# Learn to analyse with

STATA is a software package used for statistical data analysis, data management, and graphical representation. It is extensively used by researchers and professionals in the field of social sciences economics, epidemiology, biostatics, and finance.

## Learning outcomes of this STATA module

- The distinction between Regular series, Time Series, Univariate, Multivariate, and Panel Data.
- Establishment of important properties of data like moving average, autoregressive average, first differencing and lags.
- The distinction between Stationary and Non-Stationary Time Series.
- Testing the time series on the basis of Stationarity, Heteroskedasticity, Autocorrelation, and Stability.
- Proposing Multivariate analysis on more than one-time series.
- The distinction between Pooled OLS regression and Panel Data Set regression.
- The choice between Fixed Effect and Random Effect Models.
- Panel level Heteroskedasticity and Autocorrelation.

## Getting started with STATA

The articles in this section discuss different types of data that STATA handles. Furthermore, it discusses the management of dependent and independent variables and how to import data from other formats.

## Basic statistical tools

This section comprises of articles on basic statistical tools of correlation and regression. Two types of regression namely linear regression and non-linear regression are discussed. Furthermore, how they are analyzed in STATA and how the results can be interpreted.

- How to do the correlation analysis in STATA?
- Procedure and interpretation of linear regression analysis using STATA
- Non linear regression analysis in STATA and its interpretation
- Applying regression on secondary data using SPSS
- Understanding the correlation and regression analysis values
- Application of multivariate regression analysis
- How to work with a moderating variable in the regression test with SPSS?
- How to work with a mediating variable in a regression analysis?
- How to process the primary dataset for a regression analysis?
- What is the relevance of significant results in regression analysis?

## Time series analysis

This module section discusses the analysis of continuous data sets that represent time dimensions. Furthermore, it also covers stationarity, normality, and stability in data. This section is designed in a way to introduce the Univariate Time Series and Multivariate Time series. It explores the structural economic model building and critical appraisal of models based on statistical testing methods.

- Introduction to the Autoregressive Integrated Moving Average (ARIMA) model
- The problem of non-stationarity in time series analysis in STATA
- Handling unit root problem from Dickey-Fuller test in time series analysis
- How to build the univariate ARIMA model for time series in STATA?
- ARIMA modeling for time series analysis in STATA
- How to predict and forecast using ARIMA in STATA?
- How to test normality in STATA?
- How to perform Heteroscedasticity test in STATA for time series data?
- How to test time series autocorrelation in STATA?
- How to perform point forecasting in STATA?
- How to perform regression analysis using VAR in STATA?
- Lag selection and cointegration test in VAR with two variables
- How to perform Johansen cointegration test in VAR with three variables?
- How to perform Johansen cointegration test?
- How to perform Granger causality test in STATA?
- VECM in STATA for two cointegrating equations
- How to test and diagnose VECM in STATA?
- How to identify ARCH effect for time series analysis in STATA?
- ARCH model for time series analysis in STATA
- Testing the accuracy of the stock market forecasting model

## Panel data analysis

This section is designed in a way to introduce a panel data series and its estimation. Here the articles focus on pooled OLS regression, fixed effect models and random effect models. The issue of choice between fixed effect and random effect and panel level heteroskedasticity and autocorrelation are also covered.