Getting started with Stata

Stata operates with dta files to store data. In this session, we will explore working with dta files. You will learn how to open files, browse the datasets, edit data, and save files. In addition, I will show you a few useful data sources.

We explore common data structures and how to reshape data from data sources.

We discuss different methods to import csv files, which are very common.

This session demonstrates the import of Excel files into Stata.

We use a Python script, which is available for download, to address compatibility issues when using older versions of Stata. The script converts new dta files into dta files that can be read by older versions of Stata.

Merging different datasets is very common in Data Analysis. We discuss methods that can be used to accomplish these tasks.

Adding observations to datasets can be achieved using the append command. We discuss the issues in detail.

We introduce Stata Do-files, which can be used to replicate your data analysis.

Loops are essential in any programming language. This session explores the two types of loops in Stata.

The expand command looks strange in the beginning - but you will learn how to use it to handle data formats effectively.

Labels are essential to enable others to understand your datasets and variables.

Missing values can affect your data analysis. In this session, we discuss methods to deal with missing values.

This session demonstrates the use of summary statistics, which are essential in empirical research.

We discuss outlier detection and methods to address extreme values such as winsorisation.

It is common to transform variables using functions such as the ln function. We discuss the implications of transformations.

It is very useful to export Stata outputs directly to Excel (csv) or Word. This session will help you to make your work a lot more efficient.

This session outlines the theory of OLS in a very applied manner.

This session demonstrates the implementation of regression models in Stata. We focus on the interpretation of regression outputs.

This session discusses the code to export regression tables to Excel, Word or LaTeX.

We discuss multicollinearity, including tests (e.g., variance inflation factors) and methods that can mitigate the problem.

This session covers tests and robust estimation procedures.

We introduce the Ramsey RESET test, which detects non-linear relationships and omitted variables.

Endogeneity is a common problem in many applications. We review a test to detect endogeneity and discuss ways to address issues.

This session highlights the benefits of panel data and estimation procedures including panel OLS, fixed and random effects.

This session explores the Hausman test, which can be used to justify fixed or random effects models.

This session focuses on testing for serial correlation. We highlight robust estimation using the Newey-West method.

Interaction effects can be used in the context of panel data to test for differences between groups and treatment effects.

We discuss binary dependent variables and explain the need for an alternative estimation method. Logit and probit models are introduced.

This session covers model specification using a general-to-specific approach.

This session discusses the stability of estimated coefficients. Our ability to forecast relies on parameter stability.

This session explains your learning journey after completing this course. The next steps in your learning are shown.