Tag Archives: Item Response Theory

Use of Differential Item Functioning (DIF) Analysis for Bias Analysis in Test Construction (Published)

The study used differential item functioning (DIF) analysis to determine item bias in a chemistry aptitude test (CAT). A total of 270 items were administered, in paper and pencil format for item analysis purposes. Items were analysed by means of classical item analysis, IRT item analysis and DIF analysis in particular. The sample size was 554 secondary school students from SS1 and SS3. The study focused on selected secondary schools in Yoruba speaking states of the western part of Nigeria, Hausa speaking states in the northern part of Nigeria and Igbo speaking states in the eastern Nigeria. The sample was divided into subgroups which was used to investigate the DIF for the level of Education, gender, language and culture. This was used to indentify items that indicated bias in terms of gender, culture, language or level of education. Items that exceeded a predetermined amount of DIF were discarded from that final item bank, irrespective of which subgroup was being advantaged or disadvantaged. The process and results of the DIF analysis were discussed.

Keywords: Classical Test Theory, Differential Item Functioning, Item Characteristic Curves, Item Response Theory

Detecting Item Bias in Rivers State JSSCE Business Studies Using Item Response Theory (IRT) Approach (Published)

This study identified biased test items in the Rivers state JSSCE Business Studies conducted in 2009 using Item Response Theory Approach. The Sample comprises 4000 JSS III students in public and private schools that sat for the JSSCE Business Studies Examination in 2009 in Rivers state which were selected through stratified proportionate random sampling. The instruments for data collection were the test items in JSSCE Business Studies conducted in 2009 and a result collection sheet. Two null hypotheses drawn from two research questions were tested at 0.50 probability of correct response. The assumptions of unidimensionality and local independence were checked using factor analysis. The students’ responses to the test items were calibrated with an IRT statistical software named ex-calibre 4.2.2 developed by Assessment Systems Corporation. The results revealed that the test items met the assumptions of unidimensionality and local independence. It also revealed that there is school type bias in the Rivers State JSSCE Business Studies test items for 2009. Based on the findings, recommendations were made, one of them being that business studies curriculum should be restructured so as to accommodate the new technological advances which may be one of the reasons for the presence of school type bias in the Business Studies test conducted in 2009 in Rivers State.

Keywords: Item Characteristic Curve, Item Response Theory, Unidimensionality

Psychometric Advent of Advanced Progressive Matrices – Smart Version (Apm-Sv) For Use in Nigeria (Published)

The Raven’s Advanced Progressive Matrices (APM) test is a leading global non-verbal measure of mental ability, helping to identify individuals with advanced observation and clear thinking skills who can handle rigorous study programmes as well as the complexity and ambiguity of the modern workplace. APM scale is largely employed by researchers and practitioners in the field of psychometrics, education, medicine and the social sciences. A sample of 3100 participants in Nigeria was randomly drawn to answer nine research questions. Triangulation research design, adopting item response theory (IRT) guided the study. The study developed an abridged form of the APM dubbed Advanced Progressive Matrices-Smart Version (APM-SV). Results revealed that all 15 items of the APM-SV test yield favourable statistics under 3-Parameter Logistic IRT Model with regards to item discrimination, difficulty and guessing. Item Response Function showed preponderance of APM-SV’s reliability of 0.92. The APM-SV showed perfect fit, is bias-free and very suitable for use in Nigeria. APM-SV scale strongly and positively correlated well with other measures of fluid ability such as the APM scale itself, CFIT, Digit Span scale, and Bennett Mechanical Comprehension Test (BMCT).

Keywords: 3-Parameter Logistic Model, Advanced Progressive Matrices, Item Response Theory, Nigeria, Test Bias, X-Calibre

Item Response Theory Validation of Advanced Progressive Matrices in Nigeria (Published)

Raven’s Advanced Progressive Matrices (APM) is a leading global non-verbal mental ability test for identification of individuals with clear thinking skills who can handle rigorous study programmes and cope with complexity and ambiguity of the contemporary workplace. The test is popularly used in America, Europe and Asia but has never been validated for use in Nigeria. A validation sample of 2100 in Nigeria was randomly drawn for this study. Triangulation research design, adopting Item Response Theory (IRT), guided this validation of APM. Results revealed that all items of the test yield favourable statistics under 3-Parameter Logistic IRT Model with regards to discrimination, difficulty and guessing. Item Response Function showed preponderance of APM’s reliability (0.948) and construct cum concurrent validity (0.701) with Culture Fair Intelligence Test (CFIT). X-Calibre analysis confirmed suitable difficulty indexes (-2.595 to 2.133 b parameter) of APM. The APM is bias-free and very suitable for use in Nigeria.

Keywords: 3-Parameter Logistic Model, Advanced Progressive Matrices, CFIT, Item Response Theory, Nigeria, Test Bias, X-Calibre

Detecting Item Bias in Rivers State JSSCE Business Studies Using Item Response Theory (IRT) Approach (Published)

This study identified biased test items in the Rivers state JSSCE Business Studies conducted in 2009 using Item Response Theory Approach. The Sample comprises 4000 JSS III students in public and private schools that sat for the JSSCE Business Studies Examination in 2009 in Rivers state which were selected through stratified proportionate random sampling. The instruments for data collection were the test items in JSSCE Business Studies conducted in 2009 and a result collection sheet. Two null hypotheses drawn from two research questions were tested at 0.50 probability of correct response. The assumptions of unidimensionality and local independence were checked using factor analysis. The students’ responses to the test items were calibrated with an IRT statistical software named ex-calibre 4.2.2 developed by Assessment Systems Corporation. The results revealed that the test items met the assumptions of unidimensionality and local independence. It also revealed that there is school type bias in the Rivers State JSSCE Business Studies test items for 2009. Based on the findings, recommendations were made, one of them being that business studies curriculum should be restructured so as to accommodate the new technological advances which may be one of the reasons for the presence of school type bias in the Business Studies test conducted in 2009 in Rivers State.

Keywords: Item Bias, Item Characteristic Curve, Item Response Theory, Unidimensionality