A Decision Support System for the Assessment of Higher Education Degrees in Portugal


 Abigayle Harper
 2 years ago
 Views:
Transcription
1 A Decision Support System for the Assessment of Higher Education Degrees in Portugal José Paulo Santos, José Fernando Oliveira, Maria Antónia Carravilla, Carlos Costa Faculty of Engineering of the University of Porto (FEUP) Portugal Abstract The Foundation of Portuguese Universities (FUP) is a private institution of public interest, created in 1993 and subscribed both by Public Universities and the Catholic Portuguese University, all of them members of the Council of the Portuguese Universities Rectors (CRUP). The assessment of higher education degrees in Portugal is coordinated by FUP. The degrees are grouped by scientific areas and for each area an evaluation panel is designated. The evaluation panels are composed by representatives of the Portuguese universities and by representatives of independent institutions. The task of the evaluation panels is the assessment of the degrees belonging to a scientific area, considering, on the one hand, the selfevaluation reports presented by each school and, on the other hand, a 2 or 3day visit to the degree site. The assessment is accomplished considering several predefined criteria. Recently, the results of the assessment of higher education in Portugal started to be expressed in a quantitative way, complementing the qualitative evaluation. A first phase of this process intended to obtain, for each group of degrees, assessed by the same evaluation panel, a rating for each evaluation criterion. In a second phase, after the definition of a methodology to weight each one of the evaluation criteria, an absolute ranking of the degrees belonging to a certain scientific area may be obtained. We will present a first approach to a Decision Support System (DSS) that intended to help the Foundation of the Portuguese Universities in the task of managing part of the process. The prototype of this DSS was built on an Excel sheet using VBA and it incorporates a methodology to obtain the rating of the degrees for each criterion. Keywords: DSS; Higher Education Degrees; Rating 1 Introduction 1.1 Objective One of the objectives of the Bologna declaration is the assessment of teaching quality. The process of assessment of higher education degrees in Portugal was built with this objective in mind. This is a process of great dimension and complexity, generator of conflicts regarding fundamental questions of the decision model, such as: what is evaluated, how it is evaluated, who evaluates and when it is done. It is therefore necessary, in an initial phase, to clearly define a series of rules, agreed on by all participating elements of this process, that eliminates or at least reduces the inconsistency of the results. This project aims at building a support system for the decision process related to the assessment of higher education degrees. To obtain this objective a statistically robust Decision Support System (DSS) was created. This system should include support tools for the following phases of the assessment process: Input and handle the information; Methodology to obtain a degree rating within each of the assessment criteria. 1.2 Organization and Summary This document is divided into three sections, including this introduction. Section 2 addresses the assessment support system of higher education degrees (AHED) and it is subdivided in three subsections, beginning with a brief introduction to AHED, followed by a description on how the information is input and the methodologies used in the different phases of the process. The third and last section includes a summary of the results and some future work to be done. 1.3 General Overview The decision support system presented in this paper is based on pair wise comparisons between degrees. Each assessor that visited a pair of institutions just has to say if, for each criterion, degree i is better, similar or worse than degree j. The evaluations of all assessors are merged and a global evaluation is computed based on the most frequent score given by all assessors. To much low levels of agreement among assessors and lack of evaluations for a certain pair of degrees are situations that are automatically detected and tools to aid their resolution are implemented. The final step is the rating of the degrees, i.e., deciding to which group each degree should belong. The decision of accepting or rejecting a degree in a group is based on a test of hypothesis over the distance of a degree to the best of the good groups and to the worst of the bad groups. These tests are performed over a normalized sum of the scores obtained by each degree.
2 2 AHED 2.1 Introduction The support system for the assessment of higher education degrees (AHED) is composed by two modules, which correspond to the two phases of the assessment process. In a first phase, the definition of methodologies to input and handle information supplied by each element of the evaluation panel; in a second phase the definition of methodologies in order to obtain the degree rating within each of the assessment criteria. 2.2 Input and Treatment of Information The Worksheet Setup To start the process it is necessary to insert some initial data. These data define the number of degrees, the criteria and the assessors and their designations. Suppose that you fill in the data sheet with the values shown in Figure 1: Figure 1: Data Sheet To start the process the macro StartUp should be executed. This macro will generate one sheet for each assessor s data, an auxiliary sheet and RS m rating sheets, where m is the number of degrees. RS m is given by the following expression: RS m = m 2 if m even Inserting the Assessor s Data m if m odd (1) The next step is the insertion of the information given by each one of the assessors (Figure 2). Figure 2: Example  Assessor s Data For each criterion, there is a square matrix of dimension equal to the number of degrees. The values to put in the cells of the referred matrix can be 0 (worst), 0.5 (similar) or 1 (best). It is important to refer that it is not necessary to fill in all the cells, as generally an assessor does not visit all the degrees. In this case the assessor should leave the cells blank ( ). In order to explain the meaning of these values, the matrix of criterion1, for assessor1, presented in Figure 2, will be used: the (1) in element (1,2) of the matrix means that degree1 is better than degree2; the (0.5) in element (1,3) of the matrix means that degree1 is similar than degree3; the (0) in element (2,3) of the matrix means that degree2 is worse than degree3. In this same table it can be noticed that it is only necessary to fill in the upper triangular matrix. In fact, when classifying element (1,2) of the matrix with value 1, i.e., classifying degree1 as being better than degree2, then element (2,1) of the same matrix automatically receives the information that degree2 is worse than degree1, i.e, it receives the value 0. In general, if Element ij = 1/0 then Element ji = 0/1, else if Element ij = 0.5 then Element ji = 0.5, else Element ij = Element ji =. 2.3 Obtaining the Degree s Rating for Each Criterion The Vote Count We will use the following notation: d assessor {1,...D} k criterion {1,...K} i degree {1,...I} j degree {1,...I} w score {0, 0.5, 1} The votes of each assessor d are input and for each criterion k, each pair of degrees (i,j) and each score w, the votes are counted V kwij. The total number of votes TV kij are also obtained. These partial sums are represented in Figure 3 of our example. The calculation of V kwij and TV kij is done by the following expressions: 1 if d scored with w the relation ij for k P dkwij = 0 if not kwij V kwij = (2) D P dkwij (3) d=1
