Michal Kolesár
Biographic Data
| ID | 8879217 |
|---|---|
| NAME | Michal Kolesár |
| GIVEN NAMES | Michal |
| FAMILY NAME | Kolesár |
| SIGNATURE | KOLESÁR M |
| AFFILIATIONS | Princeton University |
| ORCID | 0000-0002-2482-7796 |
| VERIFIED | Yes |
| TOTAL WORKS | 7 |
| TOTAL CITATIONS | 0 |
| WORKS AS AUTHOR | 7 |
| WORKS AS EDITOR | 0 |
| FIRST PUBLICATION YEAR | 2015 |
| LATEST PUBLICATION YEAR | 2025 |
| H-INDEX | 0 |
Dynamic Causal Effects in a Nonlinear World
Applied macroeconomists frequently use impulse response estimators motivated by linear models. We study whether the estimands of such procedures have a causal interpretation when the data generating process is in fact nonlinear. We show that vector autoregressions and linear local projections onto observed shocks or proxies identify weighted averages of causal effects regardless of the extent of nonlinearities. By contrast, identification approac…
One instrument to rule them all
When can we ignore measurement error in the running variable
In many applications of regression discontinuity designs, the running variable used to assign treatment is only observed with error. We show that, provided the observed running variable (i) correctly classifies treatment assignment and (ii) affects the conditional means of potential outcomes smoothly, ignoring the measurement error nonetheless yields an estimate with a causal interpretation: the average treatment effect for units whose observed r…
Shift-Share Designs
We study inference in shift-share regression designs, such as when a regional outcome is regressed on a weighted average of sectoral shocks, using regional sector shares as weights. We conduct a placebo exercise in which we estimate the effect of a shift-share regressor constructed with randomly generated sectoral shocks on actual labor market outcomes across U.S. commuting zones. Tests based on commonly used standard errors with 5% nominal signi…
Inference in Regression Discontinuity Designs with a Discrete Running Variable
We consider inference in regression discontinuity designs when the running variable only takes a moderate number of distinct values. In particular, we study the common practice of using confidence intervals (CIs) based on standard errors that are clustered by the running variable as a means to make inference robust to model misspecification (Lee and Card 2008). We derive theoretical results and present simulation and empirical evidence showing th…
Robust Standard Errors in Small Samples
We study the properties of heteroskedasticity-robust confidence intervals for regression parameters. We show that confidence intervals based on a degrees-of-freedom correction suggested by Bell and McCaffrey (2002) are a natural extension of a principled approach to the Behrens-Fisher problem. We suggest a further improvement for the case with clustering. We show that these standard errors can lead to substantial improvements in coverage rates ev…
Identification and Inference With Many Invalid Instruments
We study estimation and inference in settings where the interest is in the effect of a potentially endogenous regressor on some outcome. To address the endogeneity, we exploit the presence of additional variables. Like conventional instrumental variables, these variables are correlated with the endogenous regressor. However, unlike conventional instrumental variables, they also have direct effects on the outcome, and thus are “invalid” instrument…
No prominent works on this page.
Identification and Inference With Many Invalid Instruments
We study estimation and inference in settings where the interest is in the effect of a potentially endogenous regressor on some outcome. To address the endogeneity, we exploit the presence of additional variables. Like conventional instrumental variables, these variables are correlated with the endogenous regressor. However, unlike conventional instrumental variables, they also have direct effects on the outcome, and thus are “invalid” instrument…
Robust Standard Errors in Small Samples
We study the properties of heteroskedasticity-robust confidence intervals for regression parameters. We show that confidence intervals based on a degrees-of-freedom correction suggested by Bell and McCaffrey (2002) are a natural extension of a principled approach to the Behrens-Fisher problem. We suggest a further improvement for the case with clustering. We show that these standard errors can lead to substantial improvements in coverage rates ev…
Inference in Regression Discontinuity Designs with a Discrete Running Variable
We consider inference in regression discontinuity designs when the running variable only takes a moderate number of distinct values. In particular, we study the common practice of using confidence intervals (CIs) based on standard errors that are clustered by the running variable as a means to make inference robust to model misspecification (Lee and Card 2008). We derive theoretical results and present simulation and empirical evidence showing th…
Shift-Share Designs
We study inference in shift-share regression designs, such as when a regional outcome is regressed on a weighted average of sectoral shocks, using regional sector shares as weights. We conduct a placebo exercise in which we estimate the effect of a shift-share regressor constructed with randomly generated sectoral shocks on actual labor market outcomes across U.S. commuting zones. Tests based on commonly used standard errors with 5% nominal signi…
When can we ignore measurement error in the running variable
In many applications of regression discontinuity designs, the running variable used to assign treatment is only observed with error. We show that, provided the observed running variable (i) correctly classifies treatment assignment and (ii) affects the conditional means of potential outcomes smoothly, ignoring the measurement error nonetheless yields an estimate with a causal interpretation: the average treatment effect for units whose observed r…
One instrument to rule them all
Dynamic Causal Effects in a Nonlinear World
Applied macroeconomists frequently use impulse response estimators motivated by linear models. We study whether the estimands of such procedures have a causal interpretation when the data generating process is in fact nonlinear. We show that vector autoregressions and linear local projections onto observed shocks or proxies identify weighted averages of causal effects regardless of the extent of nonlinearities. By contrast, identification approac…
Econometrics (5 works) · Advanced Causal Inference Techniques (4 works) · Computer Science (4 works) · Mathematics (4 works) · Statistical Methods and Inference (4 works) · Statistics (4 works) · Inference (3 works) · Regression (3 works) · Advanced Statistical Methods and Models (2 works) · Artificial Intelligence (2 works)