Yazar "Atilgan, Hakan" seçeneğine göre listele

Listeleniyor 1 - 7 / 7
  • Küçük Resim Yok
    Öğe
    The eTIMSS and TIMSS Measurement Invariance Study: Multigroup Factor Analyses and Differential Item Functioning Analyses with the 2019 Cycle
    (Assoc Measurement & Evaluation Education & Psychology, 2024) Yalcinkaya, Murat; Atilgan, Hakan; Dascioglu, Selim; Aydin, Burak
    In this study, measurement invariance and differential item functioning (DIF) studies of the TIMSS 2019 4th and 8thgrade mathematics and science achievement tests were conducted for the country groups participating in both TIMSS and eTIMSS. The study sample consisted of 9560 responders of the first booklet of the 2019 cycle. Multiple Group Confirmatory Factor Analysis (MGCFA) was utilized to test measurement invariance, and Mantel-Haenszel (MH), Logistic Regression (LR), and SIBTEST were used for the DIF analyses. The measurement invariance results indicated strict invariance between groups for all tests which included 111 items in total. In the DIF analyses, for the 4th and 8th -grade mathematics tests, only three items showed moderate DIF with MH, and four items showed DIF with SIBTEST. For the 4th -grade science test, one item showed moderate DIF with both MH and SIBTEST. However, in the 8th -grade science test, no items showed DIF with MH and LR methods, while four items showed moderate DIF with SIBTEST. Overall, MH and SIBTEST techniques were in agreement, whereas LR method produced inconsistent results and showed disagreement with these two methods. The results of the measurement invariance analysis and the LR method were consistent and indicated equivalency of TIMSS and e-TIMSS scores.
  • Küçük Resim Yok
    Öğe
    PISA 2015 Reading Test Item Parameters Across Language Groups: A measurement Invariance Study with Binary Variables
    (Assoc Measurement & Evaluation Education & Psychology, 2021) Bagdu Soyler, Pelin; Aydin, Burak; Atilgan, Hakan
    Large-scale international assessments, including PISA, might be useful for countries to receive feedback on their education systems. Measurement invariance studies are one of the active research areas for these assessments, especially cross-cultural and linguistic comparability have attracted attention. PISA questions are prepared in the English language, and students from many countries answer the translated form. In this respect, the purpose of our study is to investigate whether there is a measurement invariance problem across native English and non-native English speaker groups in the PISA-2015 reading skills subtest. The study sample included students from Canada, the USA, and the UK as the native speaker group and students from Japan, Thailand, and Turkey as the non-native speaker group. Measurement invariance studies taking into account the binary structure of the data set for these two groups revealed that eight of the twenty-eight items in the PISA-2015 reading skills test had possible limitations in equivalence.
  • Küçük Resim Yok
    Öğe
    Predicting aggression in children with ADHD
    (Biomed Central Ltd, 2014) Ercan, Elif; Ercan, Eyup Sabri; Atilgan, Hakan; Basay, Burge Kabukcu; Uysal, Taciser; Inci, Sevim Berrin; Ardic, Ulku Akyol
    Objective: The present study uses structural equation modeling of latent traits to examine the extent to which family factors, cognitive factors and perceptions of rejection in mother-child relations differentially correlate with aggression at home and at school. Methods: Data were collected from 476 school-age (7-15 years old) children with a diagnosis of ADHD who had previously shown different types of aggressive behavior, as well as from their parents and teachers. Structural equation modeling was used to examine the differential relationships between maternal rejection, family, cognitive factors and aggression in home and school settings. Results: Family factors influenced aggression reported at home (.68) and at school (.44); maternal rejection seems to be related to aggression at home (.21). Cognitive factors influenced aggression reported at school (.-05) and at home (-.12). Conclusions: Both genetic and environmental factors contribute to the development of aggressive behavior in ADHD. Identifying key risk factors will advance the development of appropriate clinical interventions and prevention strategies and will provide information to guide the targeting of resources to those children at highest risk.
