Asjad Naqvi, Vienna University of Economics and Business (WI)
Advanced Data Visualizations with Stata Part V: Hierarchical data
This presentation focuses on visualizing complex hierarchical relational datasets through a suite of new packages including sankey, alluvial, treemap, circlepack, circlebar, and sunburst.
Links
Watch presentation
|
Annalivia Polselli, University of Essex
Influence Analysis with Panel Data using Stata
The presence of anomalous observations in a data set can severely affect least squares estimates that are, by construction, sensitive to extreme cases. This presentation formalises statistical measures to quantify the degree of leverage and outlyingness of units in a panel data framework and outlines the two user-written commands used to conduct the proposed influence analysis.
Links
Watch presentation
|
Chuck Huber, StataCorp
Introduction to difference in differences in Stata 17
Stata 17 introduced two commands to fit difference-in-differences (DID) and difference-in-difference-in-differences (DDD) models. This talks briefly to introduce the concepts and jargon of DID and DDD models and then show how to fit the models by using the new commands.
Links
Watch presentation
|
Jeff Wooldridge, Michigan State University
Rolling Estimation Methods for Staggered Difference-in-Differences
This talk discusses relatively efficient regression, propensity score, and doubly robust estimation methods in settings with staggered policy interventions. The estimators and standard errors can be obtained using existing Stata commands.
Links
Watch presentation
|
Facilitated Panel Session
Stata Authors' tips
This panel discussion brought together Colin Cameron, Distinguished Professor of Economics at the University of California – Davis; Demetris Christodoulou, University of Sydney Business School and Irma Mooi-Reci, professor of sociology and social policy at the School of Social and Political Sciences (SSPS) at the University of Melbourne. In this facilitated panel session we heard from Colin, Demetris and Irma their inspiration to write text books on Stata and their learnings on Stata as they wrote their books. We also heard their top tip for using Stata.
Links - Irma Mooi-Reci, University of Melbourne
Links - Colin Cameron, University of California – Davis
Links - Demetris Christodoulou, University of Sydney
|
Laura Whiting, Survey Design and Analysis Services
Building connected dashboards using Stata
ashboards have become essential tools for business management to understand their performance, the issues they face and the risks just around the corner. In this presentation Laura shows how Stata can create a dashboard and make it accessible to people in a company / organisation using tools already available in Stata to extract data from an organisational database, then analyse the data in Stata, then make the analysed information available in an interactive dashboard.
Links
Watch presentation
|
Joe Hirschberg, University of Melbourne
This presentation presents a review of the style of scripts or code used for data analysis with Stata in applied economics research and provides recommendations for the creation of higher quality code.
Links
Watch presentation
|
Simon Turner, Cochrane Australia and Monash University
How plots helped solve the mystery of the interrupted time series aggregation bias.
Interrupted time series (ITS) designs are often used to evaluate the impact of public health interventions targeted at populations. This presentation argues when aggregating ITS observations over time, correction to the level change estimate may be required to avoid aggregation bias and that plots are an effective method for identifying, understanding, and providing potential solutions for unexpected results in numerical simulation studies.
Links
Watch presentation
|
Jan Kabatek, University of Melbourne's Melbourne Institute
Plot suite – fast graphing commands for very large datasets
This presentation showcases the functionality of the heavily-updated ‘plot suite’ of graphing commands. The suite excels in visualizing very large datasets, enabling users to produce a variety of highly-customizable plots in a fraction of time required by Stata's native graphing commands.
Links
Watch presentation
|
