Oster_fig.pdf (155.13 kB)View fileThis item contains files with download restrictions
.EPS
Oster_fig_1.eps (325.5 kB)View fileThis item contains files with download restrictions
.GPH
Oster_fig_1.gph (130.44 kB)View fileThis item contains files with download restrictions
DOCUMENT
Oster_fig_1.pdf (105.7 kB)View fileThis item contains files with download restrictions
.EPS
Oster_fig_2.eps (328.84 kB)View fileThis item contains files with download restrictions
.GPH
Oster_fig_2.gph (131.64 kB)View fileThis item contains files with download restrictions
DOCUMENT
Oster_fig_2.pdf (106.9 kB)View fileThis item contains files with download restrictions
TEXT
ReadMe.txt (1.03 kB)View fileThis item contains files with download restrictions
TEXT
Scenario_1.do (14.38 kB)View fileThis item contains files with download restrictions
TEXT
Scenario_1.log (11.47 kB)View fileThis item contains files with download restrictions
TEXT
Scenario_2.do (14.38 kB)View fileThis item contains files with download restrictions
TEXT
Scenario_2.log (9.54 kB)View fileThis item contains files with download restrictions
TEXT
estout.ado (159.06 kB)View fileThis item contains files with download restrictions
.HLP
estout.hlp (106.11 kB)View fileThis item contains files with download restrictions
TEXT
psacalc.ado (16.53 kB)View fileThis item contains files with download restrictions
.STHLP
psacalc.sthlp (8.68 kB)View fileThis item contains files with download restrictions
Next page
Previous page
1/1
Switch ViewSwitch between different file views
Thumbnail viewList viewFile view
17 filesFullscreen
Comments on “Unobservable Selection and Coefficient Stability: Theory and Evidence” and “Poorly Measured Confounders are More Useful on the Left Than on the Right”
posted on 2019-05-08, 15:30authored byGiuseppe De Luca, Jan R. Magnus, Franco Peracchi
We establish a link between the approaches proposed by Oster (2019) and Pei, Pischke, and Schwandt (2019) which contribute to the development of inferential procedures for causal effects in the challenging and empirically relevant situation where the unknown data-generation process is not included in the set of models considered by the investigator. We use the general misspecification framework recently proposed by De Luca, Magnus, and Peracchi (2018) to analyze and understand the implications of the restrictions imposed by the two approaches.
Funding
Giuseppe De Luca and Franco Peracchi acknowledge financial support from MIUR PRIN 2015FMRE5X.