Somayeh Bahmanabadi; Mohammad reza Falsafinejad; noorali farrokhi; asghar minaei
Abstract
Identification of the consequences of violations of the assumptions of measurement models is a major concern in the field of psychometrics. The purpose of the present study was to investigating the role of test dimensionality violation in equating errors of IRT and classical theory models. Research method ...
Read More
Identification of the consequences of violations of the assumptions of measurement models is a major concern in the field of psychometrics. The purpose of the present study was to investigating the role of test dimensionality violation in equating errors of IRT and classical theory models. Research method was experimental and a 3 × 3 factorial design was used. The study population consisted of all the Mathematical and Technical Sciences Entrance Examiners in 2017 and 2018. The sample group consisted of 5000 examiners who were selected by random sampling. Mathematic test (55 items) was used for equating that three different types of data structure including one-dimensional, two- dimensional and three-dimensional data was generated from it. Data was equated with three equating methods including equipercentile method, true score and observed score equating method. Equating standard errors, bias and root mean square error were used to evaluate the effects of independent variables. To determine the error statistics, the equating results in all three datasets and the three equating methods were repeated 20 times in different samples. Data analysis showed that violation of dimensionality increases equating standard error, bias of equating results and the root mean square error. The bias of equating results in classical methods is more than the IRT methods. The effect of dimensionality violation on equating errors was not different between the classical theory and IRT models.
hamidreza karami; Masoud gramipour; Asghar Minaei
Abstract
Although rasch tree model analysis has been introduced to identify Bias questions in various tests, little research has been done. The purpose of this study was to use the rasch tree model and to investigate the intervening factors in revealing the differential action of the test questions. To answer ...
Read More
Although rasch tree model analysis has been introduced to identify Bias questions in various tests, little research has been done. The purpose of this study was to use the rasch tree model and to investigate the intervening factors in revealing the differential action of the test questions. To answer the research questions, the method of simulation studies and data of the specific test of Amin University of Law Enforcement Sciences were used. The present research is applied in terms of purpose and descriptive in terms of method called psychometric research. The statistical population of the special exam of Amin University of Law Enforcement Sciences in 1398 with the number of 2414 people has been analyzed in full. The DIFtree package in R software was used to determine the detection rate of the differentiation Item Functioning using the rasch tree model. The results of the simulation study showed that the rasch tree model detects the differentiation Item Functioning in samples with a volume of more than 1000 subjects as 100%. The results also showed that in the specific exam of the University of Law Enforcement Sciences, 9 questions have differentiation Item Functioning, in the most important of which, 7 questions in the mathematics group with 18 years of age (second category) and 6 questions in the mathematics group with 19 years of age (category First) has a bias towards the experimental sciences group (third category) and the orientation of the bias has been in favor of the first and second category and to the detriment of the third category.
alireza khoshgooyanfard; Mohammadreza Falsafinejad; noorali farrokhi
Abstract
Nonresponse is an inevitable challenge to large-scale studies and can result in wasting money, time and human resource involved in data collection and can also prevent the studies from obtaining their objects especially scores distribution. Imputation methods have thus been invented to estimate item ...
Read More
Nonresponse is an inevitable challenge to large-scale studies and can result in wasting money, time and human resource involved in data collection and can also prevent the studies from obtaining their objects especially scores distribution. Imputation methods have thus been invented to estimate item nonresponses in order to make inference from a completed data set. Using a simulation study on a real data set in the form of a multivariate experimental design, this paper evaluates the accuracy of three models including cumulative logit model, graded response model and explanatory item response model. The results show that the imputed values of all three models are acceptable under random nonresponse mechanism although the imputed values of the explanatory item response model are always more accurate than those of the other models. If nonrandom nonresponses are occurred, explanatory item response model has acceptable imputed values only at 5% nonresponse rate and the other models are not accurate at all. The results also show that it is more accurate to impute individual item nonresponses and then compute the total score instead of directly imputing the total score.
Asghar Minaei; Zahra Ghafari
Abstract
The biggest worry, discussed in tests being inequitable, is the presence of bias possibility or differential functioning. Because bias causes test validity to be suspected and doubted. Objective: In this research differential item functioning on the whole 14 blocks of mathematics tests of TIMSS in grade ...
Read More
The biggest worry, discussed in tests being inequitable, is the presence of bias possibility or differential functioning. Because bias causes test validity to be suspected and doubted. Objective: In this research differential item functioning on the whole 14 blocks of mathematics tests of TIMSS in grade 8 between Iranian girls and boys has been studied using IRT approach. Method: In the order that, first, data have been recoded by SPSS and the assumption of items being unidimensional in all blocks, by NOHARM software have been studied. In the next step the best model that is known as “base model” has been fit for data by BILOG-MG software. In the next process from that base model for studying the items having differential functioning and anchor, IRTLRDIF (Thissen,2001) has been used and at last for final estimation of item and ability parameters, MULTILOG software has been used. Findings show that from 219 items, being studied, of mathematics test in grade 8 of TIMSS 2011, 144 anchor items and 75 items have DIF and items have differential functioning and it is to the loss of girls, the focal group.
farzaneh roai; ali delavar
Abstract
Background: Meta-analysis is a strong approach, but sometimes leads to wrong and misleading answers. Objective: To conduct case studies of clinical trials and observed cases regarding factors that affect the credibility of meta-research, such as the effect size, the number of analyses, data scale, analyses’ ...
Read More
Background: Meta-analysis is a strong approach, but sometimes leads to wrong and misleading answers. Objective: To conduct case studies of clinical trials and observed cases regarding factors that affect the credibility of meta-research, such as the effect size, the number of analyses, data scale, analyses’ flexibility, method of reporting, and conflict of interest. Research Method: The meta-analysis method was adopted in this research. A case study of corticosteroid therapy in acute bacterial meningitis was discussed in this paper. In addition, the meta-analysis progressed in a step-by-step manner with 6 researches out of 11 ones. Results: The results of the metaanalysis of acute bacterial meningitis indicated that numerous studies have been carried out under such a title in different places. Each author has identified reasons for the use of steroid treatment. Although their reasons were sometimes incomplete, it must be noted that their researches have some things in common.
