Health Surveys Methodology samplng and household lstng manual Demographc and Health Surveys Methodology Ths document s part of the Demographc and Health Survey s DHS Toolkt of methodology for the MEASURE DHS Phase III project, mplemented

More information

Survey Weighting and the Calculation of Sampling Variance

Survey Weighting and the Calculation of Sampling Variance Survey Weghtng and the Calculaton of Samplng Varance Survey weghtng... 132 Calculatng samplng varance... 138 PISA 2012 TECHNICAL REPORT OECD 2014 131 Survey weghts are requred to facltate analyss of PISA

More information

benefit is 2, paid if the policyholder dies within the year, and probability of death within the year is ).

benefit is 2, paid if the policyholder dies within the year, and probability of death within the year is ). REVIEW OF RISK MANAGEMENT CONCEPTS LOSS DISTRIBUTIONS AND INSURANCE Loss and nsurance: When someone s subject to the rsk of ncurrng a fnancal loss, the loss s generally modeled usng a random varable or

More information

Traffic-light a stress test for life insurance provisions

Traffic-light a stress test for life insurance provisions MEMORANDUM Date 006-09-7 Authors Bengt von Bahr, Göran Ronge Traffc-lght a stress test for lfe nsurance provsons Fnansnspetonen P.O. Box 6750 SE-113 85 Stocholm [Sveavägen 167] Tel +46 8 787 80 00 Fax

More information

Overview of monitoring and evaluation

Overview of monitoring and evaluation 540 Toolkt to Combat Traffckng n Persons Tool 10.1 Overvew of montorng and evaluaton Overvew Ths tool brefly descrbes both montorng and evaluaton, and the dstncton between the two. What s montorng? Montorng

More information

Module 2 LOSSLESS IMAGE COMPRESSION SYSTEMS. Version 2 ECE IIT, Kharagpur

Module 2 LOSSLESS IMAGE COMPRESSION SYSTEMS. Version 2 ECE IIT, Kharagpur Module LOSSLESS IMAGE COMPRESSION SYSTEMS Lesson 3 Lossless Compresson: Huffman Codng Instructonal Objectves At the end of ths lesson, the students should be able to:. Defne and measure source entropy..

More information

CHOLESTEROL REFERENCE METHOD LABORATORY NETWORK. Sample Stability Protocol

CHOLESTEROL REFERENCE METHOD LABORATORY NETWORK. Sample Stability Protocol CHOLESTEROL REFERENCE METHOD LABORATORY NETWORK Sample Stablty Protocol Background The Cholesterol Reference Method Laboratory Network (CRMLN) developed certfcaton protocols for total cholesterol, HDL

More information

1.1 The University may award Higher Doctorate degrees as specified from time-to-time in UPR AS11 1.

1.1 The University may award Higher Doctorate degrees as specified from time-to-time in UPR AS11 1. HIGHER DOCTORATE DEGREES SUMMARY OF PRINCIPAL CHANGES General changes None Secton 3.2 Refer to text (Amendments to verson 03.0, UPR AS02 are shown n talcs.) 1 INTRODUCTION 1.1 The Unversty may award Hgher

More information

An Alternative Way to Measure Private Equity Performance

An Alternative Way to Measure Private Equity Performance An Alternatve Way to Measure Prvate Equty Performance Peter Todd Parlux Investment Technology LLC Summary Internal Rate of Return (IRR) s probably the most common way to measure the performance of prvate

More information

The Development of Web Log Mining Based on Improve-K-Means Clustering Analysis

The Development of Web Log Mining Based on Improve-K-Means Clustering Analysis The Development of Web Log Mnng Based on Improve-K-Means Clusterng Analyss TngZhong Wang * College of Informaton Technology, Luoyang Normal Unversty, Luoyang, 471022, Chna wangtngzhong2@sna.cn Abstract.

More information

Proceedings of the Annual Meeting of the American Statistical Association, August 5-9, 2001

Proceedings of the Annual Meeting of the American Statistical Association, August 5-9, 2001 Proceedngs of the Annual Meetng of the Amercan Statstcal Assocaton, August 5-9, 2001 LIST-ASSISTED SAMPLING: THE EFFECT OF TELEPHONE SYSTEM CHANGES ON DESIGN 1 Clyde Tucker, Bureau of Labor Statstcs James

More information

The OC Curve of Attribute Acceptance Plans

The OC Curve of Attribute Acceptance Plans The OC Curve of Attrbute Acceptance Plans The Operatng Characterstc (OC) curve descrbes the probablty of acceptng a lot as a functon of the lot s qualty. Fgure 1 shows a typcal OC Curve. 10 8 6 4 1 3 4

More information

Capacity-building and training

Capacity-building and training 92 Toolkt to Combat Traffckng n Persons Tool 2.14 Capacty-buldng and tranng Overvew Ths tool provdes references to tranng programmes and materals. For more tranng materals, refer also to Tool 9.18. Capacty-buldng

More information

DEFINING %COMPLETE IN MICROSOFT PROJECT

DEFINING %COMPLETE IN MICROSOFT PROJECT CelersSystems DEFINING %COMPLETE IN MICROSOFT PROJECT PREPARED BY James E Aksel, PMP, PMI-SP, MVP For Addtonal Informaton about Earned Value Management Systems and reportng, please contact: CelersSystems,

More information

To manage leave, meeting institutional requirements and treating individual staff members fairly and consistently.

