@LaurawherryR @jamie_daw The problem with matching on pre-period stuff arises because matching is applied *asymmetrically in time* @Lizstuartdc et al have a nice paper that addresses PS methods that are balanced *across* the pre/post boundary https://t.co
差の差(DID)分析にPS weightingを使用したsimulation study. 自分の知っている方法と異なる点もあり、勉強になった。 simulationの解析コード欲しかったな Using propensity scores in difference-in-differences models to estimate the effects of a policy change https://t.co/1QouP77zL8
RT @sankyoh: 傾向スコアで重み付け(IPWとか)した後、差の差法を使うとどうなるのか気になった。ほぼ思いつきなのだが、探してみると、Elizabeth Stuart先生 @Lizstuartdc の論文があった。思いつきを機に勉強しよう。 https://t.co…
傾向スコアで重み付け(IPWとか)した後、差の差法を使うとどうなるのか気になった。ほぼ思いつきなのだが、探してみると、Elizabeth Stuart先生 @Lizstuartdc の論文があった。思いつきを機に勉強しよう。 https://t.co/GxNEWfr29E
RT @laura_tastic: @sylvainCF noticed the problem https://t.co/krHTnNNFYt and worked out the theory https://t.co/nNhKQK9DsL @Lizstuartdc @M…
RT @laura_tastic: @sylvainCF noticed the problem https://t.co/krHTnNNFYt and worked out the theory https://t.co/nNhKQK9DsL @Lizstuartdc @M…
RT @laura_tastic: @sylvainCF noticed the problem https://t.co/krHTnNNFYt and worked out the theory https://t.co/nNhKQK9DsL @Lizstuartdc @M…
RT @laura_tastic: @sylvainCF noticed the problem https://t.co/krHTnNNFYt and worked out the theory https://t.co/nNhKQK9DsL @Lizstuartdc @M…
Thread explaining some sneaky ways that bias can find its way into diff-in-diff analysis. Happy to see that the “solution” is a paper that my @UNCpublichealth @uncsheps friends have already given me!
RT @laura_tastic: @sylvainCF noticed the problem https://t.co/krHTnNNFYt and worked out the theory https://t.co/nNhKQK9DsL @Lizstuartdc @M…
@sylvainCF noticed the problem https://t.co/krHTnNNFYt and worked out the theory https://t.co/nNhKQK9DsL @Lizstuartdc @Michael_Chernew @colleenlbarry et al. developed symmetric PS weighting for diff-in-diff that avoids the problem https://t.co/fjhNAOB2LZ