|
|
|
|
| LEADER |
01428nam a2200205Ia 4500 |
| 001 |
10.1080-07350015.2017.1366909 |
| 008 |
220511s2019 CNT 000 0 und d |
| 020 |
|
|
|a 07350015 (ISSN)
|
| 245 |
1 |
0 |
|a Why High-Order Polynomials Should Not Be Used in Regression Discontinuity Designs
|
| 260 |
|
0 |
|b American Statistical Association
|c 2019
|
| 856 |
|
|
|z View Fulltext in Publisher
|u https://doi.org/10.1080/07350015.2017.1366909
|
| 520 |
3 |
|
|a It is common in regression discontinuity analysis to control for third, fourth, or higher-degree polynomials of the forcing variable. There appears to be a perception that such methods are theoretically justified, even though they can lead to evidently nonsensical results. We argue that controlling for global high-order polynomials in regression discontinuity analysis is a flawed approach with three major problems: it leads to noisy estimates, sensitivity to the degree of the polynomial, and poor coverage of confidence intervals. We recommend researchers instead use estimators based on local linear or quadratic polynomials or other smooth functions. © 2018, © 2018 American Statistical Association.
|
| 650 |
0 |
4 |
|a Causal identification
|
| 650 |
0 |
4 |
|a Policy analysis
|
| 650 |
0 |
4 |
|a Polynomial regression
|
| 650 |
0 |
4 |
|a Regression discontinuity
|
| 650 |
0 |
4 |
|a Uncertainty
|
| 700 |
1 |
|
|a Gelman, A.
|e author
|
| 700 |
1 |
|
|a Imbens, G.
|e author
|
| 773 |
|
|
|t Journal of Business and Economic Statistics
|
