Kaspar Wüthrich
Biographic Data
| ID | 8879205 |
|---|---|
| NAME | Kaspar Wüthrich |
| GIVEN NAMES | Kaspar |
| FAMILY NAME | Wüthrich |
| SIGNATURE | WÜTHRICH K |
| AFFILIATIONS | University of Michigan |
| ORCID | 0000-0001-9196-4582 |
| VERIFIED | Yes |
| TOTAL WORKS | 5 |
| TOTAL CITATIONS | 0 |
| WORKS AS AUTHOR | 5 |
| WORKS AS EDITOR | 0 |
| FIRST PUBLICATION YEAR | 2020 |
| LATEST PUBLICATION YEAR | 2025 |
| H-INDEX | 0 |
The Power of Tests for Detecting p -Hacking
A flourishing empirical literature investigates the prevalence of p-hacking based on the distribution of p-values across studies. Interpreting results in this literature requires a careful understanding of the power of methods for detecting p-hacking. We theoretically study the implications of likely forms of p-hacking on the distribution of p-values to understand the power of tests for detecting it. Power can be low and depends crucially on the …
Factorial Designs, Model Selection, and (Incorrect) Inference in Randomized Experiments
Factorial designs are widely used to study multiple treatments in one experiment. Although t-tests using a fully saturated “long” model provide valid inferences, “short” model t-tests (that ignore interactions) yield higher power if interactions are zero, but incorrect inferences otherwise. Of 27 factorial experiments published in top-five journals (2007–2017), nineteen use the short model. After including interactions, more than half of their re…
Discussion of “Imputation of Counterfactual Outcomes when the Errors are Predictable” by Sílvia Gonçalves and Serena Ng
I argue that the PUP approach proposed by Goncalves and Ng is not only useful for reducing the mean squared error of treatment effect estimators but can also be motivated from an identification perspective when units select into treatment based on past shocks
Omitted Variable Bias of Lasso-Based Inference Methods
We study the finite sample behavior of Lasso-based inference methods such as post–double Lasso and debiased Lasso. We show that these methods can exhibit substantial omitted variable biases (OVBs) due to Lasso's not selecting relevant controls. This phenomenon can occur even when the coefficients are sparse and the sample size is large and larger than the number of controls. Therefore, relying on the existing asymptotic inference theory can be pr…
A Comparison of Two Quantile Models With Endogeneity
This article studies the relationship between the two most-used quantile models with endogeneity: the instrumental variable quantile regression (IVQR) model (Chernozhukov and Hansen 2005 Chernozhukov, V., and Hansen, C. (2005), “An IV Model of Quantile Treatment Effects,” Econometrica, 73, 245–261.[Crossref], [Web of Science ®] , [Google Scholar]) and the local quantile treatment effects (LQTE) model (Abadie, Angrist, and Imbens 2002 Abadie, A., …
No prominent works on this page.
A Comparison of Two Quantile Models With Endogeneity
This article studies the relationship between the two most-used quantile models with endogeneity: the instrumental variable quantile regression (IVQR) model (Chernozhukov and Hansen 2005 Chernozhukov, V., and Hansen, C. (2005), “An IV Model of Quantile Treatment Effects,” Econometrica, 73, 245–261.[Crossref], [Web of Science ®] , [Google Scholar]) and the local quantile treatment effects (LQTE) model (Abadie, Angrist, and Imbens 2002 Abadie, A., …
Omitted Variable Bias of Lasso-Based Inference Methods
We study the finite sample behavior of Lasso-based inference methods such as post–double Lasso and debiased Lasso. We show that these methods can exhibit substantial omitted variable biases (OVBs) due to Lasso's not selecting relevant controls. This phenomenon can occur even when the coefficients are sparse and the sample size is large and larger than the number of controls. Therefore, relying on the existing asymptotic inference theory can be pr…
Discussion of “Imputation of Counterfactual Outcomes when the Errors are Predictable” by Sílvia Gonçalves and Serena Ng
I argue that the PUP approach proposed by Goncalves and Ng is not only useful for reducing the mean squared error of treatment effect estimators but can also be motivated from an identification perspective when units select into treatment based on past shocks
The Power of Tests for Detecting p -Hacking
A flourishing empirical literature investigates the prevalence of p-hacking based on the distribution of p-values across studies. Interpreting results in this literature requires a careful understanding of the power of methods for detecting p-hacking. We theoretically study the implications of likely forms of p-hacking on the distribution of p-values to understand the power of tests for detecting it. Power can be low and depends crucially on the …
Factorial Designs, Model Selection, and (Incorrect) Inference in Randomized Experiments
Factorial designs are widely used to study multiple treatments in one experiment. Although t-tests using a fully saturated “long” model provide valid inferences, “short” model t-tests (that ignore interactions) yield higher power if interactions are zero, but incorrect inferences otherwise. Of 27 factorial experiments published in top-five journals (2007–2017), nineteen use the short model. After including interactions, more than half of their re…
Computer Science (4 works) · Mathematics (4 works) · Statistics (4 works) · Artificial Intelligence (3 works) · Econometrics (3 works) · Statistical Methods and Inference (3 works) · Advanced Causal Inference Techniques (2 works) · Artificial Intelligence (2 works) · Econometric model (2 works) · Inference (2 works)