Publications and Preprints
- D. Ham, L. Janson, K. Imai. (2022). Using Machine Learning to Test Hypothesis in Conjoint Analysis, Political Analysis (forthcoming). [PDF] [arXiv]
- D. Ham, J. Qie. (2022). Hypothesis Testing in Sequentially Sampled Data: ART to Maximize Power Beyond iid Sampling, submitted, TEST (forthcoming). [PDF][arXiv]
- D. Ham, L. Miratrix. (2022). Benefits and costs of matching prior to a Difference in Difference analysis when parallel trends does not hold, submitted. [PDF][arXiv]
- D. Ham, I. Bojinov, M. Lindon, M. Tingley. (2022). Design-Based Confidence Sequence for Anytime-Valid Inference. [PDF][arXiv]
- M. Lindon, D. Ham, M. Tingley, I. Bojinov. (2022). Anytime-Valid F-Tests for Faster Sequential Experimentation Through Covariate Adjustment. [PDF][arXiv]
- D. Ham, I. Bojinov, M. Lindon, M. Tingley. (2023). Design-Based Inference for Multi-arm Bandits. [PDF][arXiv]
Invited Talks and Conferences
- D. Ham, L. Miratrix. Benefits and costs of matching prior to a Difference in Difference analysis when parallel trends does not hold. American Causal Inference Conference (2022, UC Berkeley).
- D. Ham, L. Janson, K. Imai. Using Machine Learning to Test Hypothesis in Conjoint Analysis. Society for Political Methodology (2022, University of Washington Saint Louis)
- D. Ham, L. Janson, K. Imai. Using Machine Learning to Test Hypothesis in Conjoint Analysis. American Political Science Association (2022, Montreal)
- D. Ham, I. Bojinov, M. Lindon, M. Tingley. (2022). Design-Based Confidence Sequence for Anytime-Valid Inference. Conference on Digital Experimentation (2022, MIT)
- D. Ham, I. Bojinov, M. Lindon, M. Tingley. (2023). Design-Based Confidence Sequence for Anytime-Valid Inference. American Causal Inference Conference (2023, University of Texas, Austin).