  • Küçük Resim Yok
    Öğe
    A Preliminary Study to Evaluate the Reproducibility of Factor Analysis Results: The Case of Educational Research Journals in Turkey
    (Assoc Measurement & Evaluation Education & Psychology, 2019) Aydin, Burak; Kaplan, Mehmet; Atilgan, Hakan; Gurel, Sungur
    In quantitative research, an attempt to reproduce previously reported results requires at least a transparent definition of the population, sampling method, and the analyses procedures used in the prior studies. Focusing on the articles published between 2010 and 2017 by the four prestigious educational research journals in Turkey, this study aimed to investigate the reproducibility of the factor analysis results from a theoretical perspective. A total of 275 articles were subject to descriptive content analysis. Results showed that 77.8% of the studies did not include an explicit definition of the population under interest, and in 50.9% of the studies, the sampling method was either not clear or reported to be convenience sampling. Moreover, information about the missing data or a missing data dealing technique was absent in the 76% of the articles. Approximately, half of the studies were found to have inadequate model fit. Furthermore, in almost all studies, it could not be determined whether the item types (i.e., levels of measurement scales) were taken into consideration during the analyses. In conclusion, the majority of the investigated factor analysis results were evaluated to be non-reproducible in practice.
  • Küçük Resim Yok
    Öğe
    Reliability of Essay Ratings: A Study on Generalizability Theory
    (Ani Yayincilik, 2019) Atilgan, Hakan
    Purpose: This study intended to examine the generalizability and reliability of essay ratings within the scope of the generalizability (G) theory. Specifically, the effect of raters on the generalizability and reliability of students' essay ratings was examined. Furthermore, variations of the generalizability and reliability coefficients with respect to the number of raters and optimal number of raters for obtaining optimal reliability of the rating of the writing ability of a student, which is considered to be an implicit trait as a whole and in its sub-dimensions of wording/writing, paragraph construction, and title selection, were determined. Research Methods: The student sample of the study comprised 443 students who were selected via random cluster sampling, and rater sample of this study comprised four Turkish teachers. All the essays written by the students in the sample were independently rated on a writing skill scale (WSS), which is an ordinal scale comprising 20 items, by four trained teachers. In this study, data analysis was performed using the multivariate p degrees x i degrees x r degrees design of the G theory. Finding: In the G studies that were performed, variances of the rater (r) as well as item and rater (ixr) were low in all sub-dimensions; however, variance of the object of measurement and rater (pxr) was relatively high. The presence of trained raters increased the reliability of the ratings. Implications for Research and Practice: In the decision (D) study analyses of the original study conducted using four raters, the G and Phi coefficients for the combined measurement were observed to be .95 and .94, respectively. Further, the G and Phi coefficients were .91 and .90, respectively, for the alternative D studies that were conducted by two trained raters. Thus, rating of essays by two trained raters may be considered to be satisfactory. (C) 2019 Ani Publishing Ltd. All rights reserved
  • Küçük Resim Yok
    Öğe
    Sample Size for Estimation of G and Phi Coefficients in Generalizability Theory
    (Ani Yayincilik, 2013) Atilgan, Hakan
    Problem Statement: Reliability, which refers to the degree to which measurement results are free from measurement errors, as well as its estimation, is an important issue in psychometrics. Several methods for estimating reliability have been suggested by various theories in the field of psychometrics. One of these theories is the generalizability theory. In generalizability theory, two distinct reliability coefficients are estimated: the generalizability coefficient (G coefficient) for relative evaluation, and the index of dependability (Phi coefficient) for absolute decisions. Like in all methods of reliability estimation, G and Phi coefficients are estimated based on a data set obtained from a sample as a result of administering the instrument. Therefore, it has been a critical issue to determine what sample size is necessary in order to reliably estimate the population's characteristics. Purpose of Study: The purpose of this study is to determine the adequate sample size required to ensure that the G and Phi coefficients obtained from a sample can estimate the G and Phi coefficients for the population in an unbiased way. Methods: A total of 480691 students who took Form A of the SBS test for the 60, grade in 2008 were considered as the population of the study. Using a bootstrap method, a total of 1200 students were selected from this population, randomly falling