scholarly journals Dimensionality assessment of binary response test items: A non-parametric approach of bayesian item response theory measurement

2020 ◽  
Vol 9 (2) ◽  
pp. 385
Author(s):  
Musa Adekunle Ayanwale ◽  
Flourish O. Isaac-oloniyo ◽  
Funmilayo Rebecca Abayomi
Keyword(s):  
Factor Analysis ◽  
Item Response Theory ◽  
Mathematics Achievement ◽  
Item Response ◽  
Achievement Test ◽  
Binary Response ◽  
Full Information ◽  
Test Items ◽  
Essential Unidimensionality ◽  
Second Eigenvalue

This study investigated dimensionality of Binary Response Items through a non-parametric technique of Item Response Theory measurement framework. The study used causal comparative research type of non-experimental design. The sample consisted of 5,076 public senior secondary school examinees (SSS3) between the age of 14-16 years from 45 schools, which were drawn randomly from three senatorial districts of Osun State, Nigeria. Instrument used for this study was 2018 Osun State unified multiple-choice mathematics achievement test items with empirical reliability coefficient of 0.82. Data obtained were analysed using Non-linear factor analysis, Stout’s Test of Essential Unidimensionality (STEU), Factor Analysis (FA), Full Information Factor Analysis (FIFA) and Bootstrap Modified Parallel Analysis Test (BMPAT). Results showed that both the BMPAT and STEU ascertained violation of unidimensionality assumption of the test items (the observed difference in the second eigenvalue of the observed data and that of second eigenvalue of the simulated data was statistically significant, p = 0.0099; Stout’s test rejected the assumption of essential unidimensionality, T = 10.6260, p<0.05). Non-linear factor analysis and full information factor analysis revealed that four dimensions embedded in the test items and loadings of the items showed within-item multidimensionality respectively. The authors’ concluded that modeling examinees’ performance with unidimensional model when it was actually multidimensional in nature would affect performance of examinees adversely and could lead to blur judgment. Consequently, it is recommended that unidimensional scoring method of Osun State unified mathematics achievement test implicit in Classical Test Theory should be jettisoned and an appropriate scoring model (multidimensional) should be embraced.

scholarly journals Developing a Numerical Ability Test for Students of Education in Jordan: An Application of Item Response Theory

2015 ◽  
Vol 9 (1) ◽  
pp. 161
Author(s):  
Eman Rasmi Abed ◽  
Mohammad Mustafa Al-Absi ◽  
Yousef Abdelqader Abu shindi
Keyword(s):  
Factor Analysis ◽  
Item Response Theory ◽  
Item Response ◽  
Information Function ◽  
Response Theory ◽  
Ability Test ◽  
Numerical Ability ◽  
Test Items ◽  
Test Information ◽  
Test Information Function

<p class="apa">The purpose of the present study is developing a test to measure the numerical ability for students of education. The sample of the study consisted of (504) students from 8 universities in Jordan. The final draft of the test contains 45 items distributed among 5 dimensions.</p><p class="apa">The results revealed that acceptable psychometric properties of the test; items parameters (difficulty, discrimination) were estimated by item response theory IRT, the reliability of the test was assessed by: Cronbach’s Alpha, average of inter-item correlation, and test information function (IRT), and the validity of the test was assessed by: arbitrator's views, factor analysis, RMSR, and Tanaka Index.</p><p class="apa">The numerical ability test can be used to measure the strength and weaknesses in numerical ability for educational faculty students, and the test can be used to classify students on levels of numerical ability.</p>

scholarly journals Test fairness and assessment of differential item functioning of mathematics achievement test for senior secondary students in Cross River state, Nigeria using item response theory

2021 ◽  
Vol 20 (1) ◽  
pp. 55-62
Author(s):  
Anthony Pius Effiom
Keyword(s):  
Item Response Theory ◽  
Mathematics Achievement ◽  
Differential Item Functioning ◽  
Item Response ◽  
Female Students ◽  
Response Theory ◽  
Test Fairness ◽  
Cross River State ◽  
Test Items ◽  
Item Functioning

This study used Item Response Theory approach to assess Differential Item Functioning (DIF) and detect item bias in Mathematics Achievement Test (MAT). The MAT was administered to 1,751 SS2 students in public secondary schools in Cross River State. Instrumentation research design was used to develop and validate a 50-item instrument. Data were analysed using the maximum likelihood estimation technique of BILOG-MG V3 software. The result of the study revealed that 6% of the total items exhibited differential item functioning between the male and female students. Based on the analysis, the study observed that there was sex bias on some of the test items in the MAT. DIF analysis attempt at eliminating irrelevant factors and sources of bias from any kind for a test to yield valid results is among the best methods of recent. As such, test developers and policymakers are recommended to take into serious consideration and exercise care in fair test practice by dedicating effort to more unbiased test development and decision making. Examination bodies should adopt the Item Response Theory in educational testing and test developers should therefore be mindful of the test items that can cause bias in response pattern between male and female students or any sub-group of consideration. Keywords: Assessment, Differential Item Functioning, Validity, Reliability, Test Fairness, Item Bias, Item Response Theory.

scholarly journals Psychometric Analysis of Economics Achievement Test Using Item Response Theory

2020 ◽  
Vol 10 (2) ◽  
pp. 59
Author(s):  
Roseline Ifeoma Ezechukwu ◽  
Basil Chinecherem, E. Oguguo ◽  
Catherine U. Ene ◽  
Clifford O. Ugorji
Keyword(s):  
Item Response Theory ◽  
Item Response ◽  
Research Question ◽  
Achievement Test ◽  
Choice Test ◽  
Response Theory ◽  
Test Items ◽  
Significant Difference ◽  
Research Questions ◽  
Two Parameter

