The foundation of network data analysis in psychometrics rests on particular theory, special ontological assumptions and particular methodology. Therefore it is possible to call network analysis as an independent paradigm with given techniques for data gathering and data analysis. This study introduces the analysis of network data as a psychometric- mathematical technique, and its use in questionnaire item analysis. To achieve this goal, data gathered from implementation of a self- made questionnaire on 1000 Tehran's high school students. The questionnaire was made based on occupational- personality Holland theory. Researchers analyzed questionnaire’s items according to conventional methods (classical test theory, item response theory and factor analysis) and proposed method (network data analysis). Comparison of the results shows that a complete conformity between conventional methods final outputs and the outputs from network data analysis. Therefore, psychometricians can use network data analysis independently or alongside conventional methods to analyze questionnaires items. Advantages of such a method are simplicity, accuracy, being virtually and integrity.

The Italian edition of the Templer’s Death Anxiety Scale (DAS, 1970), was administrated on 138 under-graduate students of Chamran University. The aim of this administration, was the factor analyis of the questionnaire. The results obtained from Principal Components Analysis method (PC) extracted five factors, among that, the greatest proportion of variance accounted to the first factor. In addition, the split half reliability coefficient was 0.62 for DAS, and Cronbach’s Alfa coefficient was 0.73; the correlation coefficient between DAS and the Death Concern Scale was 0.40 and between DAS and Manifest Anxiety Scale was 0.43.

Recent years have witnessed an increasing interest in providing new insights into modern language testing method targeting test bias. In this study, item-focused trees (IFT) approach was applied to identify uniform and non-uniform differential item functioning (DIF) of an English as a foreign language (EFL) reading comprehension test. The multistage cluster sampling method was employed to randomly choose a large sample of 4937 students who took the entrance exam of MA program in English studies. The reading comprehension section of the general English test including 20 items was selected for the IFT analysis. Three categorical and continuous DIF source variables including gender and academic background were concomitantly taken into account for the IFT analysis, which is capable of handling more than one variable with both binary and continuous measurement. Then, in the final stage of IFT analysis within a logistic regression framework, uniform and nonuniform DIF was analyzed using DIF tree package of R. The results showed that 10 items had uniform DIF in which 2 items had 2 joint DIF predictor variables (2 splits) and 8 items had only one split. Additionally, 6 splits and 5 non-uniform DIF items were found in non-uniform DIF analysis in which only 1 item had 2 simultaneous DIF source variables. Furthermore, gender and background knowledge had significant relationships with EFL reading comprehension. This study promises practical implications for addressing gender and background knowledge differences in EFL reading comprehension studies on the one hand, and impacting language testing methodology on the other.

One of the factors that can be the link between our intentions and actions and their external consequences is human agency, which indicates the conscious design and intentional execution of actions by the individual in order to influence future events.Objective and Method: This research with a developmental approach of psychometric method and method 1, examines the psychometric indices of the Human Factor Characteristics Scale using the classical theory of test score measurement and the graduated question-answer theory. The purpose of this study, which included high school students in Tehran, was selected by cluster sampling of 500 people as a sample size and statistical analysis was performed on 481 data. To collect the data, the ion Human Agent Characteristics Scale (2011) was used and the research questions were evaluated using IRTPRO and SPSS software.Results:The assumption of local independence based on Pearson x2 index was established by applying Simjima's calibrated question-answer theory and the assumption of being one-dimensional based on the analysis of multidimensional question-answer theory. Diagnosis parameters with question-answer approach and classical approach Test score Both item 25 approach had the lowest and item 2 had the highest diagnosis parameter. The answer thresholds for all the questions were so far apart that no option was covered by the other option, and the options were independently selected by individuals at intervals of theta. The total scale was calculated with Cronbach's alpha of 0.945, intentionality of 0.894, foresight of 0.780, self-reactivity of 0.871 and rethinking of 0.762. Also, the role of each item in internal consistency was investigated by the loop method, which all questions had a favorable role in internal consistency of this scale. The value of the validity coefficient obtained from the question-answer theory was obtained by marginal method for intentionality 0.92, forethought 0.85, self-reaction 0.91, rethinking 0.83..

The present study aims at investigating the presence of Differential Item Functioning (DIF) in terms of gender in a high stakes language proficiency test, the National University Entrance Exam for Foreign Languages (NUEEFL). The participants (N = 5000) of this study have been selected randomly from a pool of examinees who had taken the NUEEFL as a university entrance requirement for English language studies (English literature, Teaching, and Translation). The results revealed that among 95 items, 40 items exhibit DIF between male and female. Our investigation revealed that the test is not unidimensional and a correct answer requires other knowledge, ability, and skill than the ones that the items aim to measure. It is concluded that the NUEEFL test’ s scores are not free of construct-irrelevant variance and the overall fairness of the test is under question. In addition, the current research provides several important implications for test designers, stake-holders, administrators, as well as teachers and students.

This study was carried out to identify the major factors of the revised version of the Mathematical Self-Efficacy Scale-Revised (MSES-R). The sample consisted of 233 university students (125 females and 107 males) who have had a mathematical or statistics course. The results obtained from principal components analysis extracted four factors which have been consisted to the previous research results and confirmed the constract validity of the scale. Also the Pearson"s correlation coefficient calculated between the MSES-R and the General Self-efficacy Scale was 0.39. The reliability coefficient (Alfa-Corenbach) obtained for whole scale as well as the subscales were satisfactory.

Introduction: Measuring level of disability in elderly in attention to their physical status requires an instrument practicable in elderly and easy to score.Objective: Survey the reliability and validity of the HAQ 8-item DI in older people residing in Kashan Golabchi nursing home.Methods: In this methodological study, samples were chosen by census method (n=100). After translation of original copy, the inter-rater agreement between evaluators and internal consistency were assessed. For validity determination, concurrent validity, exploratory factor analysis and Known-groups were used. The data were analyzed using Pearson correlation coefficient, Intra-class correlation coefficient (ICC), Kappa, Equal- Length spearman-brown, Guttman, Alpha Cronbach coefficient, Kruskal-Wallis test and factor analysis via principal component analysis with varimax rotation.Results: Inter-rater reliability coefficient for every item was good or excellent (Kappa>0.7). ICC in relation to overall instrument was 0.992. The questionnaire reliability coefficient (internal consistency) was 0.95-0.98. Item-total correlation confirmed its reliability too. Its concurrent validity with original Barthel index was confirmed (r=-0.92, p<0.0001). The known-groups approach revealed this tool as valid (p<0.0001). The factor analysis extracted one main factor with value more than one which could explain %87.15 of the total variance of elderly disability.Conclusion: The Persian translation of HAQ 8-item DI for evaluation of disability in elderly people residing in Golabchi nursing home is valid and reliable.