To manage leave, meeting institutional requirements and treating individual staff members fairly and consistently. Corporate Polces & Procedures Human Resources - Document CPP216 Leave Management Frst Produced: Current Verson: Past Revsons: Revew Cycle: Apples From: 09/09/09 26/10/12 09/09/09 3 years Immedately Authorsaton:

More information

Can Auto Liability Insurance Purchases Signal Risk Attitude?

Can Auto Liability Insurance Purchases Signal Risk Attitude? Internatonal Journal of Busness and Economcs, 2011, Vol. 10, No. 2, 159-164 Can Auto Lablty Insurance Purchases Sgnal Rsk Atttude? Chu-Shu L Department of Internatonal Busness, Asa Unversty, Tawan Sheng-Chang

More information

Hollinger Canadian Publishing Holdings Co. ( HCPH ) proceeding under the Companies Creditors Arrangement Act ( CCAA )

Hollinger Canadian Publishing Holdings Co. ( HCPH ) proceeding under the Companies Creditors Arrangement Act ( CCAA ) February 17, 2011 Andrew J. Hatnay ahatnay@kmlaw.ca Dear Sr/Madam: Re: Re: Hollnger Canadan Publshng Holdngs Co. ( HCPH ) proceedng under the Companes Credtors Arrangement Act ( CCAA ) Update on CCAA Proceedngs

More information

Reporting Forms ARF 113.0A, ARF 113.0B, ARF 113.0C and ARF 113.0D FIRB Corporate (including SME Corporate), Sovereign and Bank Instruction Guide

Reporting Forms ARF 113.0A, ARF 113.0B, ARF 113.0C and ARF 113.0D FIRB Corporate (including SME Corporate), Sovereign and Bank Instruction Guide Reportng Forms ARF 113.0A, ARF 113.0B, ARF 113.0C and ARF 113.0D FIRB Corporate (ncludng SME Corporate), Soveregn and Bank Instructon Gude Ths nstructon gude s desgned to assst n the completon of the FIRB

More information

ANALYZING THE RELATIONSHIPS BETWEEN QUALITY, TIME, AND COST IN PROJECT MANAGEMENT DECISION MAKING

ANALYZING THE RELATIONSHIPS BETWEEN QUALITY, TIME, AND COST IN PROJECT MANAGEMENT DECISION MAKING ANALYZING THE RELATIONSHIPS BETWEEN QUALITY, TIME, AND COST IN PROJECT MANAGEMENT DECISION MAKING Matthew J. Lberatore, Department of Management and Operatons, Vllanova Unversty, Vllanova, PA 19085, 610-519-4390,

More information

Instructions for Analyzing Data from CAHPS Surveys:

Instructions for Analyzing Data from CAHPS Surveys: Instructons for Analyzng Data from CAHPS Surveys: Usng the CAHPS Analyss Program Verson 4.1 Purpose of ths Document...1 The CAHPS Analyss Program...1 Computng Requrements...1 Pre-Analyss Decsons...2 What

More information

How To Understand The Results Of The German Meris Cloud And Water Vapour Product

How To Understand The Results Of The German Meris Cloud And Water Vapour Product Ttel: Project: Doc. No.: MERIS level 3 cloud and water vapour products MAPP MAPP-ATBD-ClWVL3 Issue: 1 Revson: 0 Date: 9.12.1998 Functon Name Organsaton Sgnature Date Author: Bennartz FUB Preusker FUB Schüller

More information

Statistical algorithms in Review Manager 5

Statistical algorithms in Review Manager 5 Statstcal algorthms n Reve Manager 5 Jonathan J Deeks and Julan PT Hggns on behalf of the Statstcal Methods Group of The Cochrane Collaboraton August 00 Data structure Consder a meta-analyss of k studes

More information

The program for the Bachelor degrees shall extend over three years of full-time study or the parttime equivalent.

The program for the Bachelor degrees shall extend over three years of full-time study or the parttime equivalent. Bachel of Commerce Bachel of Commerce (Accountng) Bachel of Commerce (Cpate Fnance) Bachel of Commerce (Internatonal Busness) Bachel of Commerce (Management) Bachel of Commerce (Marketng) These Program

More information

Enhancing the Quality of Price Indexes A Sampling Perspective

Enhancing the Quality of Price Indexes A Sampling Perspective Enhancng the Qualty of Prce Indexes A Samplng Perspectve Jack Lothan 1 and Zdenek Patak 2 Statstcs Canada 1 Statstcs Canada 2 Abstract Wth the release of the Boskn Report (Boskn et al., 1996) on the state

More information

Course outline. Financial Time Series Analysis. Overview. Data analysis. Predictive signal. Trading strategy

Course outline. Financial Time Series Analysis. Overview. Data analysis. Predictive signal. Trading strategy Fnancal Tme Seres Analyss Patrck McSharry patrck@mcsharry.net www.mcsharry.net Trnty Term 2014 Mathematcal Insttute Unversty of Oxford Course outlne 1. Data analyss, probablty, correlatons, vsualsaton

