Nathaniel Haines

Nathaniel Haines

Data Scientist & Computational Psychologist, PhD

Ledger Investing

Biography

I am a data scientist and computational psychologist with 6+ years of experience developing bespoke probabilistic models of risky decision-making, counterfactual reasoning, reinforcement learning, and latent variable measurement. I use principles from machine learning, decision theory, causal inference, and psychometrics throughout my work. Altogether, this framework allows for me to extract reliable and meaningful signals from noisy observational data, enabling me to make the right data-driven decisions given imperfect or incomplete information.

Download my CV.

Interests
  • Bayesian Statistics <3
  • Risk Modeling
  • Computational Reproducibility
  • Uncertainty Quantification and Visualization
  • Clinical and Mathematical Psychology
Education

  • Ph.D. in Psychology, 2021

    The Ohio State University

  • M.A. in Psychology, 2017

    The Ohio State University

  • B.A. in Psychology, 2015

    The Ohio State University

Skills

Python
R
Bayesian Statistics
Computational Modeling
ML-Ops
Psychology

Experience

 
 
 
 
 
Ledger Investing
Senior Data Scientist
Ledger Investing
Oct 2022 – Present Remote / Ohio

Responsibilities include:

  • Develop Bayesian forecasting, pricing, and cashflow models
  • Research novel methods for robust Bayesian model comparison
  • Build semi-automated reports for executive decision-making
  • Design internal software to improve model development and deployment
 
 
 
 
 
Aivo Health
Data Scientist
Aivo Health
Sep 2021 – Oct 2022 Remote / Ohio

Responsibilities include:

  • Developed theoretical models of chronic pain
  • Built real-time data pipelines for in-app experience
  • Deployed models for real-time inference
  • Designed research studies and writing papers
 
 
 
 
 
The Ohio State University
Graduate Student Researcher
The Ohio State University
Aug 2016 – Jul 2021 Ohio

During my PhD., I:

  • Received the Presidential Fellowship for my dissertation research
  • Was instructor of record for 4 semesters of Abnormal Psychology
  • Trained in and conducted 400+ hours of cognitive behavioral therapy, motivational interviewing, acceptance and commitment therapy, and mindfulness based relapse prevention
  • Published my research in journals including Computational Psychiatry, Cognitive Science, Clinical Psychological Science, and Drug and Alcohol Dependence

Recent Posts

Data Science and Computational Reproducibility: Using asdf, poetry, and renv to make your local Python and R environments easy(er) to manage
The Problem In a previous blog post, we discussed the benefits of using renv, Docker, and GitHub Actions to streamline computational reproducibility workflows in R. However, this workflow is a bit overkill at times.
Last updated on Sep 22, 2022 13 min read
Automating Computational Reproducibility in R using renv, Docker, and GitHub Actions
The Problem Have you ever wanted to run someone else’s R code (or your own—from a distant past), but upon downloading it, you realized that it relied on versions of either R or R libraries that are dramatically different from those on your own computer?
Jan 24, 2022 20 min read Computational Reproducibility, R, GitHub, Docker
A Series on Building Formal Models of Classic Psychological Effects: Part 1, the Dunning-Kruger Effect
Introduction The Dunning-Kruger effect is perhaps one of the most well-known effects in all of social psychology, defined as the phenomenon wherein people with low “objective” skill tend to over-estimate their objective skill, whereas people with high objective skill tend to under-estimate their skill.
Jan 10, 2021 44 min read Statistical Modeling, Measurement Error, Formal Models
On Curbing Your Measurement Error: From Classical Corrections to Generative Models
Introduction In this post, we will explore how measurement error arising from imprecise parameter estimation can be corrected for. Specifically, we will explore the case where our goal is to estimate the correlation between a self-report and behavioral measure–a common situation throughout the social and behavioral sciences.
Jun 13, 2020 40 min read Statistical Modeling, Measurement Error
Thinking generatively: Why do we use atheoretical statistical models to test substantive psychological theories?
The Reliability Paradox Defining Reliability In 2017, Hedge, Powell, and Sumner (2017) conducted a study to determine the reliability of a variety of of behavioral tasks. Reliability has many different meanings throughout the psychological literature, but what Hedge et al.
Sep 5, 2019 32 min read Statistical Modeling, Measurement
See all posts

