Technical Information



Similar documents
Reception baseline: criteria for potential assessments

A s h o r t g u i d e t o s ta n d A r d i s e d t e s t s

Office of Institutional Research & Planning

RR887. Changes in shift work patterns over the last ten years (1999 to 2009)

Public and Private Sector Earnings - March 2014

Progression from GCSE to AS and A level, 2010

Using MS Excel to Analyze Data: A Tutorial

Assessment Policy. 1 Introduction. 2 Background

Charity giving over Christmas survey. December 2013

Analysis of academy school performance in GCSEs 2014


The relationship between mental wellbeing and financial management among older people

COGNITIVE ABILITIES TEST: FOURTH EDITION. Sample Reports SECONDARY.

The Personal Learning Insights Profile Research Report

Test Reliability Indicates More than Just Consistency

International Benchmarking Analysis of CFA Institute Qualifications

2. Incidence, prevalence and duration of breastfeeding

Beyond 2011: Population Coverage Survey Field Test 2013 December 2013

Technological Attitude and Academic Achievement of Physics Students in Secondary Schools (Pp )

General Method: Difference of Means. 3. Calculate df: either Welch-Satterthwaite formula or simpler df = min(n 1, n 2 ) 1.

Primary school accountability in A technical guide for primary maintained schools, academies and free schools

UK application rates by country, region, constituency, sex, age and background. (2015 cycle, January deadline)

MULTIPLE REGRESSION WITH CATEGORICAL DATA

Chapter 2: Health in Wales and the United Kingdom

Linear Models in STATA and ANOVA

Chapter 5: Financial Wealth, Wealth in Great Britain

UK Quality Code for Higher Education

SIMPLE LINEAR CORRELATION. r can range from -1 to 1, and is independent of units of measurement. Correlation can be done on two dependent variables.

Regional characteristics of foreignborn people living in the United Kingdom

Specifications on Reasonable Adjustments

Parkinson s prevalence in the United Kingdom (2009)

11. Analysis of Case-control Studies Logistic Regression

Association Between Variables

AUTISM SPECTRUM RATING SCALES (ASRS )

UNDERSTANDING THE DEPENDENT-SAMPLES t TEST

Student loan repayments

TRADE UNION MEMBERSHIP Statistical Bulletin JUNE 2015

Correlational Research. Correlational Research. Stephen E. Brock, Ph.D., NCSP EDS 250. Descriptive Research 1. Correlational Research: Scatter Plots

Multivariate Analysis of Variance. The general purpose of multivariate analysis of variance (MANOVA) is to determine

CHAPTER 7 PRESENTATION AND ANALYSIS OF THE RESEARCH FINDINGS

10. European Union. (a) Past trends

Partial Estimates of Reliability: Parallel Form Reliability in the Key Stage 2 Science Tests

UK Income Tax Liabilities Statistics

8 th European Conference on Psychological Assessment

International comparisons of obesity prevalence

Version : klm. General Certificate of Education. Mathematics MPC1 Pure Core 1. Mark Scheme examination - June series

Management Information

Year 9 mathematics test

Dental Care Professionals Pay Findings from the Dental Business Trends survey

Regulated qualifications in England, Wales and Northern Ireland are in either the:

Chapter 8 Hypothesis Testing Chapter 8 Hypothesis Testing 8-1 Overview 8-2 Basics of Hypothesis Testing

Statistical skills example sheet: Spearman s Rank

Understanding the UK education system

Estimating differences in public and private sector pay

Volunteering in Northern Ireland: What do we know in 2012?

Income Tax Liabilities Statistics to

Stigmatisation of people with mental illness

Statistical First Release

oxford english testing.com

c. Construct a boxplot for the data. Write a one sentence interpretation of your graph.