More information

Analysis of Premium Liabilities for Australian Lines of Business

Analysis of Premium Liabilities for Australian Lines of Business Summary of Analyss of Premum Labltes for Australan Lnes of Busness Emly Tao Honours Research Paper, The Unversty of Melbourne Emly Tao Acknowledgements I am grateful to the Australan Prudental Regulaton

More information

Fixed income risk attribution

Fixed income risk attribution 5 Fxed ncome rsk attrbuton Chthra Krshnamurth RskMetrcs Group chthra.krshnamurth@rskmetrcs.com We compare the rsk of the actve portfolo wth that of the benchmark and segment the dfference between the two

More information

FREQUENCY OF OCCURRENCE OF CERTAIN CHEMICAL CLASSES OF GSR FROM VARIOUS AMMUNITION TYPES

FREQUENCY OF OCCURRENCE OF CERTAIN CHEMICAL CLASSES OF GSR FROM VARIOUS AMMUNITION TYPES FREQUENCY OF OCCURRENCE OF CERTAIN CHEMICAL CLASSES OF GSR FROM VARIOUS AMMUNITION TYPES Zuzanna BRO EK-MUCHA, Grzegorz ZADORA, 2 Insttute of Forensc Research, Cracow, Poland 2 Faculty of Chemstry, Jagellonan

More information

The Current Employment Statistics (CES) survey,

The Current Employment Statistics (CES) survey, Busness Brths and Deaths Impact of busness brths and deaths n the payroll survey The CES probablty-based sample redesgn accounts for most busness brth employment through the mputaton of busness deaths,

More information

Assessment of the legal framework

Assessment of the legal framework 46 Toolkt to Combat Traffckng n Persons Tool 2.4 Assessment of the legal framework Overvew Ths tool offers gudelnes and resources for assessng a natonal legal framework. See also Tool 3.2 on crmnalzaton

More information

Construction Rules for Morningstar Canada Target Dividend Index SM

Construction Rules for Morningstar Canada Target Dividend Index SM Constructon Rules for Mornngstar Canada Target Dvdend Index SM Mornngstar Methodology Paper October 2014 Verson 1.2 2014 Mornngstar, Inc. All rghts reserved. The nformaton n ths document s the property

More information

Institute of Informatics, Faculty of Business and Management, Brno University of Technology,Czech Republic

Institute of Informatics, Faculty of Business and Management, Brno University of Technology,Czech Republic Lagrange Multplers as Quanttatve Indcators n Economcs Ivan Mezník Insttute of Informatcs, Faculty of Busness and Management, Brno Unversty of TechnologCzech Republc Abstract The quanttatve role of Lagrange

More information

Traffic-light extended with stress test for insurance and expense risks in life insurance

Traffic-light extended with stress test for insurance and expense risks in life insurance PROMEMORIA Datum 0 July 007 FI Dnr 07-1171-30 Fnansnspetonen Författare Bengt von Bahr, Göran Ronge Traffc-lght extended wth stress test for nsurance and expense rss n lfe nsurance Summary Ths memorandum

More information

Assessing the Fairness of a Firm s Allocation of Shares in Initial Public Offerings: Adapting a Measure from Biostatistics

Assessing the Fairness of a Firm s Allocation of Shares in Initial Public Offerings: Adapting a Measure from Biostatistics Assessng the Farness of a Frm s Allocaton of Shares n Intal Publc Offerngs: Adaptng a Measure from Bostatstcs by Efstatha Bura and Joseph L. Gastwrth Department of Statstcs The George Washngton Unversty

More information

Staff Paper. Farm Savings Accounts: Examining Income Variability, Eligibility, and Benefits. Brent Gloy, Eddy LaDue, and Charles Cuykendall

Staff Paper. Farm Savings Accounts: Examining Income Variability, Eligibility, and Benefits. Brent Gloy, Eddy LaDue, and Charles Cuykendall SP 2005-02 August 2005 Staff Paper Department of Appled Economcs and Management Cornell Unversty, Ithaca, New York 14853-7801 USA Farm Savngs Accounts: Examnng Income Varablty, Elgblty, and Benefts Brent

More information

Traffic State Estimation in the Traffic Management Center of Berlin

Traffic State Estimation in the Traffic Management Center of Berlin Traffc State Estmaton n the Traffc Management Center of Berln Authors: Peter Vortsch, PTV AG, Stumpfstrasse, D-763 Karlsruhe, Germany phone ++49/72/965/35, emal peter.vortsch@ptv.de Peter Möhl, PTV AG,

More information

CHAPTER 14 MORE ABOUT REGRESSION

CHAPTER 14 MORE ABOUT REGRESSION CHAPTER 14 MORE ABOUT REGRESSION We learned n Chapter 5 that often a straght lne descrbes the pattern of a relatonshp between two quanttatve varables. For nstance, n Example 5.1 we explored the relatonshp

More information

Project Networks With Mixed-Time Constraints

Project Networks With Mixed-Time Constraints Project Networs Wth Mxed-Tme Constrants L Caccetta and B Wattananon Western Australan Centre of Excellence n Industral Optmsaton (WACEIO) Curtn Unversty of Technology GPO Box U1987 Perth Western Australa

