Anita Israni's research focuses on hierarchical linear modeling, specifically working with longitudinal and mediation data. Her interests include extending the basic multilevel models to incorporate data structure complexities, such as cross-classified or multiple membership structures that are usually encountered in empirical data, and measurement error to improve reliability and accuracy of parameters estimates. Israni also has experience in software development. Her experience has allowed her to work with Unix and Linux, C++, and R, among others. Much of her academic research has been conducted using a Bayesian approach where she has used the following Bayesian-specific software programs: WinBUGS, OpenBUGS, and Rstan. She has used the supercomputer at the University of Texas at Austin for multiple simulation analyses for her research. Israni teaches undergraduate and graduate statistics courses in the College of Education. She has co-authored a chapter detailing an approach to simultaneously modeling inter-related student and teacher test score data while incorporating a cross-classified model. She also has extensive experience in the private education field with administration management and teaching a variety of mathematical and technical courses, including Calculus, Differential Equations, Engineering Economics, Probability & Statistics, and Computer Science.