X = T + E. Reliability. Reliability. Classical Test Theory 7/18/2012. Refers to the consistency or stability of scores

ACER Mechanical Reasoning Test Canadian Technical Supplement

CALCULATIONS & STATISTICS

Nursing our future. An RCN study into the challenges facing today s nursing students in the UK

Chapter 10. Key Ideas Correlation, Correlation Coefficient (r),

CIMA salary survey 2012

How To Track Life Expectancy In England

Part 2: Analysis of Relationship Between Two Variables

Statistical First Release

Patient survey report Category C Ambulance Service User Survey 2008 North East Ambulance Service NHS Trust

National Disability Authority Resource Allocation Feasibility Study Final Report January 2013

Centre for English Language Teaching (CELT)

QUEEN S UNIVERSITY BELFAST SCHOOL OF MEDICINE, DENTISTRY AND BIOMEDICAL SCIENCES ADMISSION POLICY STATEMENT FOR MEDICINE FOR 2016 ENTRY

Using SAS Proc Mixed for the Analysis of Clustered Longitudinal Data

QUALIFICATION REFORM: A GUIDE TO WHAT IS HAPPENING AROUND THE UK

Mobile phone usage. Attitudes towards mobile phone functions including reception

Aptis for Teens. Unlock teens potential to achieve academic excellence

Matti Kyrö. International comparisons of some features of

Overview of Non-Parametric Statistics PRESENTER: ELAINE EISENBEISZ OWNER AND PRINCIPAL, OMEGA STATISTICS

Patterns of higher education institutions in the UK:

Version /10. General Certificate of Education. Economics. ECON1: Markets and Market Failure. Mark Scheme examination - January series

Sports Coaching in the UK III. A statistical analysis of coaches and coaching in the UK

IMPACT OF TRUST, PRIVACY AND SECURITY IN FACEBOOK INFORMATION SHARING

CENTRAL GRANT APPLICATION GUIDELINES

UNDERSTANDING THE TWO-WAY ANOVA

WHAT IS A JOURNAL CLUB?

Having a coin come up heads or tails is a variable on a nominal scale. Heads is a different category from tails.

Univariate Regression

Report on the Scaling of the 2013 NSW Higher School Certificate. NSW Vice-Chancellors Committee Technical Committee on Scaling

Opgaven Onderzoeksmethoden, Onderdeel Statistiek

GCSE MATHEMATICS H Unit 2: Number and Algebra (Higher) Report on the Examination. Specification 4360 November Version: 1.

CHAPTER 3: RESEARCH METHODS. A cross-sectional correlation research design was used for this study where the

Global Food Security Programme A survey of public attitudes

Transcription:

Technical Information Trials The questions for Progress Test in English (PTE) were developed by English subject experts at the National Foundation for Educational Research. For each test level of the paper version around 50% more questions were developed than required for the final version of the test booklet. These questions were trialed in spring 2013 using three test paper booklets for each year group with common questions between booklets. Each question was taken by around 300 students. The numbers of students taking part in the paper trials were as follows. Number of students PTE5 1016 PTE6 870 PTE7 1016 PTE8 875 PTE9 1171 PTE10 1119 PTE11 1228 PTE11T 1417 PTE12 1198 PTE13 881 PTE14 1032 Total 11823 The data from the paper trials were analysed to provide information on the difficulty level of each question, its ability to discriminate between high and low scorers, and the extent to which it proved equally difficult for both genders, once each sex s general level of performance was taken into account. This information was then used to select questions for the final standardisation version of the paper and digital versions. 1

Standardisation Two separate standardisations were conducted: one for the United Kingdom and one for Northern Ireland. Sufficient numbers of students were required for each of these standardisations. The standardisation for all levels of PTE except PTE11T took place between February and June 2014. PTE11T was standardised in September and October 2014. A national database of schools was created and schools were grouped into categories by country (Wales, Scotland and Northern Ireland). In England, schools were further grouped into independent or grammar plus five categories of school intake based on overall school performance at end of primary schooling using Key Stage 2 outcomes, or for secondary schools using the GCSE outcomes. For the Northern Ireland standardisations, schools were categorised into independent or grammar plus five categories of school intake based on uptake of free school meals within the schools. Schools were selected by stratified random sampling procedures within these groupings. As this was a national sample, many schools taking part in the standardisation had never used English assessments from GL Assessment before. For the standardisation, schools were asked to do one pre-selected PTE test level and were given an option to do other levels. Primary schools were asked to test all students in the year group but secondary schools had the option to either test two randomly selected teaching groups or the whole year group. The numbers of students taking part in the two standardisations were as follows. Number of students United Kingdom Northern Ireland PTE5 2450 705 PTE6 2905 1005 PTE7 2453 1014 PTE8 3145 1099 PTE9 2926 1197 PTE10 3412 1350 PTE11 3020 1002 PTE11T 6319 1039 PTE12 3750 1427 PTE13 3705 1140 PTE14 3339 1095 Total 37424 12073 Total of which: Paper 27637 8163 Digital 9787 3910 2