More information

Risk-based Fatigue Estimate of Deep Water Risers -- Course Project for EM388F: Fracture Mechanics, Spring 2008

Risk-based Fatigue Estimate of Deep Water Risers -- Course Project for EM388F: Fracture Mechanics, Spring 2008 Rsk-based Fatgue Estmate of Deep Water Rsers -- Course Project for EM388F: Fracture Mechancs, Sprng 2008 Chen Sh Department of Cvl, Archtectural, and Envronmental Engneerng The Unversty of Texas at Austn

More information

LAW ENFORCEMENT TRAINING TOOLS. Training tools for law enforcement officials and the judiciary

LAW ENFORCEMENT TRAINING TOOLS. Training tools for law enforcement officials and the judiciary chapter 5 Law enforcement and prosecuton 261 LAW ENFORCEMENT TRAINING TOOLS Tool 5.20 Tranng tools for law enforcement offcals and the judcary Overvew Ths tool recommends resources for tranng law enforcement

More information

Computer-assisted Auditing for High- Volume Medical Coding

Computer-assisted Auditing for High- Volume Medical Coding Computer-asssted Audtng for Hgh-Volume Medcal Codng Computer-asssted Audtng for Hgh- Volume Medcal Codng by Danel T. Henze, PhD; Peter Feller, MS; Jerry McCorkle, BA; and Mark Morsch, MS Abstract The volume

More information

Study on Model of Risks Assessment of Standard Operation in Rural Power Network

Study on Model of Risks Assessment of Standard Operation in Rural Power Network Study on Model of Rsks Assessment of Standard Operaton n Rural Power Network Qngj L 1, Tao Yang 2 1 Qngj L, College of Informaton and Electrcal Engneerng, Shenyang Agrculture Unversty, Shenyang 110866,

More information

What is Candidate Sampling

What is Candidate Sampling What s Canddate Samplng Say we have a multclass or mult label problem where each tranng example ( x, T ) conssts of a context x a small (mult)set of target classes T out of a large unverse L of possble

More information

Multiple-Period Attribution: Residuals and Compounding

Multiple-Period Attribution: Residuals and Compounding Multple-Perod Attrbuton: Resduals and Compoundng Our revewer gave these authors full marks for dealng wth an ssue that performance measurers and vendors often regard as propretary nformaton. In 1994, Dens

More information

Data Mining from the Information Systems: Performance Indicators at Masaryk University in Brno

Data Mining from the Information Systems: Performance Indicators at Masaryk University in Brno Data Mnng from the Informaton Systems: Performance Indcators at Masaryk Unversty n Brno Mkuláš Bek EUA Workshop Strasbourg, 1-2 December 2006 1 Locaton of Brno Brno EUA Workshop Strasbourg, 1-2 December

More information

Screening Tools Chart As of November 2011

Screening Tools Chart As of November 2011 Screenng Chart As of November 2011 Ths tools chart reflects the results of the fourth annual revew of screenng tools by the Center s Techncal Revew Commttee (TRC). The Center defnes screenng as follows:

More information

Design and Development of a Security Evaluation Platform Based on International Standards

Design and Development of a Security Evaluation Platform Based on International Standards Internatonal Journal of Informatcs Socety, VOL.5, NO.2 (203) 7-80 7 Desgn and Development of a Securty Evaluaton Platform Based on Internatonal Standards Yuj Takahash and Yoshm Teshgawara Graduate School

More information

Start me up: The Effectiveness of a Self-Employment Programme for Needy Unemployed People in Germany*

Start me up: The Effectiveness of a Self-Employment Programme for Needy Unemployed People in Germany* Start me up: The Effectveness of a Self-Employment Programme for Needy Unemployed People n Germany* Joachm Wolff Anton Nvorozhkn Date: 22/10/2008 Abstract In recent years actvaton of means-tested unemployment

More information

An Evaluation of the Extended Logistic, Simple Logistic, and Gompertz Models for Forecasting Short Lifecycle Products and Services

An Evaluation of the Extended Logistic, Simple Logistic, and Gompertz Models for Forecasting Short Lifecycle Products and Services An Evaluaton of the Extended Logstc, Smple Logstc, and Gompertz Models for Forecastng Short Lfecycle Products and Servces Charles V. Trappey a,1, Hsn-yng Wu b a Professor (Management Scence), Natonal Chao

More information

Answer: A). There is a flatter IS curve in the high MPC economy. Original LM LM after increase in M. IS curve for low MPC economy

Answer: A). There is a flatter IS curve in the high MPC economy. Original LM LM after increase in M. IS curve for low MPC economy 4.02 Quz Solutons Fall 2004 Multple-Choce Questons (30/00 ponts) Please, crcle the correct answer for each of the followng 0 multple-choce questons. For each queston, only one of the answers s correct.

