Biography

I am currently a Research Scientist on the Core Data Science team at Facebook, where I work on problems in computational social science.

Prior to Facebook, I was Lead Data Scientist at Thresher and also Assistant Professor of Computational Science at Minerva Schools at KGI. I am also a Visiting Fellow at the Harvard Institute for Quantitative Social Science. I alternate between the Bay Area and the Greater Los Angeles area.

My academic background is in political science and statistics, where I specialized in causal inference with experimental and observational data. However, I have since branched out and have worked on problems involving machine learning and natural language processing. I am equally fluent in both R and Python and have an affinity for good data visualization. One of my passions is teaching statistical methods, especially to non-technical audiences.

If you have an opportunity that you feel may suit my expertise, please feel free to reach out.

• Computer-Assisted Keyword and Document Discovery from Unstructured Text

  Details PDF

• Voter Persuasion in Compulsory Electorates: Evidence from a Field Experiment in Australia

  Details PDF

• Estimating Individual Causal Effects

  Details

Over the years, I’ve created a some teaching and learning materials for myself and my students that I find to be helpful. If you find them helpful or would like to use them somewhere, please do let me know!

• Short tutorials on using R and LaTeX for beginners:

  • Learning LaTeX
  • Learning R
    
    

• Slides of various statistical concepts:

  • Probability Theory
  • A Brief Review of Probability
  • Maximum Likelihood
  • Delta Method and Generalized Linear Models
  • Causal Inference
  • Survival Models
    
    

• Slides on Bayesian statistics:

  • Bayesian Statistics in One Hour
  • Introduction to Bayesian Statistics
  • Conjugate Models
  • Non-Conjugate Models and Grid Approximations
  • Summarizing the Posterior
  • Sampling Methods
  • MCMC Methods: Gibbs Sampling and the Metropolis-Hastings Algorithm
  • Convergence Diagnostics
  • Model Checking
    
    

• Various materials from a Bayesian course I taught:

  • Syllabus
  • Important Formulas
  • Problem Sets:
    • Week 1 Problems and Solutions
    • Week 2 Problems and Solutions
    • Week 3 Problems and Solutions
    • Week 4 Problems and Solutions
    • Week 5 Problems and Solutions
    • Week 6 Problems and Solutions
    • Week 7 Problems and Solutions
      
  • R Code:
    • Binomial Example Code
    • Multi-Parameter Example Code
    • Sampling Code
    • Metropolis-Hastings Example Code

• pkphlam@gmail.com
• Located both in the Bay Area and the Greater Los Angeles area