3 kij TV kij = V kwij (4) w {0,0.5,1} The level of confidence (c) parameter is related to the statistic tests performed in the rating process will be explained in subsection In Figure 5, R kij, the summary of the assessors scores for each criterion k and for each pair of degrees (i,j) is presented. R kij is calculated by the following expression: kij if TV kij < (a) R kij = V otes? else if w V kwij TV kij (b) R kij = w (5) Figure 3: Example  VoteCount Sheet else R kij = Decision! Tuning the Parameters Before starting the rating process it is necessary to adjust three parameters: (a)  minimum total of votes; (b)  minimum percentage of votes to decide; (c)  level of confidence. Figure 4 shows the values used in the example. Figure 5: Example  Rating1 Sheet  Selection Figure 4: Example  Rating1 Sheet Setup The level of confidence parameter (c) allows to immediately determine the field Cut Value (right tail), corresponding to the percentage value for the t distribution with (I1) degrees of freedom (where I is the total number of degrees). The parameter minimum total of votes (a) is directly related to the minimum number of assessors that must be common to each pair of evaluation groups, i.e., the minimum number of assessors that can compare two degrees as they have visited both institutions. The minimum value for this parameter is, of course, 1. The parameter minimum percentage of votes to decide (b) is related to the level of agreement necessary to have a final score for each pair of degrees. For instance, a value of 75% means that at least 3/4 of the assessors have to give the same score for that score to be considered in the final tableau. If it doesn t happen this decision is left to be taken during a general meeting of the assessors. In this phase, if for all k,i,j, R kij V otes? and R kij Decision!, according to Canter [1], the values LineSum (LS ki ) and NormLineSum ( LS ki ) are calculated Figure 5. The expressions used to calculate LS ki, T k and LS ki are respectively: LS ki = T k = I R kij (6) j=1 I LS ki (7) i=1 LS ki = LS ki T k (8) The expression LS ki can also assume the label Lack of Decisions if, in the row related to degree i there are one or more Votes? (insufficiency of votes) or Decision! (decisions to make). In order to proceed to the rating process both situations have to be solved.
4 2.3.3 Insufficiency of Votes When the votes are insufficient it is necessary to verify which pairs of degrees have insufficient votes and for each one of these pairs, a pair of assessors that have visited at least one of these degrees and a third in common need to be found. In fact, not having direct information about how to compare degrees α and γ, because there isn t a common element in the committees that visited the respective institutions, makes it necessary to estimate a relation between theses degrees through an indirect comparison, ie, using a third degree β which serves as a pivot in the transitivity relation: e.g. if α is better than β and β is better than γ then α is better than γ. All possible situations for the relation of order are represented in Table 1, together with the respective result. Value 0 expresses a worst relation, value 0.5 expresses a similar relation and value 1 expresses a better relation. Finally, a * represents a wildcard meaning any value of the relation of order. The wildcard is used when the value placed in that position is indifferent for the resulting relation (α,γ) and has the objective of simplifying the table. (α,β) (β,γ) (α,γ) Table 1: Transitivity Table The use of different pivots can originate different conclusions for the relation (α,γ), given a natural degree of inconsistency in the evaluations. So, whenever there is more than one possible pivot for the relation it is necessary to collect different values in order to generate a single relation. The usage of a measure that results in a value not belonging to set V={0, 0.5, 1} is naturally eliminated. It was decided to use the average of the obtained values, rounded to the closest value of set V. Special attention should be given to values 0.25 and So, assuming that whatever can not be decided may be considered as equivalent, as has been done in the transitivity table for the cases where (α,β) (β,γ), both 0.25 and 0.75 will be rounded to 0.5. In order to unravel this transitivity process the Negotiation macro should be executed. After executing this macro the Negotiation sheet is created, where the pairs of degrees with insufficient votes are represented. This sheet indicates for each criterion, which pair or pairs of assessors visited one of the two degrees involved and a third in common, and presents as a result of the transitivity process, the relation of the degrees. To simulate a situation with insufficiency of votes, admit that, for criterion1, a set of assessors classified the degrees as illustrated in Figure 6(a). These classifications lead to the values presented in Figure 6(b), leading to the conclusion that there is an insufficiency of votes in the relation of degree2 with degree3. Through the analysis of Figure 6(a) it is said that assessor1 and assessor2 visited degree2, assessor3 visited degree3, all visited degree1 and none scored the relation of degree2 with degree3. (a) Votes (b) Selection Figure 6: Example  Insufficiency of Votes Figure 7 shows the result of the application of the transitivity process to the data present in Figure 6. Figure 7: Example  Negotiation Sheet  Insufficiency of Votes In order to determine the values presented in Figure 7, consider that (degree2, degree1, degree3) corresponds to (α, β, γ). Given that assessor1 and assessor2 scored (α, β) value 0 (if (β,α) = 1 then (α,β) = 0), and, assessor3 scored (β, γ) value 1, then, see transitivity table, (α, γ) results in value 0.5. Calculating the average of both values we obtain 0.5, score for the relation of degree2 and degree Decisions to Make When there are decisions to make for any pair of degrees, because there is not a minimum level of agreement among the assessors, then the assessors that visited those pairs of degrees should meet in order to define the relation for the pairs of degrees in question and increase the level of agreement. Now we will simulate a situation where decisions need to be made, considering that, for criterion2, the set of assessors scored the degrees as illustrated in Figure 8(a). Figure 8(b) reflects the results of these classifications, leading to a situation of doubt in the relation of degree1 with degree3. This situation is a consequence of the lack of agreement in the evaluations, given that assessor1, assessor2 and assessor3 classified the relation of degree1 with degree3, respectively with 0, 0.5 and 1. To define the relation for the pairs of degrees in question a meeting among the assessors is needed.