More information

A DYNAMIC CRASHING METHOD FOR PROJECT MANAGEMENT USING SIMULATION-BASED OPTIMIZATION. Michael E. Kuhl Radhamés A. Tolentino-Peña

A DYNAMIC CRASHING METHOD FOR PROJECT MANAGEMENT USING SIMULATION-BASED OPTIMIZATION. Michael E. Kuhl Radhamés A. Tolentino-Peña Proceedngs of the 2008 Wnter Smulaton Conference S. J. Mason, R. R. Hll, L. Mönch, O. Rose, T. Jefferson, J. W. Fowler eds. A DYNAMIC CRASHING METHOD FOR PROJECT MANAGEMENT USING SIMULATION-BASED OPTIMIZATION

More information

Small pots lump sum payment instruction

Small pots lump sum payment instruction For customers Small pots lump sum payment nstructon Please read these notes before completng ths nstructon About ths nstructon Use ths nstructon f you re an ndvdual wth Aegon Retrement Choces Self Invested

More information

PRIVATE SCHOOL CHOICE: THE EFFECTS OF RELIGIOUS AFFILIATION AND PARTICIPATION

PRIVATE SCHOOL CHOICE: THE EFFECTS OF RELIGIOUS AFFILIATION AND PARTICIPATION PRIVATE SCHOOL CHOICE: THE EFFECTS OF RELIIOUS AFFILIATION AND PARTICIPATION Danny Cohen-Zada Department of Economcs, Ben-uron Unversty, Beer-Sheva 84105, Israel Wllam Sander Department of Economcs, DePaul

More information

A 'Virtual Population' Approach To Small Area Estimation

A 'Virtual Population' Approach To Small Area Estimation A 'Vrtual Populaton' Approach To Small Area Estmaton Mchael P. Battagla 1, Martn R. Frankel 2, Machell Town 3 and Lna S. Balluz 3 1 Abt Assocates Inc., Cambrdge MA 02138 2 Baruch College, CUNY, New York

More information

RELIABILITY, RISK AND AVAILABILITY ANLYSIS OF A CONTAINER GANTRY CRANE ABSTRACT

RELIABILITY, RISK AND AVAILABILITY ANLYSIS OF A CONTAINER GANTRY CRANE ABSTRACT Kolowrock Krzysztof Joanna oszynska MODELLING ENVIRONMENT AND INFRATRUCTURE INFLUENCE ON RELIABILITY AND OPERATION RT&A # () (Vol.) March RELIABILITY RIK AND AVAILABILITY ANLYI OF A CONTAINER GANTRY CRANE

More information

Meta-Analysis of Hazard Ratios

Meta-Analysis of Hazard Ratios NCSS Statstcal Softare Chapter 458 Meta-Analyss of Hazard Ratos Introducton Ths module performs a meta-analyss on a set of to-group, tme to event (survval), studes n hch some data may be censored. These

More information

THE DISTRIBUTION OF LOAN PORTFOLIO VALUE * Oldrich Alfons Vasicek

THE DISTRIBUTION OF LOAN PORTFOLIO VALUE * Oldrich Alfons Vasicek HE DISRIBUION OF LOAN PORFOLIO VALUE * Oldrch Alfons Vascek he amount of captal necessary to support a portfolo of debt securtes depends on the probablty dstrbuton of the portfolo loss. Consder a portfolo

More information

Protection, assistance and human rights. Recommended Principles and Guidelines on Human Rights and Human Trafficking (E/2002/68/Add.

Protection, assistance and human rights. Recommended Principles and Guidelines on Human Rights and Human Trafficking (E/2002/68/Add. chapter 8 Vctm assstance 385 Tool 8.3 Protecton, assstance and human rghts Overvew Ths tool dscusses the human rghts consderatons whch must be borne n mnd n protectng and assstng vctms of traffckng. Recommended

More information

Implementation of Deutsch's Algorithm Using Mathcad

Implementation of Deutsch's Algorithm Using Mathcad Implementaton of Deutsch's Algorthm Usng Mathcad Frank Roux The followng s a Mathcad mplementaton of Davd Deutsch's quantum computer prototype as presented on pages - n "Machnes, Logc and Quantum Physcs"

More information

Selecting Best Employee of the Year Using Analytical Hierarchy Process

Selecting Best Employee of the Year Using Analytical Hierarchy Process J. Basc. Appl. Sc. Res., 5(11)72-76, 2015 2015, TextRoad Publcaton ISSN 2090-4304 Journal of Basc and Appled Scentfc Research www.textroad.com Selectng Best Employee of the Year Usng Analytcal Herarchy

More information

Time Value of Money Module

Time Value of Money Module Tme Value of Money Module O BJECTIVES After readng ths Module, you wll be able to: Understand smple nterest and compound nterest. 2 Compute and use the future value of a sngle sum. 3 Compute and use the

More information

Number of Levels Cumulative Annual operating Income per year construction costs costs ($) ($) ($) 1 600,000 35,000 100,000 2 2,200,000 60,000 350,000

Number of Levels Cumulative Annual operating Income per year construction costs costs ($) ($) ($) 1 600,000 35,000 100,000 2 2,200,000 60,000 350,000 Problem Set 5 Solutons 1 MIT s consderng buldng a new car park near Kendall Square. o unversty funds are avalable (overhead rates are under pressure and the new faclty would have to pay for tself from

