The effect of the maximum odds method for addressing missing values and loss ratios in the coefficients of the quadrilateral parameter model, its accuracy and relevance
Article Sidebar
Main Article Content
Abstract
The study aimed to reveal the effect of the maximum odds method to treat missing values and the percentage of loss (10%, 15%, 20%) on the suitability of items and individual coefficients according to the parameter quadrant model. To achieve the objectives of the study, the researcher used the non-verbal reasoning test prepared by Mik Bryon (2012). And their fit according to the parameter quadrant model, and then using the addition of kutool for excel program, responses were deleted (10%, 15%, 20%) and then compensated for the missing values according to the method of maximum likelihood and extracting the individual coefficients, their accuracy and suitability according to the parameter quadrant model. The results showed that:
1- That the assumptions of the response theory are fulfilled, and the indicators of one-dimensional assumptions (explained variance, vocabulary saturation and indicators of local independence) are increasing.
2- There are no statistically significant differences in the proportion of appropriate vocabulary between the complete data on the one hand and the complementary data at the percentage of loss (20%) and (15%), and the results also showed the absence of statistically significant differences in the proportion of appropriate vocabulary between the complementary data between the proportion of Loss (10%) and (15%), there are statistically significant differences in the percentage of appropriate vocabulary between the complete data on the one hand and the complementary data on the percentage of loss (10%), and the results showed that there are statistically significant differences in the percentage of appropriate vocabulary between the complementary data Between the percentage of loss (10%) and (20%), and between the percentage of appropriate vocabulary between the percentage of loss (15%) and (20%).
3- There are no statistically significant differences in the value of the coefficient of difficulty and vocabulary guesswork and its accuracy according to the percentage of loss, and there are statistically significant differences in the value of the coefficient of discrimination and the coefficient of lack of interest and its accuracy according to the percentage of loss, and to find out the sources of the differences, the researcher conducted an examination test, and the results showed that there are differences Statistically significant in the discrimination coefficients between the complete data on the one hand and the complementary data at the loss percentage (10%) and (20%) on the other hand. Distinguishing the complementary data at the percentage of loss (15%) and (20%), and there are statistically significant differences in the disinterestedness transactions between the complete data from the complementary data at the loss percentage (10%). Attention to the percentage of loss (10%) on the one hand, and the discrimination coefficients for the complementary data at the percentage of loss (15%) and (20%), and there are statistically significant differences in the accuracy of the discrimination coefficients between the complete data and the complementary data at the loss ratio (10%). The results also showed that there were statistically significant differences in the accuracy of the coefficients Discrimination at the percentage of loss (10%) on the one hand and the accuracy of the discrimination coefficients for the complementary data at the percentage of loss (15%) and (20%). The results also showed that there were statistically significant differences in the accuracy of the disinterest coefficients at the loss percentage (10%) on the one hand, and the discrimination coefficients for the complementary data at the loss rate (15%) and (20%).
Metrics
Article Details
College of Education for Humanities, TIKRIT UNIVERSITY. THIS IS AN OPEN ACCESS ARTICLE UNDER THE CC BY LICENSE http://creativecommons.org/licenses/by/4.0/
References
Sources
Al-Darabah, Riyadh. (2012). The effect of the method of estimating ability and the method of dealing with missing values on the accuracy of estimating the parameters of paragraphs and individuals. Unpublished doctoral thesis. Yarmouk University: Jordan.
Leave, salary. Al-Darabah, Riyadh. (2014). The effect of the methods of dealing with missing values and the method of estimating the ability on the accuracy of estimating the parameters of paragraphs and individuals. Specialized International Educational Journal. Volume 3. Number 6. pp. 23-47.
Al-Sarayra, Raji Awad. (2018). The effect of the percentage of missing values and the method of processing them on the accuracy of estimating the maximum value of the paragraph informational function and the value of the paragraph stability index. Studies Journal - Educational Sciences. Volume 45. Issue 4. pp. 485–501.
Obeidat, Thouqan. Adass, Abdel Rahman. Abdelhak, Kayed. (2000). Scientific research: (concept, tools, methods). Riyadh: Dar Osama for Publishing and Distribution.