5 (a) Votes (b) Selection Figure 8: Example  Decisions to Make The Rating Process After defining the scores for all pairs of degrees it is possible to start the rating process, by executing the Rating macro. The degrees are ordered both in decreasing and increasing order of LS ki. Considering that degree l is such that LS kl = max i LSki the differences R klj R kij are calculated together with the mean j (R klj R kij )/I and the standard deviation for each i. The same is done for degree u, where LS ku = min i LSki (see Figure 9). Figure 9: Example  Best and Worst (criterion1) Since this situation is dealt with sample pairs of small dimension and according to Guimarães and Cabral [2] we must test the hypothesis of the expected value of a normal population µ = 0. The value t of the tdistribution is calculated by the following expression: t = d µ s m (9) The value t for the best degree is not calculated (because s = 0) and is automatically accepted. The remaining is compared with the cut value (for example ) and if they are inferior to this value they are Accepted, if not they are Rejected. The analysis for the Worst table is similar to the analysis relative to the Best. If a degree is rejected by both groups, i.e., by the Best and the Worst, then it is evaluated in the following Rating sheet. Considering the degree is accepted by one of the groups (Best or Worst) then it will be immediately rated. For each Rating i sheet, the degrees belonging to the Best group are labelled i, while the degrees belonging to the Worst group is labelled m i+1. At a final stage the numbers are converted to classes labelled by letters in alphabetical sequence. It should be printed out that the number of rating classes obtained in this process is dependent on the level of confidence defined for the hypothesis test. A high level of confidence (near 1) means that we want to be very sure when rejecting a degree from a group and so we will end up with just one group: nothing is excluded, all the degrees are equal. On the other hand, a low value for the level of confidence will originate a rating where each group will have just one element, i.e, all the degrees are very different but we may be very wrong. A few trial runs should be performed in order to tune an adequate value for this parameter. 3 Conclusions and Future Work Some important results obtained in this investigation and some future work to be done will now be summarized. The Decision Support System (DSS) for the Assessment of Higher Education Degrees is an extremely important tool to manage the whole assessment process. During the meetings, whenever there are situations of uncertainty, it determines which assessors should meet to complete the rating of degrees for the different criteria. This DDS, which is based on the analysis of sample pairs, was used to obtain the rating of engineering degrees in Portugal, having produced valuable results. As for future work, the search for theoretical results that may eventually lead to more efficient systems emerges, as a way of improving the statistical robustness of the evaluation process. Another topic includes the implementation and testing of methodologies to weight the evaluation criteria, leading to the determination of an absolute ranking. References [1] Larry W. Canter. Environmental Impact Assessment, pages McGrawHil, 2nd edition, [2] Rui Campos Guimarães and José A. Sarsfield Cabral. Estatística, pages McGrawHill, José Paulo Santos José Paulo Santos graduated in Electrical and Computer Engineering and awarded a MSc in Computational Methods in Sciences and Engineering in the area of Simulation at the Faculty of Engineering of the University of Porto (FEUP), Portugal. Recently he is attending a PhD in Electrical and Computer Engineering at the same faculty. José Fernando Oliveira José Fernando Oliveira is Auxiliary Professor at the Department of Electrical and Computers Engineering of the Faculdade de Engenharia da
6 Universidade do Porto and Senior Researcher in the Manufacturing Systems Engineering Unit at INESCPorto, in Portugal. He received his PhD by the Faculdade de Engenharia da Universidade do Porto, in His primary area of interest is the application of Decision and Optimization Methods to industrial and organizational problems. The main application areas have been Cutting and Packing Problems and Decisions Support Systems for the government of Higher Education schools. Maria Antónia Carravilla Maria Antónia Carravilla graduated in Electrical Engineering and finished her MSc in Electrical and Computer Engineering in the area of Control Theory, both in the Faculty of Engineering of the University of Porto (FEUP). In 1996 she concluded her PhD in Operations Research and Production Planning at FEUP. She is Auxiliary Professor at the Department of Electrical and Computers Engineering of FEUP and Senior Researcher in the Manufacturing Systems Engineering Unit at INESCPorto, in Portugal. In the last years, her main research areas have been Logistics, Decision Support Systems and Constraint Logic Programming. Carlos Costa Carlos Costa is a Full Professor of Chemical Engineering at the Faculty of Engineering of the University of Porto, Portugal since He obtained his PhD in Chemical Engineering from the Faculty of Engineering of the University of Porto, in His current research interests centre on Process and Environmental Systems Engineering. He is the author of over 50 publications in refereed journals and presented over 50 communications at international conferences with refereeing. He is, since 2001, Dean of the Faculty of Engineering of the University of Porto.
Data Analysis Tools. Tools for Summarizing Data
Data Analysis Tools This section of the notes is meant to introduce you to many of the tools that are provided by Excel under the Tools/Data Analysis menu item. If your computer does not have that tool
More informationANALYTIC HIERARCHY PROCESS (AHP) TUTORIAL
Kardi Teknomo ANALYTIC HIERARCHY PROCESS (AHP) TUTORIAL Revoledu.com Table of Contents Analytic Hierarchy Process (AHP) Tutorial... 1 Multi Criteria Decision Making... 1 Cross Tabulation... 2 Evaluation
More informationPUBLIC NOTICE. II  Workplace Faculdade de Ciências da Universidade de Lisboa, located in Campo Grande, 1749016 Lisboa.
