Home  /  News and events  /  Upcoming conferences  /  JSM 2024

JSM 2024
Portland, OR | 3–8 August 2024

StataCorp will be exhibiting and hiring at the 2024 Joint Statistical Meetings. We're also hosting two computer technology workshops. Attending from StataCorp: Yulia Marchenko, Vice President, Statistics and Data Science; Aramayis Dallakyan, Senior Statistician and Software Developer; Meghan Cain, Assistant Director, Educational Services; and Yaojin Sun, Senior Statistician and Software Developer. For more information about the meeting, visit the JSM 2024 page.

Try Stata for free by requesting a short-term evaluation license. To be notified of future software releases, free webinars, classroom and web-based training courses, and more, sign up for email alerts.

Title: Causal mediation analysis using Stata
Presenter: Aramayis Dallakyan, Senior Statistician and Software Developer, StataCorp
Date: Wednesday, 7 August 2024
Time: 1:00–2:45 p.m.
Location: Room B113 of the Oregon Convention Center
Description: Causal mediation analysis (CMA) aims to explore and determine the mechanisms through which a treatment influences an outcome via a mediator. The objective of this workshop is to provide a practical guide, facilitating an understanding of CMA using Stata. We will begin by introducing the fundamental steps of causal analysis and applying them to CMA. We will highlight the differences between causal and traditional mediation analysis. The workshop will also delve into various types of direct and indirect effects. Examples demonstrating how to perform CMA within Stata using different types of outcomes and mediators (continuous, binary, and count) will be provided. No prior knowledge of Stata is required, although a basic understanding of causal inference will be beneficial.
Title: Bayesian model averaging using Stata
Presenter: Yulia Marchenko, Vice President, Statistics and Data Science, StataCorp
Date: Wednesday, 7 August 2024
Time: 3:30–4:45 p.m.
Location: Room B113 of the Oregon Convention Center
Description: Model uncertainty accompanies many data analyses. Bayesian model averaging (BMA) helps address this uncertainty. For instance, in the regression context, we may want to know which predictors are important given the observed data, which models are more plausible, or how predictors relate to each other across different models. BMA can answer these and more questions. BMA uses the Bayes theorem to aggregate the results across multiple candidate models to account for model uncertainty during inference and prediction in a principled and universal way. In this workshop, I will describe the basics of BMA and demonstrate it with Stata's bma suite. I will also show how BMA can become a useful tool for your regression analysis, Bayesian or not! No prior knowledge is required, but familiarity with Bayesian analysis will prove useful.

Presenter

Aramayis Dallakyan portrait

Aramayis Dallakyan is a Senior Statistician and Software Developer at StataCorp LLC. His research interests lie at the intersection of high-dimensional time series, causal discovery, and statistical/machine learning. Aramayis has published articles in renowned journals, including the Journal of Graphical and Computational Statistics, the Journal of Computational Statistics and Data Analysis, and the Stata Journal. Prior to joining StataCorp, he earned a PhD in statistics from Texas A&M University.

Yulia Marchenko portrait

Yulia Marchenko is Vice President, Statistics and Data Science at StataCorp. Yulia has been with Stata for almost 20 years and has more than 25 years of software development experience. Her primary responsibility is to oversee Stata's scientific software development. Her areas of interest include Bayesian analysis, multiple imputation, meta-analysis, multilevel modeling, survival analysis, power analysis, causal analysis, and other areas of statistics, biostatistics, and econometrics. Yulia has a PhD in statistics from Texas A&M University.

PDF flyers

Browse the Stata flyers below.

Introduction to Stata



Stata overview
Letter   A4

Why Stata
Letter   A4

Stata 18 highlights
Letter   A4

StataNow
Letter   A4  

Stata/MP
Letter   A4  

Features



Bayesian analysis
Letter   A4

Bayesian model averaging
Letter   A4

Causal inference/Treatment effects
Letter   A4

Causal mediation analysis
Letter   A4

Choice models
Letter   A4

Clinical trials
Letter   A4

Customizable tables
Letter   A4

Data frames
Letter   A4

Difference in differences
Letter   A4

Extended regression models (ERMs)
Letter   A4

Finite mixture models (FMMs)
Letter   A4

Group sequential designs
Letter   A4

Interval-censored Cox model
Letter   A4

Item response theory (IRT)
Letter   A4

Lasso: Prediction and inference
Letter   A4

Latent class analysis (LCA)
Letter   A4

Maximum likelihood estimation
Letter   A4

Meta-analysis
Letter   A4

Multilevel mixed-effects models
Letter   A4

Multiple imputation
Letter   A4

Nonparametric regression
Letter   A4

Panel data
Letter   A4

Power, precision, and sample-size analysis
Letter   A4

PyStata
Letter   A4

Reproducible and automated reporting
Letter   A4

Reproducibility and backward compatibility
Letter   A4

Spatial autoregressive (SAR) models
Letter   A4

Structural equation modeling (SEM)
Letter   A4

Survey data
Letter   A4

Survival analysis
Letter   A4

Time series
Letter   A4

View all Stata features.

Resources



Programming with Stata
Letter   A4

Teaching with Stata
Letter   A4

Tech support
Letter   A4

Stata Press



Author Support Program
Letter   A4

Become a Stata Press® author
Letter   A4

Visit stata-press.com for more information.

Stata Journal



Publish in the Stata Journal
Letter   A4

The Stata Journal
Letter   A4

Visit stata-journal.com for more information.

Supplementary materials