Matching, Regression Discontinuity, Difference in Differences, and Beyond

Lee, Myoung‐jae

doi:10.1093/acprof:oso/9780190258733.001.0001

Cited by 58 publications

(36 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The vector X i , t accounts for game and play specific characteristics. As noted in Lee (), and as evident from our discussions above, “Even if X is not controlled for, its effect can be removed in DID as long as the effect is common between the two groups.” But conditioning on some play‐specific variables could, as noted by Wooldridge (), “account for the possibility that the random samples within a group have systematically different characteristics in the two time periods.” This would make the common trend assumption even more plausible and also improve the precision of the estimation. In our analysis, we explicitly control for many determinants of penalty outcomes, be they observable or unobservable.…”

Section: Estimation Strategymentioning

confidence: 76%

“Crime” on the Field

Kitchens¹,

Makofske

Wang³

2018

Southern Economic Journal

View full text Add to dashboard Cite

Does a greater police presence cause crime rates to decrease? To answer this question, we circumvent common simultaneity and reverse causality issues by exploiting an experiment from college football. In 2013, the Big XII added an eighth referee to conference games only. Unique features of this experiment allow us to identify the causal effects of increased "police force" (officiating crew) size on observed "crime" (penalty) rates, and to distinguish between alternative mechanisms behind those effects. Overall, we find that the increased police presence causes an increase in the observed crime rate. This increase is largest in teams' first treated games, suggesting a substantial detection effect. However, the penalty rate decreases sharply in teams' second treated games, suggesting a large general deterrent effect. Under mild assumptions, results suggest that the general deterrent effect is partly due to players learning to avoid detection, but that the learning process involves errors over time.

show abstract

Section: Estimation Strategymentioning

confidence: 76%

“Crime” on the Field

Kitchens¹,

Makofske

Wang³

2018

Southern Economic Journal

View full text Add to dashboard Cite

show abstract

“…Also, the regression can be easily adapted to accommodate multiple periods and continuous treatments, among other features. An introductory discussion and a more elaborate discussion are available elsewhere . The DD analysis has been used in the medical field …”

Section: Red Blood Cell Irradiation Example Of Difference‐in‐differenmentioning

confidence: 99%

Difference in difference: simple tool, accurate results, causal effects

Cataife

Pagano

2017

Transfusion

View full text Add to dashboard Cite

“…The availability of instruments enables us to find the source of endogeneity, and controlling this (a 'control function (CF) approach') leads to 'selection on unobservables' that (D, W ) are as good as randomized given X and the controlled source of endogeneity (Lee, 2005(Lee, , 2016. We implement our causal framework with a doubly censored maximum likelihood estimator (MLE).…”

Section: Introductionmentioning

confidence: 99%

Practical Causal Analysis for the Treatment Timing Effect on Doubly Censored Duration: Effect of Fertility on Work Span

Angelov¹,

Johansson

Lee

2019

Journal of the Royal Statistical Society Series A: Statistics in Society

View full text Add to dashboard Cite

Summary We present a practical causal framework to estimate the effects of a treatment and its timing on a doubly censored response. We then apply the methodology to find the effect of fertility on work duration where, not just fertility itself, but the timing of fertility should matter greatly. Since fertility and its decision of timing are chosen by the individual, it is likely to be endogenous. We use a populationwide data set over mothers with two children to address the endogeneity issue by using the first two children's same‐sex instrument in a ‘control function’ setting. We find that having a third child reduces the average labour market work duration, and that the magnitude of the effect increases monotonically with the waiting time between the second and third children. Moreover, the negative effect varies substantially over education and second‐birth age, being stronger for mothers with higher education and lower second‐birth age.

show abstract

Matching, Regression Discontinuity, Difference in Differences, and Beyond

Cited by 58 publications

References 0 publications

“Crime” on the Field

“Crime” on the Field

Difference in difference: simple tool, accurate results, causal effects

Practical Causal Analysis for the Treatment Timing Effect on Doubly Censored Duration: Effect of Fertility on Work Span

Contact Info

Product

Resources

About