PUBLIC NOTICE National and international applications are open by Faculdade de Ciências da Universidade de Lisboa (FCUL), for a period of 30 (thirty) working days counted from the day immediately following
More informationStatistics Review PSY379
Statistics Review PSY379 Basic concepts Measurement scales Populations vs. samples Continuous vs. discrete variable Independent vs. dependent variable Descriptive vs. inferential stats Common analyses
More informationUsing Excel for Statistical Analysis
Using Excel for Statistical Analysis You don t have to have a fancy pants statistics package to do many statistical functions. Excel can perform several statistical tests and analyses. First, make sure
More informationIntroduction to. Hypothesis Testing CHAPTER LEARNING OBJECTIVES. 1 Identify the four steps of hypothesis testing.
Introduction to Hypothesis Testing CHAPTER 8 LEARNING OBJECTIVES After reading this chapter, you should be able to: 1 Identify the four steps of hypothesis testing. 2 Define null hypothesis, alternative
More informationPUBLIC NOTICE. In accordance with Articles 37 to 51 and 62 A of ECDU, the following requirements shall apply: I Admission requirements:
PUBLIC NOTICE National and international applications are invited by the Faculty of Sciences of the University of Lisbon, for a period of 30 (thirty) working days from the day immediately following the
More informationProject Management Organization
Project Management Organization Article Info:, Vol. 3 (2008), No. 1, pp. 003009 Received 12 Januar 2008 Accepted 24 April 2008 UDC 005.8 Summary In our work we will try to show, according to recent and
More informationPERFORMANCE MEASUREMENT OF INSURANCE COMPANIES BY USING BALANCED SCORECARD AND ANP
PERFORMANCE MEASUREMENT OF INSURANCE COMPANIES BY USING BALANCED SCORECARD AND ANP Ronay Ak * Istanbul Technical University, Faculty of Management Istanbul, Turkey Email: akr@itu.edu.tr Başar Öztayşi Istanbul
More informationTeaching Logistics without Formal Classes: a case study
Teaching Logistics without Formal Classes: a case study Maria Antónia Carravilla, José Fernando Oliveira Faculty of Engineering, University of Porto {mac,jfo}@fe.up.pt Abstract In this paper we will present
More informationUsing Excel for Statistics Tips and Warnings
Using Excel for Statistics Tips and Warnings November 2000 University of Reading Statistical Services Centre Biometrics Advisory and Support Service to DFID Contents 1. Introduction 3 1.1 Data Entry and
More informationRisk Analysis Using Monte Carlo Simulation
Risk Analysis Using Monte Carlo Simulation Here we present a simple hypothetical budgeting problem for a business startup to demonstrate the key elements of Monte Carlo simulation. This table shows the
More informationt Tests in Excel The Excel Statistical Master By Mark Harmon Copyright 2011 Mark Harmon
ttests in Excel By Mark Harmon Copyright 2011 Mark Harmon No part of this publication may be reproduced or distributed without the express permission of the author. mark@excelmasterseries.com www.excelmasterseries.com
More informationSYSTEMS OF EQUATIONS AND MATRICES WITH THE TI89. by Joseph Collison
SYSTEMS OF EQUATIONS AND MATRICES WITH THE TI89 by Joseph Collison Copyright 2000 by Joseph Collison All rights reserved Reproduction or translation of any part of this work beyond that permitted by Sections
More informationEquations and Inequalities
Rational Equations Overview of Objectives, students should be able to: 1. Solve rational equations with variables in the denominators.. Recognize identities, conditional equations, and inconsistent equations.
More informationMULTICRITERIA MAKING DECISION MODEL FOR OUTSOURCING CONTRACTOR SELECTION
2008/2 PAGES 8 16 RECEIVED 22 12 2007 ACCEPTED 4 3 2008 V SOMOROVÁ MULTICRITERIA MAKING DECISION MODEL FOR OUTSOURCING CONTRACTOR SELECTION ABSTRACT Ing Viera SOMOROVÁ, PhD Department of Economics and
More informationUsing MS Excel to Analyze Data: A Tutorial
Using MS Excel to Analyze Data: A Tutorial Various data analysis tools are available and some of them are free. Because using data to improve assessment and instruction primarily involves descriptive and
More informationAlmost all spreadsheet programs are based on a simple concept: the malleable matrix.
MS EXCEL 2000 Spreadsheet Use, Formulas, Functions, References More than any other type of personal computer software, the spreadsheet has changed the way people do business. Spreadsheet software allows
More informationLAB 4 INSTRUCTIONS CONFIDENCE INTERVALS AND HYPOTHESIS TESTING
LAB 4 INSTRUCTIONS CONFIDENCE INTERVALS AND HYPOTHESIS TESTING In this lab you will explore the concept of a confidence interval and hypothesis testing through a simulation problem in engineering setting.
More informationKeywords: Business Process Management, Implementation Methodologies, Blinds Manufacturing Company.