Schools were free to choose between the paper and digital version the tests. Overall, around a quarter of the UK sample, and a third of the Northern Ireland sample, completed the digital version. The students in the Northern Ireland standardisations were included in the UK standardisations but are over-represented in the UK sample compared with the proportions nationally. The results were weighted to reflect the national distributions of students in the categories mentioned above separately for the paper version and the digital version. Test reliability The reliability of a test is a measure of the consistency of a student s test scores over repeated testing, assuming conditions remain the same that is, there was no fatigue, learning effect or lack of motivation. Tests with poor reliability might result in very different scores for a student across two test administrations. The reliability of the test was estimated using the Cronbach s Alpha formula which produces values ranging from 0 to 1. Values above 0.80 are considered to be very good. The reliability values for the levels of PTE are given in the table below, separately for the UK and the Northern Ireland standardisations, and all show that the tests are very reliable. There were no significant differences between the reliabilities between the two regions, and further analysis showed that the reliabilities for the paper and digital versions were very similar. Reliability UK NI PTE5 0.83 0.86 PTE6 0.91 0.91 PTE7 0.92 0.92 PTE8 0.93 0.94 PTE9 0.91 0.92 PTE10 0.92 0.92 PTE11 0.93 0.92 PTE11T 0.94 0.93 PTE12 0.92 0.92 PTE13 0.93 0.92 PTE14 0.93 0.92 For interpreting the score of an individual student, the standard error of measurement (SEM) is a more useful statistic than a reliability coefficient. It indicates how large, on average, the fluctuations in standard scores may be and indicates the 68% chance or confidence band. However, most tests show the 90% chance or confidence bands. The SEM for PTE12 is 4.2 for the UK, and for an average- 3

performing student with a PTE12 Standard Age Score (SAS) of 100, there is a 90% chance that the student s true SAS will be in the range +/- 7.0, i.e. from 93 to 107. SEM 90% SAS confidence band (+/-) UK NI UK NI PTE5 6.1 5.6 10.1 9.3 PTE6 4.4 4.5 7.2 7.4 PTE7 4.3 4.2 7.0 6.8 PTE8 4.0 3.8 6.5 6.3 PTE9 4.4 4.2 7.2 7.0 PTE10 4.2 4.1 6.9 6.8 PTE11 4.1 4.2 6.7 6.8 PTE11T 3.7 4.0 6.1 6.6 PTE12 4.2 4.3 7.0 7.0 PTE13 3.9 4.3 6.4 7.0 PTE14 4.1 4.1 6.8 6.8 Gender differences The tests have been age standardised to a national mean of 100 and standard deviation of 15. There were approximately similar numbers of males and females in the standardisations. The table below shows the mean SAS score differences between males and females for the UK and for Northern Ireland. Differences of more than 3 SAS points can be considered to be significant. Females in general tend, on average, to perform better than males in primary schools but differences are much smaller in secondary school. Gender - mean SAS differences UK standardisation NI standardisation PTE5 2.2 0.5 PTE6 4.4 5.4 PTE7 3.5 3.8 PTE8 4.1 2.6 PTE9 4.2 3.1 PTE10 3.1 3.3 PTE11 2.5 3.0 PTE11T 3.4 8.3 PTE12 1.3-0.5 PTE13 1.6-1.1 PTE14 3.1-1.1 Note - positive scores: females higher than males; negative scores: females lower than males. 4

