1. Basic Introduction to STATA.

2. STATA Installation.

3. Creating Directory.

4. The participant should be able to understand how to open data in STATA format as well as to import data from foreign format and to save the data in the working directory.

5. The user should be able to learn to rename variables, label variables, label categories (values) in a categorical variable.

6. categorize/split a continuous variable and convert variable types

7. handle missing values/Imputation

8. handle outliers (continuous variables)

9. handle inconsistencies (categorical variables)

10. The participant will learn to print conditional tables/filtering, sort data, append.

11. The participant will taken through data sorting techniques in STATA

12. The participant will learn appending techniques and will be required to append various datasets.

13. Merge and reshape datasets

14. Concatenate and order (reposition) variables

15. The user will be taught to declare string date variables as to be of type date, among other type conversions

The learner will be taken through STATA’s powerful commands for calculation of measures of central tendency (mean, mode and median) and their confidence intervals; measures of dispersion (variance, standard deviation, interquartile range, range, coefficient of variation); skewness and kurtosis, proportions and frequencies and interpretations of the same.

The learner will be introduced to parametric and non-parametric methods of data analysis and the concepts underlying each. This will be accompanied by a rigorous hands-on insight into the various forms of regressions (linear, logistic, and probit) and their related concepts including model goodness of fit, R square, marginal effects and sensitivity and specificity, odds ratios for the case of binary logistic regression; correlations (Pearson’s r, Spearman’s rho, Kendall’s tau, Cramer’s v and phi),, tests of associations (Chi-square, Fisher’s exact, McNemar); and tests of hypothesis (ANOVA and its post hoc tests, t-tests, Kruskal-Wallis, Mann-Whitney U, and Cochrane’s Q)

The participants will learn to analyze longitudinal data using survival analysis approaches that include non-parametric (Kaplan-Meier, Nelson-Aalen); semi-parametric (cox-proportional hazards) and its assumptions; parametric (lognormal, exponential, Weibull, gaussian) and interpretations of Hazard ratios and risk ratios obtained from generalized estimating equations (GEE).

The participant will be able to visualize – continuous variables in histograms, box plots, scatter plots, density plots and line plots; categorical variables in the form of bar graphs and pie-charts; sensitivity and specificity in the form of Receiver Operating Characteristic (ROC) curves.