More information

Research on Evaluation of Customer Experience of B2C Ecommerce Logistics Enterprises

Research on Evaluation of Customer Experience of B2C Ecommerce Logistics Enterprises 3rd Internatonal Conference on Educaton, Management, Arts, Economcs and Socal Scence (ICEMAESS 2015) Research on Evaluaton of Customer Experence of B2C Ecommerce Logstcs Enterprses Yle Pe1, a, Wanxn Xue1,

More information

An Interest-Oriented Network Evolution Mechanism for Online Communities

An Interest-Oriented Network Evolution Mechanism for Online Communities An Interest-Orented Network Evoluton Mechansm for Onlne Communtes Cahong Sun and Xaopng Yang School of Informaton, Renmn Unversty of Chna, Bejng 100872, P.R. Chna {chsun,yang}@ruc.edu.cn Abstract. Onlne

More information

Efficient Project Portfolio as a tool for Enterprise Risk Management

Efficient Project Portfolio as a tool for Enterprise Risk Management Effcent Proect Portfolo as a tool for Enterprse Rsk Management Valentn O. Nkonov Ural State Techncal Unversty Growth Traectory Consultng Company January 5, 27 Effcent Proect Portfolo as a tool for Enterprse

More information

One Click.. Ȯne Location.. Ȯne Portal...

One Click.. Ȯne Location.. Ȯne Portal... New Addton to your NJ-HITEC Membershp! Member Portal Detals & Features Insde! One Clck.. Ȯne Locaton.. Ȯne Portal... Connect...Share...Smplfy Health IT Member Portal Benefts Trusted Advsor - NJ-HITEC s

More information

Lecture 2: Single Layer Perceptrons Kevin Swingler

Lecture 2: Single Layer Perceptrons Kevin Swingler Lecture 2: Sngle Layer Perceptrons Kevn Sngler kms@cs.str.ac.uk Recap: McCulloch-Ptts Neuron Ths vastly smplfed model of real neurons s also knon as a Threshold Logc Unt: W 2 A Y 3 n W n. A set of synapses

More information

Objectives How Can Pharmacy Staff Add to the Accountability of ACO s?

Objectives How Can Pharmacy Staff Add to the Accountability of ACO s? Objectves How Can Pharmacy Staff Add to the Accountablty of ACO s? Sandra Van Trease Group Presdent, BJC HealthCare Presdent, BJC HealthCare ACO, LLC The speaker has no conflct of nterest to declare. 1.

More information

NPAR TESTS. One-Sample Chi-Square Test. Cell Specification. Observed Frequencies 1O i 6. Expected Frequencies 1EXP i 6

NPAR TESTS. One-Sample Chi-Square Test. Cell Specification. Observed Frequencies 1O i 6. Expected Frequencies 1EXP i 6 PAR TESTS If a WEIGHT varable s specfed, t s used to replcate a case as many tmes as ndcated by the weght value rounded to the nearest nteger. If the workspace requrements are exceeded and samplng has

More information

A Secure Password-Authenticated Key Agreement Using Smart Cards

A Secure Password-Authenticated Key Agreement Using Smart Cards A Secure Password-Authentcated Key Agreement Usng Smart Cards Ka Chan 1, Wen-Chung Kuo 2 and Jn-Chou Cheng 3 1 Department of Computer and Informaton Scence, R.O.C. Mltary Academy, Kaohsung 83059, Tawan,

More information

The Use of Analytics for Claim Fraud Detection Roosevelt C. Mosley, Jr., FCAS, MAAA Nick Kucera Pinnacle Actuarial Resources Inc.

The Use of Analytics for Claim Fraud Detection Roosevelt C. Mosley, Jr., FCAS, MAAA Nick Kucera Pinnacle Actuarial Resources Inc. Paper 1837-2014 The Use of Analytcs for Clam Fraud Detecton Roosevelt C. Mosley, Jr., FCAS, MAAA Nck Kucera Pnnacle Actuaral Resources Inc., Bloomngton, IL ABSTRACT As t has been wdely reported n the nsurance

More information

MONITORING METHODOLOGY TO ASSESS THE PERFORMANCE OF GSM NETWORKS

MONITORING METHODOLOGY TO ASSESS THE PERFORMANCE OF GSM NETWORKS Electronc Communcatons Commttee (ECC) wthn the European Conference of Postal and Telecommuncatons Admnstratons (CEPT) MONITORING METHODOLOGY TO ASSESS THE PERFORMANCE OF GSM NETWORKS Athens, February 2008

More information

Predicting Software Development Project Outcomes *

Predicting Software Development Project Outcomes * Predctng Software Development Project Outcomes * Rosna Weber, Mchael Waller, June Verner, Wllam Evanco College of Informaton Scence & Technology, Drexel Unversty 3141 Chestnut Street Phladelpha, PA 19104

More information

Feature selection for intrusion detection. Slobodan Petrović NISlab, Gjøvik University College

Feature selection for intrusion detection. Slobodan Petrović NISlab, Gjøvik University College Feature selecton for ntruson detecton Slobodan Petrovć NISlab, Gjøvk Unversty College Contents The feature selecton problem Intruson detecton Traffc features relevant for IDS The CFS measure The mrmr measure

