Software for Econometrics and Big Data
The aim of this course is to provide students with programming skills that can be used to perform data management operations and several types of statistical and econometric analysis in an efficient and reproducible way. Students will be taught the fundamentals of programming in Stata. The module will prepare students for PhD research or work as an econometrician consultant in public and private organisations.
Prerequisites
Please note to take this course you must first have completed Foundations of Econometrics.
Delivery
This module consists of 2-hour lectures per day for 5 days, plus a 1-hour tutorial per day. There will be optional clinics on the last day of the course.
Study Hours
Approximately 100 hours of study, of which 15 are contact hours and 85 are private study.
Software Used
Stata
Credits
10 CATS credits
Programme Faculty
Prof. Christopher Baum (Guest Lecturer)
Programme Faculty
Key Outcomes
- —Understand the principles of Stata programming
- —Write Stata do-files for automating the workflow
- —Write ADO-files to extend Stata by creating new commands
- —Understand the basics of Mata Programming Language
Desired Skills
- —Use automatic model selection to build econometric models
- —Use saturation estimation
- —Present, interpret and analyse the results of automatic model selection
- —Utilise effectively PcGive and the R gets package packages
Lecture Programme
- WK 01
Lecture 1: Programming: Some Fundamental Concepts
- ·Do and ado files in Stata
- ·Data types: Working with dates and time, time series operators, factor variables
- ·Debugging – the capture command
- ·Protecting your data with preserve and restore
- WK 02
Lecture 2: Guidelines for writing programs in Stata
- ·Basic guidelines for writing do-files
- ·Enhancing speed and efficiency
- ·How to seek help for Stata programming
- WK 03
Lecture 3: Programming Stata Do-Files I
- ·Transformation of string and numeric variables
- ·Recoding discrete and continuous variables
- ·Recoding missing variables
- ·Generate and egen functions
- ·Local and global macros
- ·Extended macro functions and list functions
- WK 04
Lecture 4: Programming Stata Do-Files II
- ·Scalars and matrices
- ·Temporary variables and tempnames
- ·Looping commands: forvalues and foreach
- ·By, statsby, rolling and other prefix commands
- ·Transforming data with reshape
- ·Combining datasets with append and merge
- WK 05
Lecture 5: Programming Concepts and Tools in Action I
- ·Tabulating and computing statistics across a set of variables and groups
- ·Computing durations and aggregating transactions data
- ·Summarising group characteristics over observations
- WK 06
Lecture 6: Programming Concepts and Tools in Action II
- ·Adding aggregate characteristics to micro observations
- ·Reusing results: return and ereturn commands
- ·Accessing estimation results and margins
- WK 07
Lecture 7: Automation - Do-File Programming I
- ·Storing results in matrices
- ·Stata's post and postfile commands
- WK 08
Lecture 8: Automation - Do-File Programming II
- ·Automating estimation output – the user-written commands estout and tabout, saveresults
- ·Automating graphical output
- WK 09
Lecture 9: ADO-File Programming I
- ·Structure of an ado-file
- ·Syntax and return statements
- ·Using program options
- ·Including a subset of observations
- ·Generalizing commands to handle multiple variables
- ·Rendering commands byable
- WK 10
Lecture 10: ADO-File Programming II
- ·Writing an e-class program
- ·Programs for egen, ml, nl
- ·Programs for gmm
- ·Guidelines for ado-file programming style
- WK 11
Lecture 11: Fundamentals of Mata programming
- ·Mata Fundamentals
- ·A simple Mata function
- ·Components of a Mata function
- ·Calling Mata functions
- ·Mata's st_interface functions
Assessment
Online coursework submission with the support of your module lecturer and tutor. All sessions are conducted live online at a scheduled time and recorded for review.