Global ETD Search

271	Lasso Regularization for DIF Detection in Graded Response Models Avila Alejo, Denisse 05 1900 (has links) Previous research has tested the lasso method for DIF detection in dichotomous items, but limited research is available on this technique for polytomous items. This simulation study compares the lasso method to hybrid ordinal logistic regression to test performance in terms of TP and FP rates when considering sample size, test length, number of response categories, group balance, DIF proportion, and DIF magnitude. Results showed better Type I error control with the lasso, with smaller sample sizes, unbalanced groups, and weak DIF. The lasso also exhibited more stable Type I error control when DIF was weak, and groups were unbalanced. Lastly, low DIF proportion contributed to better Type I error control and higher TP rates with both methods. DIF analysis lasso regularization polytomous items graded response model Hybrid OLR Item Response Theory Education, Educational Psychology Statistics Education, Tests and Measurements
272	Workplace Social Courage in the United States and India: A Measurement Invariance Study Sturgis, Grayson D. January 2022 (has links) No description available. Occupational Psychology Psychology Statistics measurement invariance psychometrics item response theory confirmatory factor analysis IRT CFA workplace social courage workplace social courage India united states America cultural dimensions Hofstede
273	Respondent and Test Delivery Characteristics that Induce Item Unfolding Lake, Christopher J. 13 October 2010 (has links) No description available. Organizational Behavior Psychological Tests Psychology unfolding item response theory IRT generalized graded unfolding model GGUM attitude structure ambivalence indifference attitude strength
274	Bayesian Model Checking Methods for Dichotomous Item Response Theory and Testlet Models Combs, Adam 02 April 2014 (has links) No description available. Statistics Bayesian Model Checking Posterior Predictive Model Checking Pivotal Discrepancy Measures Prior Predictive Posterior Testlet Model Checking Item Response Theory Person Fit Checking
275	The Development and Validation of All Four TRAILS (Tool for Real-Time Assessment of Information Literacy Skills) Tests for K-12 Students Salem, Joseph A., Jr. 10 December 2014 (has links) No description available. Educational Tests and Measurements Library Science information literacy
276	THE RELATIONSHIP BETWEEN STUDENT EVALUATIONS AND TEACHER QUALITY IN HIGH SCHOOL IN SAUDI ARABIA: ITEM RESPONSE THEORY ANALYSIS AND MULTILEVEL MODELING Alqarni, Abdulelah M., Dr 04 May 2015 (has links) No description available. Educational Tests and Measurements Student evaluations student ratings of teacher teacher quality Item response theory IRT Rasch analysis Multilevel modeling hierarchical linear model HLM
277	Faking is a FACT: Examining the Susceptibility of Intermediate Items to Misrepresentation Foster, Garett C. 22 March 2017 (has links) No description available. Psychology Ideal Point Item Response Theory Faking Selection Personality Item Writing FACT Taxonomy Intermediate Items Delta Shift Theta Shift Appropriateness Measurement
278	Exploring item response theory in forced choice psychometrics for construct and trait interpretation in cross-cultural context Huang, Teng-Wei 03 1900 (has links) This thesis explores item response theory (IRT) in the Personal Profile Analysis (PPA) from Thomas International. The study contains two parts (Part 1 and Part II) for which two sample groups were collected. For Part I of the research 650 participants were collected via the old form (CPPA25/C7) in the Beijing office of Thomas International in China (male=323, Female=267, missing=60). Part II of the research used the amended form in the same area and collected a sample of 307 (male=185, female=119, missing=3). The study postulates that IRT methods are applicable to forced-choice psychometrics. The results of Part I showed that the current CPPA form functions, to some extent, according to PPA’s original constructs. Part I of the research identified 16 items that need to be amended (called Amend A in this research). The amended form was returned to China for the collection of samples for Part II, and the results are deemed acceptable. The study concludes with a research protocol for PPA-IRT research generated from the current research. The research protocol suggests four levels of analysis for forced choice (FC) psychometrics, namely: 1. Textual analysis, 2. Functional analysis, 3. Dynamic analysis, and 4. Construct analysis. / Psychology / M.A. (Psychology) Psychometric theory Classical Test theory Cross culture research Psychometric adaptation General (graded) Respose model Item Response Theory Forced choice Personal Profile Analysis (PPA) Chinese translation Research protocol 150.287 Item response theory Psychological tests Personality and occupation
279	Exploring item response theory in forced choice psychometrics for construct and trait interpretation in cross-cultural context Huang, Teng-Wei 03 1900 (has links) This thesis explores item response theory (IRT) in the Personal Profile Analysis (PPA) from Thomas International. The study contains two parts (Part 1 and Part II) for which two sample groups were collected. For Part I of the research 650 participants were collected via the old form (CPPA25/C7) in the Beijing office of Thomas International in China (male=323, Female=267, missing=60). Part II of the research used the amended form in the same area and collected a sample of 307 (male=185, female=119, missing=3). The study postulates that IRT methods are applicable to forced-choice psychometrics. The results of Part I showed that the current CPPA form functions, to some extent, according to PPA’s original constructs. Part I of the research identified 16 items that need to be amended (called Amend A in this research). The amended form was returned to China for the collection of samples for Part II, and the results are deemed acceptable. The study concludes with a research protocol for PPA-IRT research generated from the current research. The research protocol suggests four levels of analysis for forced choice (FC) psychometrics, namely: 1. Textual analysis, 2. Functional analysis, 3. Dynamic analysis, and 4. Construct analysis. / Psychology / M.A. (Psychology) Psychometric theory Classical Test theory Cross culture research Psychometric adaptation General (graded) Respose model Item Response Theory Forced choice Personal Profile Analysis (PPA) Chinese translation Research protocol 150.287 Item response theory Psychological tests Personality and occupation
280	Zdraví a jeho socioekonomické ukazatele - testování reliability a validity na PSAS / Health and Its Socioeconomic Indicators - Reliability and Validity Testing of Scales Juráčková, Veronika January 2018 (has links) The diploma thesis "Health and Socio-economic Indicators - reliability and validity testing of the PSAS" deals with a theoretical concept of health and its socio-economic indicators. A substantial part of the work concentrates on the application of PSAS tools to the Czech population and determining whether the range is reliable and valid for Czech respondents. To determine the reliability, a complex test is used for the whole range through the value of Cronbach's Alpha, and then the Item Response Theory (IRT) is also tested. The IRT test is done using the 18-point Likert's range of responses, of which is the PSAS composed. The validity is tested based on confirmatory factor analysis, using the construct validity as well as analysis of cognitive interviews for face validity. The secondary data analysis is done in SPSS, MPLUS, R, and IRTPRO programs. The last two programs are used to test the lesser known Item Response Theory.

Search results