Identification of Treatment and Control Group

[Tariqul Islam]

Respected members,

I am trying to employ DID as a means of analysis. In my dataset of 287 firms between 2001 and 2016, there was a policy reform in 2010 of including at least 10 percent of female directors. After reading some articles on DID, I have developed the following alternatives to identify the treatment and control groups.

Option 1
Treatment group: Firms that did not have 10% of female directors before 2010.
Control group: Firms that had female directors of 10% or above before 2010.

Option 2
Treatment group: Firms that did not have 10% of female directors before 2010 and had at least 10% of female directors from 2010 onwards.
Control group: Firms that did not have 10% of female directors before 2010 and did not have at least 10% of female directors even after 2010.
The firms that already had at least 10% female directors before 2010 are excluded from the analysis.

Could you please advise me in this regard as to which of the above option (1 or 2) is appropriate?

Thanks in anticipation.

[Clyde Schechter]

Well, as between these two I would choose Option 2. But I don't think that one's quite right either. What you really want for a control group is firms that were not subject to the policy reform but were otherwise very similar to the treatment group. For example, the control group might be firms from a neighboring jurisdiction that did not adopt the policy regulation, or firms that were exempt from the policy because of, say, size (although in that case you would need to restrict your treatment group to firms that were just on the other side of the size threshold so they would be comparable on this variable) or something like that. The problem with option 2 is that your control group is essentially firms that were non-compliant with the policy change--and that's really not going to be a good comparison. The ideal control group is firms that were not subject to the policy.

[Tariqul Islam]

Many thanks Clyde for your kind reply.

For me, the minimum level (10%) of women directors are mandatory for all the firms irrespective of size, age, industry etc. That is, each and every firms in the particular country settings has to maintain at least 10% female directors into boards from 2012 onwards. Please note, my outcome variable is Risk and I want see if the policy has any impact on Risk.

Now, what do you suggest?

[Clyde Schechter]

I don't know what to suggest. It sounds like perhaps your data are not suitable for answering this question. If I understand correctly, you have data on a set of firms, all of which were required in 2012 to have a minimum of 10% women directors. You have data on these firms both before and after 2012, which is good. But you don't have a real control group here. The closest you can come to a control group is those firms which, despite the mandate, still did not get 10% women directors. These do not strike me as a suitable control group because these firms would either be defiant or for whatever reason incapable of complying with the mandate. Either way, they are likely to be materially different from those who did comply with the mandate in ways that would affect most outcomes. I can't comment on the specific outcome Risk because I don't know what you have in mind here: there are many kinds of risk in the world. I imagine you have some specific finance-related definition of Risk in mind, but as I do not work in finance I am not aware of what that would be.

You might be able to get more helpful advice from somebody who works in finance. There are several members of this Forum who do, and perhaps one of them will chime in. Or you might consult a colleague in your discipline to see if they can see a way around this difficulty.