Business Process Management and its results in a Blinds Manufacturing Company Eduarda Espindola eduarda.espindola@engenharia.ufjf.br Luiz Henrique Dias Alves luiz.alves@ufjf.edu.br Universidade Federal
More informationCalculating the Probability of Returning a Loan with Binary Probability Models
Calculating the Probability of Returning a Loan with Binary Probability Models Associate Professor PhD Julian VASILEV (email: vasilev@uevarna.bg) Varna University of Economics, Bulgaria ABSTRACT The
More informationHypothesis Testing. Learning Objectives. After completing this module, the student will be able to
Hypothesis Testing Learning Objectives After completing this module, the student will be able to carry out a statistical test of significance calculate the acceptance and rejection region calculate and
More informationChapter 6: The Information Function 129. CHAPTER 7 Test Calibration
Chapter 6: The Information Function 129 CHAPTER 7 Test Calibration 130 Chapter 7: Test Calibration CHAPTER 7 Test Calibration For didactic purposes, all of the preceding chapters have assumed that the
More informationNCSS Statistical Software Principal Components Regression. In ordinary least squares, the regression coefficients are estimated using the formula ( )
Chapter 340 Principal Components Regression Introduction is a technique for analyzing multiple regression data that suffer from multicollinearity. When multicollinearity occurs, least squares estimates
More informationRecall this chart that showed how most of our course would be organized:
Chapter 4 OneWay ANOVA Recall this chart that showed how most of our course would be organized: Explanatory Variable(s) Response Variable Methods Categorical Categorical Contingency Tables Categorical
More informationLeast Squares Estimation
Least Squares Estimation SARA A VAN DE GEER Volume 2, pp 1041 1045 in Encyclopedia of Statistics in Behavioral Science ISBN13: 9780470860809 ISBN10: 0470860804 Editors Brian S Everitt & David
More informationhttp://www.phd.com.ar
http://www.phd.com.ar February 2012 revision Pág. 1 de 19 Table of contents 1 Introduction.... 3 2 Installation and initial setup.... 4 2.1 Screens language.... 4 2.2 Data base conection parameters....
More informationRecommendations and Precautions to Prevent Accidents in Construction
Recommendations and Precautions to Prevent Accidents in Construction Soeiro, Alfredo Departamento de Construções Civis / Faculdade de Engenharia da Universidade do Porto / Rua Dr. Roberto Frias, S/ n.º
More informationRANKING REFACTORING PATTERNS USING THE ANALYTICAL HIERARCHY PROCESS
RANKING REFACTORING PATTERNS USING THE ANALYTICAL HIERARCHY PROCESS Eduardo Piveta 1, Ana Morra 2, Maelo Penta 1 João Araújo 2, Pedro Guerrro 3, R. Tom Price 1 1 Instituto de Informática, Universidade
More informationGetting Started with Excel 2008. Table of Contents
Table of Contents Elements of An Excel Document... 2 Resizing and Hiding Columns and Rows... 3 Using Panes to Create Spreadsheet Headers... 3 Using the AutoFill Command... 4 Using AutoFill for Sequences...
More informationAn approach to accreditation: the path of the Italian Higher Education
An approach to accreditation: the path of the Italian Higher Education Carlo Calandra Buonaura CNVSU Board and University of Modena and Reggio Emilia, calandra@unimo.it Primiano Di Nauta CNVSU Technical
More informationSTATISTICA Formula Guide: Logistic Regression. Table of Contents
: Table of Contents... 1 Overview of Model... 1 Dispersion... 2 Parameterization... 3 SigmaRestricted Model... 3 Overparameterized Model... 4 Reference Coding... 4 Model Summary (Summary Tab)... 5 Summary
More informationSpreadsheets Hoparound Cards
Spreadsheets Hoparound Cards Visit us online at HOPAROUND CARDS Preparation Print the cards out using a high quality colour printer Laminate each sheet and then cut out the individual cards to make a
More informationA Case Study in Software Enhancements as Six Sigma Process Improvements: Simulating Productivity Savings
A Case Study in Software Enhancements as Six Sigma Process Improvements: Simulating Productivity Savings Dan Houston, Ph.D. Automation and Control Solutions Honeywell, Inc. dxhouston@ieee.org Abstract
More informationThermo Scientific Dionex Chromeleon 7 Chromatography Data System Software
Thermo Scientific Dionex Chromeleon 7 Chromatography Data System Software Frank Tontala, Thermo Fisher Scientific, Germering, Germany Technical Note 708 Key Words Chromeleon Chromatography Data System,
More informationAPPENDIX N. Data Validation Using Data Descriptors
APPENDIX N Data Validation Using Data Descriptors Data validation is often defined by six data descriptors: 1) reports to decision maker 2) documentation 3) data sources 4) analytical method and detection
More informationModule 4 (Effect of Alcohol on Worms): Data Analysis
Module 4 (Effect of Alcohol on Worms): Data Analysis Michael Dunn Capuchino High School Introduction In this exercise, you will first process the timelapse data you collected. Then, you will cull (remove)
More informationModule 5 Hypotheses Tests: Comparing Two Groups
Module 5 Hypotheses Tests: Comparing Two Groups Objective: In medical research, we often compare the outcomes between two groups of patients, namely exposed and unexposed groups. At the completion of this
More informationDiagonal, Symmetric and Triangular Matrices
Contents 1 Diagonal, Symmetric Triangular Matrices 2 Diagonal Matrices 2.1 Products, Powers Inverses of Diagonal Matrices 2.1.1 Theorem (Powers of Matrices) 2.2 Multiplying Matrices on the Left Right by
More informationUSC Marshall School of Business Academic Information Services. Excel 2007 Qualtrics Survey Analysis
USC Marshall School of Business Academic Information Services Excel 2007 Qualtrics Survey Analysis DESCRIPTION OF EXCEL ANALYSIS TOOLS AVAILABLE... 3 Summary of Tools Available and their Properties...
More informationBasic Pivot Tables. To begin your pivot table, choose Data, Pivot Table and Pivot Chart Report. 1 of 18
Basic Pivot Tables Pivot tables summarize data in a quick and easy way. In your job, you could use pivot tables to summarize actual expenses by fund type by object or total amounts. Make sure you do not
More informationUnderstanding Confidence Intervals and Hypothesis Testing Using Excel Data Table Simulation
Understanding Confidence Intervals and Hypothesis Testing Using Excel Data Table Simulation Leslie Chandrakantha lchandra@jjay.cuny.edu Department of Mathematics & Computer Science John Jay College of
More informationTesting Group Differences using Ttests, ANOVA, and Nonparametric Measures
Testing Group Differences using Ttests, ANOVA, and Nonparametric Measures Jamie DeCoster Department of Psychology University of Alabama 348 Gordon Palmer Hall Box 870348 Tuscaloosa, AL 354870348 Phone:
More informationStatistical Functions in Excel
Statistical Functions in Excel There are many statistical functions in Excel. Moreover, there are other functions that are not specified as statistical functions that are helpful in some statistical analyses.