More information

On the Optimal Control of a Cascade of Hydro-Electric Power Stations

On the Optimal Control of a Cascade of Hydro-Electric Power Stations On the Optmal Control of a Cascade of Hydro-Electrc Power Statons M.C.M. Guedes a, A.F. Rbero a, G.V. Smrnov b and S. Vlela c a Department of Mathematcs, School of Scences, Unversty of Porto, Portugal;

More information

Brigid Mullany, Ph.D University of North Carolina, Charlotte

Brigid Mullany, Ph.D University of North Carolina, Charlotte Evaluaton And Comparson Of The Dfferent Standards Used To Defne The Postonal Accuracy And Repeatablty Of Numercally Controlled Machnng Center Axes Brgd Mullany, Ph.D Unversty of North Carolna, Charlotte

More information

Characterization of Assembly. Variation Analysis Methods. A Thesis. Presented to the. Department of Mechanical Engineering. Brigham Young University

Characterization of Assembly. Variation Analysis Methods. A Thesis. Presented to the. Department of Mechanical Engineering. Brigham Young University Characterzaton of Assembly Varaton Analyss Methods A Thess Presented to the Department of Mechancal Engneerng Brgham Young Unversty In Partal Fulfllment of the Requrements for the Degree Master of Scence

More information

7.5. Present Value of an Annuity. Investigate

7.5. Present Value of an Annuity. Investigate 7.5 Present Value of an Annuty Owen and Anna are approachng retrement and are puttng ther fnances n order. They have worked hard and nvested ther earnngs so that they now have a large amount of money on

More information

Marginal Benefit Incidence Analysis Using a Single Cross-section of Data. Mohamed Ihsan Ajwad and Quentin Wodon 1. World Bank.

Marginal Benefit Incidence Analysis Using a Single Cross-section of Data. Mohamed Ihsan Ajwad and Quentin Wodon 1. World Bank. Margnal Beneft Incdence Analyss Usng a Sngle Cross-secton of Data Mohamed Ihsan Ajwad and uentn Wodon World Bank August 200 Abstract In a recent paper, Lanjouw and Ravallon proposed an attractve and smple

More information

7 ANALYSIS OF VARIANCE (ANOVA)

7 ANALYSIS OF VARIANCE (ANOVA) 7 ANALYSIS OF VARIANCE (ANOVA) Chapter 7 Analyss of Varance (Anova) Objectves After studyng ths chapter you should apprecate the need for analysng data from more than two samples; understand the underlyng

More information

How Sets of Coherent Probabilities May Serve as Models for Degrees of Incoherence

How Sets of Coherent Probabilities May Serve as Models for Degrees of Incoherence 1 st Internatonal Symposum on Imprecse Probabltes and Ther Applcatons, Ghent, Belgum, 29 June 2 July 1999 How Sets of Coherent Probabltes May Serve as Models for Degrees of Incoherence Mar J. Schervsh

More information

How To Calculate The Accountng Perod Of Nequalty

How To Calculate The Accountng Perod Of Nequalty Inequalty and The Accountng Perod Quentn Wodon and Shlomo Ytzha World Ban and Hebrew Unversty September Abstract Income nequalty typcally declnes wth the length of tme taen nto account for measurement.

More information

Data Broadcast on a Multi-System Heterogeneous Overlayed Wireless Network *

Data Broadcast on a Multi-System Heterogeneous Overlayed Wireless Network * JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 24, 819-840 (2008) Data Broadcast on a Mult-System Heterogeneous Overlayed Wreless Network * Department of Computer Scence Natonal Chao Tung Unversty Hsnchu,

More information

We assume your students are learning about self-regulation (how to change how alert they feel) through the Alert Program with its three stages:

We assume your students are learning about self-regulation (how to change how alert they feel) through the Alert Program with its three stages: Welcome to ALERT BINGO, a fun-flled and educatonal way to learn the fve ways to change engnes levels (Put somethng n your Mouth, Move, Touch, Look, and Lsten) as descrbed n the How Does Your Engne Run?

More information

IT09 - Identity Management Policy

IT09 - Identity Management Policy IT09 - Identty Management Polcy Introducton 1 The Unersty needs to manage dentty accounts for all users of the Unersty s electronc systems and ensure that users hae an approprate leel of access to these

More information

VRT012 User s guide V0.1. Address: Žirmūnų g. 27, Vilnius LT-09105, Phone: (370-5) 2127472, Fax: (370-5) 276 1380, Email: info@teltonika.

VRT012 User s guide V0.1. Address: Žirmūnų g. 27, Vilnius LT-09105, Phone: (370-5) 2127472, Fax: (370-5) 276 1380, Email: info@teltonika. VRT012 User s gude V0.1 Thank you for purchasng our product. We hope ths user-frendly devce wll be helpful n realsng your deas and brngng comfort to your lfe. Please take few mnutes to read ths manual

More information

Recurrence. 1 Definitions and main statements

Recurrence. 1 Definitions and main statements Recurrence 1 Defntons and man statements Let X n, n = 0, 1, 2,... be a MC wth the state space S = (1, 2,...), transton probabltes p j = P {X n+1 = j X n = }, and the transton matrx P = (p j ),j S def.