into 12 subgroups consisting of different sample sizes (n=30, 50, 100, 200, 300, 400, 500, 600, 700, 800, 900, 1000), with each sample size having 100 replications. Since the test battery contained five subtests with distinct contents and numbers of items, and all items were replied to by all participants, a p(square) x t(c) multivariate G theory design was used. G and Phi reliability coefficients were estimated both for the population and each of the 12 distinct samples of different sizes. The relative root mean square error (R-RMSE) index was used as the error index to analyze the consistency of the G and Phi coefficients with the G and Phi parameters estimated for the population. Findings and Results: It was found that the G and Phi coefficients estimated for a sample size of 30 tended to be less than the G and Phi parameters, and the R-RMSE value was greater than.01. When the sample size was 50 or more, R-RMSE values were less than.01. Thus it can be said that G and Phi coefficients are robust estimators of G and Phi parameters. Moreover, it was concluded that where the sample size is 400 or greater, R-RMSE values become stable. It was seen that a sample size of 400 is a more exact and robust estimator of G and Phi parameters, and increasing the sample size over 400 does not make a significant contribution to the unbiased estimation of G and Phi parameters. Conclusions and Recommendations: A sample size of 30 does not provide an adequately unbiased estimation of G and Phi coefficients. It can be recommended that sample sizes of 50 to 300 are adequate for a robust estimation of G and Phi coefficients; however, a more exact and robust estimation requires a sample size of 400. In future research, the sample size for facets using different designs of G theory can be studied.
  • Küçük Resim Yok
    Öğe
    Sample Size for Estimation of G and Phi Coefficients in Generalizability Theory
    (Ani Yayincilik, 2013) Atilgan, Hakan
    Problem Statement: Reliability, which refers to the degree to which measurement results are free from measurement errors, as well as its estimation, is an important issue in psychometrics. Several methods for estimating reliability have been suggested by various theories in the field of psychometrics. One of these theories is the generalizability theory. In generalizability theory, two distinct reliability coefficients are estimated: the generalizability coefficient (G coefficient) for relative evaluation, and the index of dependability (Phi coefficient) for absolute decisions. Like in all methods of reliability estimation, G and Phi coefficients are estimated based on a data set obtained from a sample as a result of administering the instrument. Therefore, it has been a critical issue to determine what sample size is necessary in order to reliably estimate the population's characteristics. Purpose of Study: The purpose of this study is to determine the adequate sample size required to ensure that the G and Phi coefficients obtained from a sample can estimate the G and Phi coefficients for the population in an unbiased way. Methods: A total of 480691 students who took Form A of the SBS test for the 60, grade in 2008 were considered as the population of the study. Using a bootstrap method, a total of 1200 students were selected from this population, randomly falling into 12 subgroups consisting of different sample sizes (n=30, 50, 100, 200, 300, 400, 500, 600, 700, 800, 900, 1000), with each sample size having 100 replications. Since the test battery contained five subtests with distinct contents and numbers of items, and all items were replied to by all participants, a p(square) x t(c) multivariate G theory design was used. G and Phi reliability coefficients were estimated both for the population and each of the 12 distinct samples of different sizes. The relative root mean square error (R-RMSE) index was used as the error index to analyze the consistency of the G and Phi coefficients with the G and Phi parameters estimated for the population. Findings and Results: It was found that the G and Phi coefficients estimated for a sample size of 30 tended to be less than the G and Phi parameters, and the R-RMSE value was greater than.01. When the sample size was 50 or more, R-RMSE values were less than.01. Thus it can be said that G and Phi coefficients are robust estimators of G and Phi parameters. Moreover, it was concluded that where the sample size is 400 or greater, R-RMSE values become stable. It was seen that a sample size of 400 is a more exact and robust estimator of G and Phi parameters, and increasing the sample size over 400 does not make a significant contribution to the unbiased estimation of G and Phi parameters. Conclusions and Recommendations: A sample size of 30 does not provide an adequately unbiased estimation of G and Phi coefficients. It can be recommended that sample sizes of 50 to 300 are adequate for a robust estimation of G and Phi coefficients; however, a more exact and robust estimation requires a sample size of 400. In future research, the sample size for facets using different designs of G theory can be studied.