This study determined the psychometric properties of the Economics Achievement Test (EAT) using Item Response Theory (IRT). Two popular IRT models namely, one-parameter logistics (1PL) and two-parameter logistics (2PL) models were utilized. The researcher adopted instrumentation research design. Four research questions and two hypotheses were formulated to guide the study. The population size is five thousand, three hundred and sixty-two (5,362) from thirty-seven (37) schools. The sample for the study was 1,180 senior secondary school students (SSS3) drawn using multi-stage sampling procedure. The 1,180 students were stratified according to gender which resulted to 885 females and 295 males. The instrument for the study consisted of 50 multiple-choice test items on the economics achievement test, developed by the researchers. Reliability and validity for each item and for the whole test were established according to the one-parameter and two-parameter logistic models. Research question one was answered using 1PLM, while research questions two and three were answered using 2PLM IRT model. Hypothesis one was tested using t-test analysis of difference between the difficulty parameters estimated using 1PLM and 2PLM while hypothesis two was tested using Chi-square. The finding of the study revealed significant difference between the item difficulties estimated using 1PLM and 2PLM. Also the observed scores of the testees on the test items fit the 1PL 2PL models.

scholarly journals The Revised Mood Rhythm Instrument: A Large Multicultural Psychometric Study

2021 ◽  
Vol 10 (3) ◽  
pp. 388
Author(s):  
Melissa Alves Braga de Oliveira ◽  
Euclides de Mendonça Filho ◽  
Alicia Carissimi ◽  
Luciene Lima dos Santos Garay ◽  
Marina Scop ◽  
...  
Keyword(s):  
Factor Analysis ◽  
Item Response Theory ◽  
Network Analysis ◽  
Psychometric Properties ◽  
Item Response ◽  
Response Theory ◽  
Item Response Theory Analysis ◽  
Increased Risk ◽  
Psychometric Analyses ◽  
Self Reporting Questionnaire

Background: Recent studies with the mood rhythm instrument (MRhI) have shown that the presence of recurrent daily peaks in specific mood symptoms are significantly associated with increased risk of psychiatric disorders. Using a large sample collected in Brazil, Spain, and Canada, we aimed to analyze which MRhI items maintained good psychometric properties across cultures. As a secondary aim, we used network analysis to visualize the strength of the association between the MRhI items. Methods: Adults (n = 1275) between 18–60 years old from Spain (n = 458), Brazil (n = 415), and Canada (n = 401) completed the MRhI and the self-reporting questionnaire (SRQ-20). Psychometric analyses followed three steps: Factor analysis, item response theory, and network analysis. Results: The factor analysis indicated the retention of three factors that grouped the MRhI items into cognitive, somatic, and affective domains. The item response theory analysis suggested the exclusion of items that displayed a significant divergence in difficulty measures between countries. Finally, the network analysis revealed a structure where sleepiness plays a central role in connecting the three domains. These psychometric analyses enabled a psychometric-based refinement of the MRhI, where the 11 items with good properties across cultures were kept in a shorter, revised MRhI version (MRhI-r). Limitations: Participants were mainly university students and, as we did not conduct a formal clinical assessment, any potential correlations (beyond the validated SRQ) cannot be ascertained. Conclusions: The MRhI-r is a novel tool to investigate self-perceived rhythmicity of mood-related symptoms and behaviors, with good psychometric properties across multiple cultures.

scholarly journals A Short Note on Estimating the Testlet Model With Different Estimators in Mplus

2017 ◽  
Vol 78 (3) ◽  
pp. 517-529 ◽  
Author(s):  
Yong Luo
Keyword(s):  
Item Response Theory ◽  
Item Response ◽  
Latent Variable ◽  
Short Note ◽  
Bifactor Model ◽  
Estimation Methods ◽  
Full Information ◽  
Modeling Software ◽  
Two Parameter ◽  
Item Response Theory Models

Mplus is a powerful latent variable modeling software program that has become an increasingly popular choice for fitting complex item response theory models. In this short note, we demonstrate that the two-parameter logistic testlet model can be estimated as a constrained bifactor model in Mplus with three estimators encompassing limited- and full-information estimation methods.

scholarly journals Employment of Item Response Theory to measure change in Children's Analogical Thinking Modifiability Test

2013 ◽  
Vol 30 (4) ◽  
pp. 479-486
Author(s):  
Odoisa Antunes de Queiroz ◽  
Ricardo Primi ◽  
Lucas de Francisco Carvalho ◽  
Sônia Regina Fiorim Enumo
Keyword(s):  
Item Response Theory ◽  
Item Response ◽  
Dynamic Testing ◽  
Intermediate Phase ◽  
Cognitive Testing ◽  
Difficulty Level ◽  
Response Theory ◽  
Analogical Thinking ◽  
Test Items ◽  
Post Test

Dynamic testing, with an intermediate phase of assistance, measures changes between pretest and post-test assuming a common metric between them. To test this assumption we applied the Item Response Theory in the responses of 69 children to dynamic cognitive testing Children's Analogical Thinking Modifiability Test adapted, with 12 items, totaling 828 responses, with the purpose of verifying if the original scale yields the same results as the equalized scale obtained by Item Response Theory in terms of "changes quantifying". We followed the steps: 1) anchorage of the pre and post-test items through a cognitive analysis, finding 3 common items; 2) estimation of the items' difficulty level parameter and comparison of those; 3) equalization of the items and estimation of "thetas"; 4) comparison of the scales. The Children's Analogical Thinking Modifiability Test metric was similar to that estimated by the TRI, but it is necessary to differentiate the pre and post-test items' difficulty, adjusting it to samples with high and low performance.

Sign in / Sign up

Export Citation Format

Share Document