Northern Ireland compared with the UK The large numbers of students taking part in the separate Northern Ireland standardisations enable us to compare students in Northern Ireland with students in the UK. The table below shows the average SAS differences based on the UK standardisations with a UK mean SAS of 100. UK scores are on average significantly higher than Northern Ireland for ages 5 and 6 but the differences are small for the other age groups. Mean SAS difference PTE5 3.7 PTE6 4.9 PTE7 2.1 PTE8 1.3 PTE9 0.3 PTE10 1.1 PTE11 0.1 PTE11T -0.4 PTE12-1.8 PTE13-0.3 PTE14-3.0 Note - positive scores: UK higher than Northern Ireland; negative scores: UK lower than Northern Ireland Relationship between PTE and PIE outcomes PTE has been designed to replace the well-established series, Progress in English (PIE). A comparative study, in which about 350 students per year from five different year groups took both the old and the new versions of the tests, was undertaken for the test series. A sample of students aged 7 to 11 years old had to take both the new and older version of the test. Each pair of tests was then statistically equated, so that each standardised score on the old test could be mapped onto an equivalent score on the new test. The resulting information on the relationship between PTE and PIE outcomes is available for test levels 7-11. The strength of the relationship between two variables can be measured by a statistic called the correlation coefficient. A value of zero indicates no relationship between the two measures whereas a value of one indicates a perfect positive relationship. The table below shows the correlations for each level and that the correlations are all highly significant. 5

Correlation PTE7 0.83 PTE8 0.84 PTE9 0.85 PTE10 0.84 PTE11 0.84 Schools that have data on students standardised scores from PIE will clearly wish to convert these so that they can be compared directly to the students results on the new tests. The conversion table on the next pages gives this information. Teachers should take the SAS from the old test series and convert this to the equivalent at the same level of PTE. So, for example, a standardised score of 95 on Progress in English 10 is equivalent to a standardised score of 94 on the new Progress Test in English 10. This is the starting point for making a judgement by comparing this with the SAS from the next level of PTE. 6

Progress in English SAS Equivalent Progress Test in English SAS PTE7 PTE8 PTE9 PTE10 PTE11 69 69 69 69 69 71 70 69 69 69 69 72 71 69 69 69 70 73 72 70 69 69 71 74 73 71 69 70 72 75 74 72 70 71 73 76 75 73 71 72 74 77 76 74 72 73 75 78 77 75 73 74 76 79 78 76 74 75 77 80 79 77 75 76 78 81 80 79 76 77 79 82 81 80 77 78 80 83 82 81 79 79 81 84 83 82 80 80 82 85 84 83 81 81 83 86 85 84 82 82 84 87 86 85 83 83 85 88 87 86 84 84 86 88 88 87 85 85 87 89 89 88 86 86 88 90 90 90 87 87 89 91 91 91 88 88 90 92 92 92 89 89 91 93 93 93 90 90 92 94 94 94 91 91 93 95 95 95 92 92 94 96 96 96 93 93 95 97 97 97 94 94 96 98 98 98 95 95 97 99 99 100 96 96 98 100 100 101 97 97 99 101 7

Progress in English SAS Equivalent Progress Test in English SAS PTE7 PTE8 PTE9 PTE10 PTE11 101 102 98 98 100 102 102 103 99 99 101 103 103 104 100 100 102 104 104 105 101 101 103 105 105 106 102 102 104 106 106 107 103 103 105 107 107 108 104 104 106 108 108 109 105 105 107 109 109 111 106 106 108 110 110 112 107 107 109 111 111 113 108 108 110 112 112 114 109 109 111 113 113 115 110 110 112 114 114 116 111 111 114 114 115 117 112 112 115 115 116 118 113 113 116 116 117 119 114 114 117 117 118 121 115 115 118 118 119 122 116 116 119 119 120 123 117 117 120 120 121 124 118 118 121 121 122 125 119 119 122 122 123 126 120 120 123 123 124 127 122 121 124 124 125 128 123 122 125 125 126 129 124 123 126 126 127 130 125 124 127 127 128 132 126 125 128 128 129 133 127 126 129 129 130 134 128 127 130 130 131 135 129 128 131 131 132 136 130 129 132 132 8

Progress in English SAS Equivalent Progress Test in English SAS PTE7 PTE8 PTE9 PTE10 PTE11 133 137 131 130 133 133 134 138 132 131 134 134 135 139 133 132 135 135 136 140 134 133 136 136 137 141 135 134 137 137 138 141 136 135 138 138 139 141 137 136 139 139 140 141 138 136 140 139 141 141 139 137 141 140 Copyright GL Assessment 2015 9