Allam, Saladin. (2001). Diagnostic tests are the benchmark in the educational and psychological fields, Cairo: Dar Al-Fikr Al-Arabi.
Crocker, Linda, and Algina, James (2009). An Introduction to Traditional and Contemporary Measurement Theory, translation, let's, Zinat Youssef, 1st edition, Dar Al Fikr Publishers and Distributors.
Defeat, Heba. (2020). The effect of methods of processing missing values on the parameters of some models of response theory to the individual. Unpublished doctoral thesis. Syria: Aleppo University.
Majali, Fatima. (2017). Comparison of the effectiveness of three methods for processing missing values in light of the quality of paragraph matching of the three-parameter logistic model. A magister message that is not published. Mutah University.
Al-Nuaimi, Izz Al-Din. (2011). The effect of an increase in the number of linked vertebrae on the psychometric properties of vertebra and test. Arab Universities Journal. Volume 9. Number 9. pp. 158-178.
Prestige, Muhammad. (2013). Effect of missing data processing methods on the psychometric properties of multi-response scales (an empirical study and simulation). Ain Shams University Journal of Measurement and Evaluation. Volume 3. Issue 5. pp. 1-57.Anderson, T. W. (1957). Maximum likelihood estimates for a multivariate normal distribution when some observations are missing. Journal of the American Statistical Association, 52,PP. 200–203.
Baraldi, A. N., & Enders, C. K. (2010). An introduction to modern missing data analyses. Journal of school psychology, 48(1), 5-37.
Buck, S. F. (1960). A method of estimation of missing values in multivariate data suitable for use with an electronic computer. Journal of the Royal Statistical Society, Series B, 22, PP. 302–306.
Cantrell, C. E.(1997). Item Response Theory Understanding The One Paramter Rash Model.
Cokluk, O., & Kayri, M. (2011). The Effects of Methods of Imputation for Missing Values on the Validity and Reliability of Scales. Educational Sciences: Theory and Practice, 11(1), PP. 303-309.
Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977). Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society: Series B (Methodological), 39(1), PP. 1-22.
Edgett, G. L. (1956). Multiple regression with missing observations among the independent variables. Journal of the American Statistical Association, 51, PP.122–131.
Enders, C. K. (2010). Missing not at random models for latent curve analyses. Manuscript submitted for publication.
Graham, W. J.(2009). Missing data analysis: Making it work in thereal world. Annual Review of Psychology, 60, PP.549–576
Graham, W. J.(2009). Missing data analysis: Making it work in thereal world. Annual Review of Psychology, 60, PP.549–576
Hartley, H. O. (1958). Maximum likelihood estimation from incomplete data. Biometrics, 14, PP. 174–194.
Henson, R, K. (1999). Understanding The One Paramter Rash Model Of Item Response Theory.
Kalkan, Ö. K., Kara, Y., & Kelecioğlu, H. (2018). Evaluating Performance of Missing Data Imputation Methods in IRT Analyses. International Journal of Assessment Tools in Education, 5(3), PP. 403-416.
Lord, F. M. (1955). Estimation of parameters from incomplete data. Journal of the American Statistical Association, 50, PP. 870–876.
Ludlow, L. H., & O’leary, M. (1999). Scoring omitted and not-reached items: Practical data analysis implications. Educational and Psychological Measurement, 59(4), PP. 615-630.
McKnight, P. E., McKnight, K. M., Sidani, S., & Figueredo, A. J. (2007). Missing data: A gentle introduction. Guilford Press.
Mislevy, R. J., & Wu, P. K. (1988). Inferring examinee ability when some item responses are missing. ETS Research Report Series, 1988(2), i-75.
Schafer, J. L., & Graham, J. W. (2002). Missing data: Our view of the state of the art. Psychological Methods, 7, PP. 147–177.
Wilks, S. S. (1932). Moments and distributions of estimates of population parameters from fragmentary samples. The Annals of Mathematical Statistics, 3(3), PP. 163-195.
Witta, L., & Kaiser, J. (1991). Four Methods of Handling Missing Data with the 1984 General Social Survey.