Recent & Upcoming Talks

The Role of Reward and Punishment Learning in Externalizing Adolescents: A Joint Generative Model of Traits and Behavior
This presentation is part of MathPsych/ICCM 2021. See more via http://mathpsych.org/conferences/2021/
Jun 17, 2021 12:00 AM Virtual
The Role of Reward and Punishment Learning in Externalizing Adolescents: A Joint Generative Model of Traits and Behavior
An Introduction to Bayesian Data Analysis
This is just a fun tutorial talk I presented for the Cognitive Proseminar at The Ohio State University. Hope you enjoy!
Apr 5, 2021 12:00 AM Virtual
An Introduction to Bayesian Data Analysis
Generative Models Can Advance the Social, Behavioral, and Brain Sciences
This talk was presented to the Neuroscience and Mental Health Group at the Institute of Cognitive Neuroscience, University College London, on October 14th, 2020. The talk is based on my recent paper on the role of generative models for social, behavioral, and brain sciences, linked in the video.
Oct 14, 2020 12:00 AM Virtual
Generative Models Can Advance the Social, Behavioral, and Brain Sciences
Using Decision Theory to Model Anxiety-Impulsivity Interactions and Impulsive Behavior
This presentation is part of MathPsych/ICCM 2020. See more via http://mathpsych.org/conferences/2020/
Jul 20, 2020 12:00 AM Virtual
Using Decision Theory to Model Anxiety-Impulsivity Interactions and Impulsive Behavior

Featured Publications

April 2020 Clin Psych Sci
Anxiety Modulates Preference for Immediate Rewards among Trait-Impulsive Individuals: A Hierarchical Bayesian Analysis

We used hierarchical Bayesian analysis to identify determine how impulsivity and anxiety jointly determine impulsive behavior in the context of a delay discounting task.
October 2018 Cog Sci
The Outcome‐Representation Learning Model: A Novel Reinforcement Learning Model of the Iowa Gambling Task

We developed a novel computational model for the IGT and used it to investigate differences in learning mechanisms between groups with versus without substance use disorders.
March 2017 CPSY
Revealing Neurocomputational Mechanisms of Reinforcement Learning and Decision-Making With the hBayesDM Package

We developed an open-source R/Python package for fitting reinforcement learning and decision-making models using hierarchical Bayesian analysis.

Recent Publications

Quickly discover relevant content by filtering publications.
Nathaniel Haines (2021). Integrating Trait and Neurocognitive Mechanisms of Externalizing Psychopathology: A Joint Modeling Framework for Measuring Impulsive Behavior. Dissertation.

PDF Video

Woo-Young Ahn, Hairong Gu, Yitong Shen, Nathaniel Haines, Hunter Hahn, Julie Teater, Jay Myung, Mark Pitt (2020). Rapid, precise, and reliable measurement of delay discounting using a Bayesian learning algorithm. Sci Rep.

PDF Code DOI

Nathaniel Haines, Theodore Beauchaine (2020). Moving beyond Ordinary Factor Analysis in Studies of Personality and Personality Disorder: A Computational Modeling Perspective. Psychopathology.

PDF DOI

Ricardo Romeu, Nathaniel Haines, W.-Y. Ahn, J. Busemeyer, J. Vassileva (2019). A computational model of the Cambridge gambling task with applications to substance use disorders. DAD.

PDF Code DOI

Hunter Hahn, Samuel Kalnitsky, Nathaniel Haines, Sneha Thamotharan, Theodore Beauchaine (2019). Delay Discounting of Protected Sex: Relationship Type and Sexual Orientation Influence Sexual Risk Behavior. Arch Sex Behav.

PDF DOI

Theodore Beauchaine, Nathaniel Haines (2019). Functionalist and Constructionist Perspectives on Emo­ tion Dysregulation. The Oxford Handbook of Emotion Dysregulation.

PDF DOI

Nathaniel Haines, Ziv Bell, Sheila Crowell, Hunter Hahn, Dana Kamara, Heather McDonough-Caplan, Tiffany Shader, Theodore Beauchaine (2019). Using automated computer vision and machine learning to code facial expressions of affect and arousal: Implications for emotion dysregulation research. Dev. Psychopathology..

PDF DOI

Nathaniel Haines, Matthew Southward, Jennifer Cheavens, Theodore Beauchaine, Woo-Young Ahn (2019). Using computer-vision and machine learning to automate facial coding of positive and negative affect intensity. PLOS ONE.

PDF Code Dataset Poster DOI

Woo-Young Ahn, Paul Hendricks, Nathaniel Haines (2017). Easyml: Easily Build And Evaluate Machine Learning Models. BioRxiv.

PDF Code DOI

Andrew Rogers, Ilana Seager, Nathaniel Haines, Hunter Hahn, Amelia Aldeo, Woo-Young Ahn (2017). The Indirect Effect of Emotion Regulation on Minority Stress and Problematic Substance Use in Lesbian, Gay, and Bisexual Individuals. Frontiers Psych.

PDF DOI

Popular Topics

Bayesian Statistics Docker Learning Machine Learning Modeling Programming R Regularization Source Themes

Contact