Nicholas M. Michalak

Data Scientist | Ph.D. Social Psychology

Insight Data Science

Department of Psychology, University of Michigan


I'm a Data Science Fellow at Insight Data Science and a Social Psychologist working with Josh Ackerman at the University of Michigan. More broadly, I have 10 years of experience conducting research in the social sciences with a focus on motivation and social cognition. I'm skilled in statistical modeling, machine learning, and experimental design. I'm looking to my leverage research and analytical skills to help businesses solve problems (my resume).

As a Data Science Fellow, I spent 7 (intense) weeks honing my skills in computer science fundamentals, applied statistical modeling, and machine learning. During four of those weeks, I developed a Flask web application—Next Escape (nextescape.me)—that simplifies web searches for users looking for an ideal escape room or escape rooms similar to ones they’ve played and enjoyed before (GitHub | Slides).

As a psychology researcher, I use advanced methods and statistics to study how both modern and evolutionarily-relevant threats affect how people perceive themselves and others. For example, in my current work, I use the reverse correlation image classification task to estimate mental representations of infected persons. I’m also conducting a Cross-Temporal Meta-Analysis to test whether stereotype threat effects have dissapated over time, depending on negatively stereotyped group (e.g., Women, Black Americans).

I’m asking three main questions right now: (1) How do people mentally represent threatening persons, (2) How do people use emotional expressions in trait judgements, and (3) What are the effects of negative stereotypes changing over time?


  • Person Perception
  • Nonverbal
  • Threat
  • Evolution


  • Ph.D. in Social Psychology, 2020

    University of Michigan

  • M.S. in Social Psychology, 2017

    University of Michigan

  • B.S. in Neuroscience, 2012

    University of St. Thomas (MN)


Experimental Design



Machine Learning





Recent Publications

Sounds of sickness: Can people identify infectious disease using sounds of coughs and sneezes?

Cough, cough. Is that person sick, or do they just have a throat tickle? A growing body of research suggests pathogen threats shape key …

A multi-method approach to measuring mental representations of threatening others

How do people mentally represent distinct interpersonal threats? Across human history, interpersonal threats such as infectious disease …

Has Stereotype Threat Dissipated Over Time? A Cross-Temporal Meta-Analysis

Stereotype threat – the social psychological threat that arises when one is in a situation or doing something for which a negative …

Average associations between sexual desire, testosterone, and stress in women and men over time

Sexual desire and testosterone are widely assumed to be directly and positively linked to each other despite the lack of supporting …


Next Escape: Find your next escape room

Next Escape nextescape.me recommends escape rooms based on one of two search options: (1) Users can enter their favorite escape room, …

SPSS for Research

OSF page storing materials used for Undergraduate Research Opportuntiies Program (UROP) workshops conducted at the University of …

R Programming for Psychology Research

OSF page storing materials used for workshops conducted at the University of Michigan

2020 Democratic Presidential Primary Polling Averages

R Shiny Application and GitHub repository for 2020 Democratic Presidential Primary Polling Averages

Blog Posts

Learning Python as an R user

Logistic Regression in R

Introduction In this post, I’ll introduce the logistic regression model in a semi-formal, fancy way. Then, I’ll generate data from some …

Presidential primary candidate name recognition matters

Key takeaway FiveThirtyEight claims that early national primary polls can become more useful for predicting party nomination success if …

Testing Conditional Indirect Effects/Mediation in R

This post builds on a previous post on Testing Indirect Effects/Mediation in R. What is mediation? There are many ways to define …

Using Principal Components or Common Factor Analysis in Social Psychology

Multidimensional Scaling, the precursor to Principal Components Analysis, Common Factor Analysis, and related techniques …