Teaching assistant
University of Belgrade, Faculty of Organizational Sciences
Born 25.09.1998. in Zvornik, Republic of Srpska, Bosnia and Herzegovina. Citizen of Republic of Serbia since 2018. Graduated Mathematics from University of Belgrade, Faculty of Mathematics, Department of Probability and Statistics in 2021. The next year obtained Master's degree from above mentioned institution. Currently PhD student.
University of Belgrade, Faculty of Organizational Sciences
University of Belgrade, Faculty of Organizational Sciences
University of Belgrade, Faculty of Mathematics
University of Belgrade, Faculty of Mathematics
University of Belgrade, Faculty of Mathematics
University of Belgrade, Faculty of Mathematics
Grammar School "Vuk Karadžić", City of Loznica, Republic of Serbia
"Vuk Karadžić", Roćević, City of Zvornik, Republic of Srpska, Bosnia and Herzegovina
In this paper, a novel test for testing whether data are Missing Completely at Random is proposed. Asymptotic properties of the test are derived utilizing the theory of non-degenerate U-statistics. It is shown that the novel test statistic coincides with the well-known Little's statistic in the case of a univariate nonresponse. Then, the extensive simulation study is conducted to examine the performance of the test in terms of the preservation of type I error and in terms of power, under various underlying distributions, dimensions of the data and sample sizes. Performance of the Little's MCAR test is used as a benchmark for the comparison. The novel test shows better performance in all of the studied scenarios, better preserving the type I error and having higher empirical powers.
Although the era of digitalization has enabled access to large quantities of data, due to their insufficient structuring, some data are often missing, and sometimes the percentage of missing data is significant compared to the entire sample. On the other hand, most of the statistical methodology is designed for complete data. Here we explore the asymptotic properties of non-degenerate U-statistics when the data are missing completely at random and a complete-case approach is utilized. The obtained results are applied to the estimator of Kendall's $tau$ used for testing independence. In this context, the median-based imputation approach is also considered and asymptotic properties are explored. In addition, both complete-case and median imputation approaches are compared in an extensive Monte Carlo study.
Consultation: TBA
Faculty of Organizational Sciences,
Jove Ilića 154,
11000 Belgrade, Serbia.