{"id":1522,"date":"2021-08-30T14:56:20","date_gmt":"2021-08-30T18:56:20","guid":{"rendered":"http:\/\/www.kaichen.work\/?p=1522"},"modified":"2023-08-01T20:44:20","modified_gmt":"2023-08-02T00:44:20","slug":"use-stata-to-do-propensity-score-matching","status":"publish","type":"post","link":"https:\/\/www.kaichen.work\/?p=1522","title":{"rendered":"Stata command to perform propensity score matching (PSM)"},"content":{"rendered":"

Most propensity score matching (PSM) examples typically use cross-sectional data rather than panel data. However, in accounting research, panel data (observations with two subscripts i<\/em> and t<\/em>, e.g., firm-years) are often used in a difference-in-differences (DID) research design. This involves two dummy variables, TREATMENT<\/code> and POST<\/code>\u00a0, in the following regression:<\/p>\n

Outcome = TREATMENT + POST + TREATMENT * POST<\/em><\/p>\n

where TREATMENT<\/code> indicates a treatment event and POST<\/code> indicates before or after that event. In this context, it is common to perform one-to-one matching using selected pre-event<\/strong> and firm-level<\/strong> variables (X<\/code>s). These pre-event variables can be measured either at the most recent date before the event (e.g., total assets at the most recent quarter end before the event) or as an average over the pre-event period (e.g., average total assets in the four quarters preceding the event).<\/p>\n

To conduct PSM, a probit or logit regression is needed:<\/p>\n

TREATMENT = X1 + X2 + …<\/em><\/p>\n

The single nearest neighbour based on propensity score is selected as the matched control observation. The treatment observations and their respective matched control observations then form the sample for subsequent DID regressions.<\/p>\n

In Stata, the third-party module psmatch2<\/code> is commonly used to find matched control observations using PSM. To install the module, the following command can be used:<\/p>\n

ssc install psmatch2<\/code><\/p>\n

Once installed, the following command is typically used:<\/p>\n

psmatch2 TREATMENT X1 X2 ..., [noreplacement logit descending]<\/code><\/p>\n

There are three options in the above command:<\/p>\n