top of page

Expertise in research and data analysis

My expertise in research and data analysis included:

Statistical Modeling

  • Generalized Linear Models (GLM): Linear, logistic, ordinal, and multinomial regression models to explore relationships between variables for both continuous and categorical outcomes.

  • Group Comparisons: ANOVA, MANOVA, and t-tests for comparing group means and variances.

  • Distribution Analysis & Transformation: Assessing normality, skewness/kurtosis, and applying transformations when necessary.

  • Non-parametric Methods: Techniques such as Wilcoxon, Mann–Whitney U, and Kruskal–Wallis tests, quantile regression, Locally Weighted Regression etc. when data do not meet parametric assumptions 

 
Multilevel Modeling

  • Hierarchical Linear Models (HLM): Analyzing nested data (e.g., students within classes), estimating variability across levels.

  • Fixed/Random Effects Models: Controlling for unobserved heterogeneity or estimating unit-specific effects.

  • Cross-Classified & Longitudinal Models: Handling data that doesn’t fit strictly hierarchical structures or tracks change over time.

 
Structural Equation Modeling (SEM)

  • Path Analysis, CFA, Latent Variable Models: Testing theoretical models involving direct and indirect effects, latent constructs.

  • Mediation & Moderation Models: Examining how and under what conditions effects occur.

 
Latent Variable & Mixture Models

  • Latent Class/Profile Analysis: Identifying hidden subgroups in populations based on response patterns.

  • Growth Mixture Modeling: Modeling individual change trajectories and identifying distinct developmental subgroups.

 
Quasi-Experimental Methods

  • Fixed Effects Models: Controlling for time(or subject)-invariant confounding factors.

  • Propensity Score Matching (PSM): Creating comparable groups in observational studies.

  • Regression Discontinuity Design (RDD): Estimating causal effects around a cutoff or threshold.

  • Difference-in-Differences (DiD): Comparing changes over time between treatment and control groups.

 
Psychometric Analysis

  • Item and Test-Level Analysis: 

    • Item difficulty, discrimination, guessing

    •  Test dimensionality (EFA, CFA)

  • Reliability Estimation:

    • Internal consistency (Cronbach’s alpha, McDonald’s omega)

    • Test-retest and inter-rater reliability (ICC, Kappa)

  • DIF and Measurement Invariance: Assessing item bias and scale equivalence across groups.​

  • Rating Data Analysis:

    • Many-Facet Rasch Models (MFRM)

    • Rater bias, rater consistency, multilevel rater modeling

 
Scale Development and Validation

  • Construct, content, and criterion validity

  • Response format evaluation

  • Test Equating and Linking (when applicable)

  • Vertical scaling, form linking

 

​Data Reporting & Visualization

  • Visual Analytics: Using R (ggplot2), Python (matplotlib, searborn) and other tools for interactive dashboards and publication-quality graphics.

  • Reporting: Writing clear, structured analytical reports for academic, policy, or business audiences.

bottom of page