More informationNEW VERSION OF DECISION SUPPORT SYSTEM FOR EVALUATING TAKEOVER BIDS IN PRIVATIZATION OF THE PUBLIC ENTERPRISES AND SERVICES
NEW VERSION OF DECISION SUPPORT SYSTEM FOR EVALUATING TAKEOVER BIDS IN PRIVATIZATION OF THE PUBLIC ENTERPRISES AND SERVICES Silvija Vlah Kristina Soric Visnja Vojvodic Rosenzweig Department of Mathematics
More informationChiSquare Test. Contingency Tables. Contingency Tables. ChiSquare Test for Independence. ChiSquare Tests for GoodnessofFit
ChiSquare Tests 15 Chapter ChiSquare Test for Independence ChiSquare Tests for Goodness Uniform Goodness Poisson Goodness Goodness Test ECDF Tests (Optional) McGrawHill/Irwin Copyright 2009 by The
More informationSimulating ChiSquare Test Using Excel
Simulating ChiSquare Test Using Excel Leslie Chandrakantha John Jay College of Criminal Justice of CUNY Mathematics and Computer Science Department 524 West 59 th Street, New York, NY 10019 lchandra@jjay.cuny.edu
More informationData exploration with Microsoft Excel: analysing more than one variable
Data exploration with Microsoft Excel: analysing more than one variable Contents 1 Introduction... 1 2 Comparing different groups or different variables... 2 3 Exploring the association between categorical
More informationEXCEL Tutorial: How to use EXCEL for Graphs and Calculations.
EXCEL Tutorial: How to use EXCEL for Graphs and Calculations. Excel is powerful tool and can make your life easier if you are proficient in using it. You will need to use Excel to complete most of your
More informationMINITAB ASSISTANT WHITE PAPER
MINITAB ASSISTANT WHITE PAPER This paper explains the research conducted by Minitab statisticians to develop the methods and data checks used in the Assistant in Minitab 17 Statistical Software. OneWay
More informationPaper Airplanes & Scientific Methods
Paper Airplanes 1 Name Paper Airplanes & Scientific Methods Scientific Inquiry refers to the many different ways in which scientists investigate the world. Scientific investigations are done to answer
More informationAn Introduction to Excel Pivot Tables
An Introduction to Excel Pivot Tables EXCEL REVIEW 20012002 This brief introduction to Excel Pivot Tables addresses the English version of MS Excel 2000. Microsoft revised the Pivot Tables feature with
More informationChisquare test Fisher s Exact test
Lesson 1 Chisquare test Fisher s Exact test McNemar s Test Lesson 1 Overview Lesson 11 covered two inference methods for categorical data from groups Confidence Intervals for the difference of two proportions
More informationChapter 23 Inferences About Means
Chapter 23 Inferences About Means Chapter 23  Inferences About Means 391 Chapter 23 Solutions to Class Examples 1. See Class Example 1. 2. We want to know if the mean battery lifespan exceeds the 300minute
More informationMicrosoft Excel 2013 Pivot Tables (Level 3)
IT Training Microsoft Excel 2013 Pivot Tables (Level 3) Contents Introduction... 1 Creating a Pivot Table... 1 A OneDimensional Table... 2 A TwoDimensional Table... 4 A ThreeDimensional Table... 5 Hiding
More informationIntelligent Log Analyzer. André Restivo <andre.restivo@portugalmail.pt>
Intelligent Log Analyzer André Restivo 9th January 2003 Abstract Server Administrators often have to analyze server logs to find if something is wrong with their machines.
More informationCollege Algebra. Barnett, Raymond A., Michael R. Ziegler, and Karl E. Byleen. College Algebra, 8th edition, McGrawHill, 2008, ISBN: 9780072867381
College Algebra Course Text Barnett, Raymond A., Michael R. Ziegler, and Karl E. Byleen. College Algebra, 8th edition, McGrawHill, 2008, ISBN: 9780072867381 Course Description This course provides
More informationManagement Science and Business Information Systems
Objectives The objectives of the course are: Understand and practice the main concepts of MS Apply the concepts of MS in real business cases Understand the consequences of MS in companies competitive advantage
More informationPROJECT RISK MANAGEMENT
PROJECT RISK MANAGEMENT DEFINITION OF A RISK OR RISK EVENT: A discrete occurrence that may affect the project for good or bad. DEFINITION OF A PROBLEM OR UNCERTAINTY: An uncommon state of nature, characterized
More informationStatistical tests for SPSS
Statistical tests for SPSS Paolo Coletti A.Y. 2010/11 Free University of Bolzano Bozen Premise This book is a very quick, rough and fast description of statistical tests and their usage. It is explicitly
More information7 Gaussian Elimination and LU Factorization
7 Gaussian Elimination and LU Factorization In this final section on matrix factorization methods for solving Ax = b we want to take a closer look at Gaussian elimination (probably the best known method
More informationFactoring Polynomials
Factoring Polynomials Hoste, Miller, Murieka September 12, 2011 1 Factoring In the previous section, we discussed how to determine the product of two or more terms. Consider, for instance, the equations
More informationData quality in Accounting Information Systems
Data quality in Accounting Information Systems Comparing Several Data Mining Techniques Erjon Zoto Department of Statistics and Applied Informatics Faculty of Economy, University of Tirana Tirana, Albania
More informationData Preprocessing. Week 2
Data Preprocessing Week 2 Topics Data Types Data Repositories Data Preprocessing Present homework assignment #1 Team Homework Assignment #2 Read pp. 227 240, pp. 250 250, and pp. 259 263 the text book.