More information

Power-of-Two Policies for Single- Warehouse Multi-Retailer Inventory Systems with Order Frequency Discounts

Power-of-Two Policies for Single- Warehouse Multi-Retailer Inventory Systems with Order Frequency Discounts Power-of-wo Polces for Sngle- Warehouse Mult-Retaler Inventory Systems wth Order Frequency Dscounts José A. Ventura Pennsylvana State Unversty (USA) Yale. Herer echnon Israel Insttute of echnology (Israel)

More information

A DATA MINING APPLICATION IN A STUDENT DATABASE

A DATA MINING APPLICATION IN A STUDENT DATABASE JOURNAL OF AERONAUTICS AND SPACE TECHNOLOGIES JULY 005 VOLUME NUMBER (53-57) A DATA MINING APPLICATION IN A STUDENT DATABASE Şenol Zafer ERDOĞAN Maltepe Ünversty Faculty of Engneerng Büyükbakkalköy-Istanbul

More information

NEURO-FUZZY INFERENCE SYSTEM FOR E-COMMERCE WEBSITE EVALUATION

NEURO-FUZZY INFERENCE SYSTEM FOR E-COMMERCE WEBSITE EVALUATION NEURO-FUZZY INFERENE SYSTEM FOR E-OMMERE WEBSITE EVALUATION Huan Lu, School of Software, Harbn Unversty of Scence and Technology, Harbn, hna Faculty of Appled Mathematcs and omputer Scence, Belarusan State

More information

Developing an Information System for Monitoring Student s Activity in Online Collaborative Learning

Developing an Information System for Monitoring Student s Activity in Online Collaborative Learning Developng an IS for Montorng Student s Actvty n Onlne Collaboratve Learnng 1 Developng an Informaton System for Montorng Student s Actvty n Onlne Collaboratve Learnng Angel A. Juan, Thanass Daradoums,

More information

Tuition Fee Loan application notes

Tuition Fee Loan application notes Tuton Fee Loan applcaton notes for new part-tme EU students 2012/13 About these notes These notes should be read along wth your Tuton Fee Loan applcaton form. The notes are splt nto three parts: Part 1

More information

An Integrated Approach of AHP-GP and Visualization for Software Architecture Optimization: A case-study for selection of architecture style

An Integrated Approach of AHP-GP and Visualization for Software Architecture Optimization: A case-study for selection of architecture style Internatonal Journal of Scentfc & Engneerng Research Volume 2, Issue 7, July-20 An Integrated Approach of AHP-GP and Vsualzaton for Software Archtecture Optmzaton: A case-study for selecton of archtecture

More information

PSYCHOLOGICAL RESEARCH (PYC 304-C) Lecture 12

PSYCHOLOGICAL RESEARCH (PYC 304-C) Lecture 12 14 The Ch-squared dstrbuton PSYCHOLOGICAL RESEARCH (PYC 304-C) Lecture 1 If a normal varable X, havng mean µ and varance σ, s standardsed, the new varable Z has a mean 0 and varance 1. When ths standardsed

More information

Heterogeneous Paths Through College: Detailed Patterns and Relationships with Graduation and Earnings

Heterogeneous Paths Through College: Detailed Patterns and Relationships with Graduation and Earnings Heterogeneous Paths Through College: Detaled Patterns and Relatonshps wth Graduaton and Earnngs Rodney J. Andrews The Unversty of Texas at Dallas and the Texas Schools Project Jng L The Unversty of Tulsa

More information

Forecasting the Direction and Strength of Stock Market Movement

Forecasting the Direction and Strength of Stock Market Movement Forecastng the Drecton and Strength of Stock Market Movement Jngwe Chen Mng Chen Nan Ye cjngwe@stanford.edu mchen5@stanford.edu nanye@stanford.edu Abstract - Stock market s one of the most complcated systems

More information

LIFETIME INCOME OPTIONS

LIFETIME INCOME OPTIONS LIFETIME INCOME OPTIONS May 2011 by: Marca S. Wagner, Esq. The Wagner Law Group A Professonal Corporaton 99 Summer Street, 13 th Floor Boston, MA 02110 Tel: (617) 357-5200 Fax: (617) 357-5250 www.ersa-lawyers.com

More information

VOLUME 5 SECTION 1 STANDARDS FOR EDUCATIONAL INSTITUTIONS

VOLUME 5 SECTION 1 STANDARDS FOR EDUCATIONAL INSTITUTIONS Standards for Educatonal Insttutons.qxp 01/05/2007 12:28 PM Page 1 VOLUME 5 SECTION 1 STANDARDS FOR EDUCATIONAL INSTITUTIONS The Responsblty of The Mnstry of Educaton and Youth 2 Natonal Heroes Crcle Kngston

More information

Performance attribution for multi-layered investment decisions

Performance attribution for multi-layered investment decisions Performance attrbuton for mult-layered nvestment decsons 880 Thrd Avenue 7th Floor Ne Yor, NY 10022 212.866.9200 t 212.866.9201 f qsnvestors.com Inna Oounova Head of Strategc Asset Allocaton Portfolo Management

More information