Avatar

Megha Joshi

Interests

  • Causal inference
  • Meta-analysis
  • Missing data
  • Machine learning
  • Robust variance-covariance matrices

Education

  • PhD in Quantitative Methods, 2021

    The University of Texas at Austin

  • BA in Art History and Psychology, 2014

    Bryn Mawr College

Recent Posts

What should I use to quantify heterogeneity in meta-analysis?

Meta-analysis Scientific researchers tend to produce literature on the same topic either to replicate or extend prior studies or due to …
May 17, 2021 5 min read R

What is a Confidence Interval?

library(tidyverse) library(knitr) Distributions There are three kinds of distributions: Population Distribution There are around 15 …
May 11, 2021 13 min read R

ERCOT Price Gouging

Welcome to the Deregulated State of Texas! During the crisis brought on by government failure and capitalism last week in Texas that …
Feb 23, 2021 2 min read R

Unemployment Claims COVID-19

In this post I am visualizing and analyzing the unprecedented increase in the number of unemployment claims filed in the US after the …
Jun 29, 2020 4 min read R

Propensity Score Analysis with Multiply Imputed Data

In this post, I walk through steps of running propensity score analysis when there is missingness in the covariate data. Particularly, …
Jun 23, 2020 11 min read R
See all posts

Software

wildmeta

Here is the website for the package. Typical methods to conduct meta-analysis—pooling effect sizes or analyzing moderating …

simhelpers

Here is the website for the package. Monte Carlo simulations are computer experiments designed to study the performance of statistical …

Research Assistants

Recent Publications

Quickly discover relevant content by filtering publications.

WORKING PAPER Cluster wild bootstrapping to handle dependent effect sizes in meta-analysis with a small number of studies

The most common and well-known meta-regression models work under the assumption that there is only one effect size estimate per study …
Preprint Code Supplementary materials R package

The performance of multivariate methods for two-group comparisons with small samples and incomplete data

In intervention studies having multiple outcomes, researchers often use a series of univari-ate tests (e.g., ANOVAs) to assess group …
DOI

Direct ties to a faculty mentor related to positive outcomes for undergraduate researchers

Mentored research is critical for integrating undergraduates into the scientific community. Undergraduate researchers experience a …
DOI

Popular Topics

bootstrap bootstrapping causal causal inference confidence intervals continuous treatment coronavirus COVID-19 ERCOT gganimate ggplot heterogeneity I squared leaflet lockdown maximum likelihood meta-analysis missing data package R

Contact