More informationUsing Excel for Analyzing Survey Questionnaires Jennifer Leahy
University of WisconsinExtension Cooperative Extension Madison, Wisconsin PD &E Program Development & Evaluation Using Excel for Analyzing Survey Questionnaires Jennifer Leahy G365814 Introduction You
More informationAdditional sources Compilation of sources: http://lrs.ed.uiuc.edu/tseportal/datacollectionmethodologies/jintselink/tselink.htm
Mgt 540 Research Methods Data Analysis 1 Additional sources Compilation of sources: http://lrs.ed.uiuc.edu/tseportal/datacollectionmethodologies/jintselink/tselink.htm http://web.utk.edu/~dap/random/order/start.htm
More informationThe Friedman Test with MS Excel. In 3 Simple Steps. Kilem L. Gwet, Ph.D.
The Friedman Test with MS Excel In 3 Simple Steps Kilem L. Gwet, Ph.D. Copyright c 2011 by Kilem Li Gwet, Ph.D. All rights reserved. Published by Advanced Analytics, LLC A single copy of this document
More informationHow to Write a Formal Lab Report
Union College Physics and Astronomy How to Write a Formal Lab Report A formal lab report is essentially a scaleddown version of a scientific paper, reporting on the results of an experiment that you and
More informationCreating A Grade Sheet With Microsoft Excel
Creating A Grade Sheet With Microsoft Excel Microsoft Excel serves as an excellent tool for tracking grades in your course. But its power is not limited to its ability to organize information in rows and
More informationData Mining and Analysis With Excel PivotTables and The QI Macros By Jay Arthur, The KnowWare Man
Data Mining and Analysis With Excel PivotTables and The QI Macros By Jay Arthur, The KnowWare Man It s an old, but true saying that what gets measured gets done. That s why so many companies are looking
More informationRoadmap to Data Analysis. Introduction to the Series, and I. Introduction to Statistical ThinkingA (Very) Short Introductory Course for Agencies
Roadmap to Data Analysis Introduction to the Series, and I. Introduction to Statistical ThinkingA (Very) Short Introductory Course for Agencies Objectives of the Series Roadmap to Data Analysis Provide
More informationANALYTICAL HIERARCHY PROCESS AS A TOOL FOR SELECTING AND EVALUATING PROJECTS
ISSN 17264529 Int j simul model 8 (2009) 1, 1626 Original scientific paper ANALYTICAL HIERARCHY PROCESS AS A TOOL FOR SELECTING AND EVALUATING PROJECTS Palcic, I. * & Lalic, B. ** * University of Maribor,
More informationInferential Statistics
Inferential Statistics Sampling and the normal distribution Zscores Confidence levels and intervals Hypothesis testing Commonly used statistical methods Inferential Statistics Descriptive statistics are
More informationHow to do AHP analysis in Excel
How to do AHP analysis in Excel Khwanruthai BUNRUAMKAEW (D) Division of Spatial Information Science Graduate School of Life and Environmental Sciences University of Tsukuba ( March 1 st, 01) The Analytical
More informationHow to Make the Most of Excel Spreadsheets
How to Make the Most of Excel Spreadsheets Analyzing data is often easier when it s in an Excel spreadsheet rather than a PDF for example, you can filter to view just a particular grade, sort to view which
More informationQuantrix & Excel: 3 Key Differences A QUANTRIX WHITE PAPER
Quantrix & Excel: 3 Key Differences A QUANTRIX WHITE PAPER Abstract This whitepaper is designed to educate spreadsheet users about three key conceptual and practical differences between Quantrix Modeler
More informationIntegrated Municipal Asset Management tool (IMAM)
Integrated Municipal Asset Management tool (IMAM) Integrated Municipal Asset Management tool that makes it easy for decision makers to use and implement the developed Models. This tool is developed using
More informationErrors in Operational Spreadsheets: A Review of the State of the Art
Errors in Operational Spreadsheets: A Review of the State of the Art Stephen G. Powell Tuck School of Business Dartmouth College sgp@dartmouth.edu Kenneth R. Baker Tuck School of Business Dartmouth College
More informationJosé Egidio M.Tondin 1, Mario O. de Menezes 1, Marina B.A.Vasconcellos 1 and João A.Osso Jr. 1 ABSTRACT 1. INTRODUCTION
PROSPECTION OF IMPLEMENTATION OF DISTANCE LEARNING AT IPEN CNEN/SP FOR THE COURSE ON FUNDAMENTALS OF NUCLEAR PHYSICS USING INFRASTRUCTURE OF FREE SOFTWARE José Egidio M.Tondin 1, Mario O. de Menezes 1,
More informationAnalysis of Variance. MINITAB User s Guide 2 31
3 Analysis of Variance Analysis of Variance Overview, 32 OneWay Analysis of Variance, 35 TwoWay Analysis of Variance, 311 Analysis of Means, 313 Overview of Balanced ANOVA and GLM, 318 Balanced
More informationMBA 611 STATISTICS AND QUANTITATIVE METHODS
MBA 611 STATISTICS AND QUANTITATIVE METHODS Part I. Review of Basic Statistics (Chapters 111) A. Introduction (Chapter 1) Uncertainty: Decisions are often based on incomplete information from uncertain
More informationInternetBased Learning Tools: Development and Learning Psychology (DLP) Experience
InternetBased Learning Tools: Development and Learning Psychology (DLP) Experience José Tavares Ana Paula Cabral Isabel Huet Silva Rita Carvalho Anabela Pereira Isabel Lopes Educational Sciences Department,
More informationMATRIX ALGEBRA AND SYSTEMS OF EQUATIONS. + + x 2. x n. a 11 a 12 a 1n b 1 a 21 a 22 a 2n b 2 a 31 a 32 a 3n b 3. a m1 a m2 a mn b m
MATRIX ALGEBRA AND SYSTEMS OF EQUATIONS 1. SYSTEMS OF EQUATIONS AND MATRICES 1.1. Representation of a linear system. The general system of m equations in n unknowns can be written a 11 x 1 + a 12 x 2 +
More informationCREATING LEARNING OUTCOMES
CREATING LEARNING OUTCOMES What Are Student Learning Outcomes? Learning outcomes are statements of the knowledge, skills and abilities individual students should possess and can demonstrate upon completion
More informationThe structure of accounting systems: how to store accounts Lincoln Stoller, Ph.D.
The structure of accounting systems: how to store accounts Lincoln Stoller, Ph.D. balances In my most recent article I considered the simplest accounting system consisting of a single file of general ledger
More informationUser Manual for Sustainable Development Interactive Tutorial Software
User Manual for Sustainable Development Interactive Tutorial Software copyright December 2008 Philippine Council for Sustainable Development (PCSD) TABLE OF CONTENTS User Manual for Sustainable Development
More informationMicrosoft Excel 2010 and Tools for Statistical Analysis
Appendix E: Microsoft Excel 2010 and Tools for Statistical Analysis Microsoft Excel 2010, part of the Microsoft Office 2010 system, is a spreadsheet program that can be used to organize and analyze data,
More informationPivotTable and PivotChart Reports, & Macros in Microsoft Excel
PivotTable and PivotChart Reports, & Macros in Microsoft Excel Theresa A Scott, MS Biostatistician III Department of Biostatistics Vanderbilt University theresa.scott@vanderbilt.edu Table of Contents 1
More informationUsing Analytic Hierarchy Process (AHP) Method to Prioritise Human Resources in Substitution Problem
Using Analytic Hierarchy Process (AHP) Method to Raymond HoLeung TSOI Software Quality Institute Griffith University *Email:hltsoi@hotmail.com Abstract In general, software project development is often
More informationFormat for Experiment Preparation and WriteUp
Format for Experiment Preparation and WriteUp Scientists try to answer questions by applying consistent, logical reasoning to describe, explain, and predict observations; and by performing experiments
More informationREGULATION OF THIRD CYCLE STUDIES IN ECONOMICS OF THE SCHOOL OF ECONOMICS, UNIVERSITY OF PORTO. Article 1 Legal Framework
REGULATION OF THIRD CYCLE STUDIES IN ECONOMICS OF THE SCHOOL OF ECONOMICS, UNIVERSITY OF PORTO Article 1 Legal Framework This regulation seeks to develop and complement the legal framework introduced by
More informationWhich Soft? Decision Support Software
Which Soft? Decision Support Software Anabela Tereso, Ricardo Macedo, Rafael Abreu, João Brandão, Henrique Martins University of Minho, School of Engineering, 4710057 Braga, Portugal anabelat@dps.uminho.pt;
More informationMacros allow you to integrate existing Excel reports with a new information system
Macro Magic Macros allow you to integrate existing Excel reports with a new information system By Rick Collard Many water and wastewater professionals use Microsoft Excel extensively, producing reports
More informationTommy B. Harrington 104 Azalea Drive Greenville, NC 27858 Email: tommy@tommyharrington.com
M o s t U s e f u l E x c e l C o m m a n d s Tommy B. Harrington 104 Azalea Drive Greenville, NC 27858 Email: tommy@tommyharrington.com Computer Training YOU Can Understand! Most Useful Excel Commands
More information2014 ACM ICPC Southeast USA Regional Programming Contest. 15 November, 2014. Division 2
204 ACM ICPC Southeast USA Regional Programming Contest 5 November, 204 Division 2 A: Stained Carpet... B: Gold Leaf... 2 C: Hill Number... 4 D: Knight Moves... 5 E: Marble Madness... 6 F: Polling... 7
More informationDecision and uncertainty management for human and human/agent teams. Dr. David Ullman President Robust Decisions, Inc. www.robustdecisions.
Decision and uncertainty management for human and human/agent teams Dr. David Ullman President Robust Decisions, Inc. www.robustdecisions.com Topics What is Decision Management and why is it important?
More informationEXCEL VBA ( MACRO PROGRAMMING ) LEVEL 1 2122 SEPTEMBER 2015 9.00AM5.00PM MENARA PJ@AMCORP PETALING JAYA
EXCEL VBA ( MACRO PROGRAMMING ) LEVEL 1 2122 SEPTEMBER 2015 9.00AM5.00PM MENARA PJ@AMCORP PETALING JAYA What is a Macro? While VBA VBA, which stands for Visual Basic for Applications, is a programming
More informationArena 9.0 Basic Modules based on Arena Online Help
Arena 9.0 Basic Modules based on Arena Online Help Create This module is intended as the starting point for entities in a simulation model. Entities are created using a schedule or based on a time between
More informationIntroduction to Statistical Computing in Microsoft Excel By Hector D. Flores; hflores@rice.edu, and Dr. J.A. Dobelman
Introduction to Statistical Computing in Microsoft Excel By Hector D. Flores; hflores@rice.edu, and Dr. J.A. Dobelman Statistics lab will be mainly focused on applying what you have learned in class with
More informationThe Gravity Model: Derivation and Calibration
The Gravity Model: Derivation and Calibration Philip A. Viton October 28, 2014 Philip A. Viton CRP/CE 5700 () Gravity Model October 28, 2014 1 / 66 Introduction We turn now to the Gravity Model of trip
More information