1

I think it is a practical headache rising when doing empirical research. I am examining the impact of anticollusion laws on firms' asset growth as Dasgupsta, 2019 uses the genralized Difference-in-Differences for multiple groups and time periods.

The result is quite good until I perform the clustering test as a robustness test as they recommend as in the rows (7) to (10) as in the picture below

enter image description here

The significance levels are blown away when clustering. I am wondering if we can say anything in this case that we do not need to do cluster, In my case, I run all regression with firm and year fixed effects, controlling for industry * year and region * year fixed effect already. I remember someone told me about a paper of Woodridge recently that we do not necessarily do cluster in some case.

Louise
  • 97
  • 1
  • 16
  • 2
    Is treatment at firm, industry, or country level? Do you have a sample of firms and want to generalize the results to the rest or do you have the population? There is a nice discussion [here](https://blogs.worldbank.org/impactevaluations/when-should-you-cluster-standard-errors-new-wisdom-econometrics-oracle). – dimitriy Jun 23 '21 at 00:51
  • The laws is implemented in each country, and I examine the effect of the laws on firms' asset growth, so it is firms' level if I understand correctly. I have examine of the laws on all the firms excepting the utility and financial firms, and I want to know the causal impact of the laws on firms asset growth. I will definitely have a look at your shared link. Thanks so much. – Louise Jun 23 '21 at 01:02
  • 1
    It is a big problem to me too sine Petersen (2004) raising the clustering thingy, are you replicating the research in your post ? – Louise Jun 23 '21 at 01:11
  • It is an interesting topic to me, hope there is a comprehensive answer here – Louise Jun 23 '21 at 01:14
  • 1
    As treatments are applied at the country level, sure clustering at least at the country level is obvious? – Björn Jun 23 '21 at 21:27
  • Thank you @Björn. But I thought I examine the impacts of laws on firms, so, the examined objective here is at the firm level (or individual level, I deem. Is it a fallacy then? – Louise Jun 23 '21 at 21:29
  • 1
    Part of the intuition is that you cannot tell apart a general country trend (pretty plausible) from an effect of the treatment. Instead, if within the country the treatment was applied at different times per different firms you could tell it apart (and a general country trend could to some extent be absorbed into the general noise). Or if regulation is applied to different industries at different times within a country, then clustering by sector within country could be an alternative. – Björn Jun 23 '21 at 21:39
  • So, you mean, if the laws are implemented across countries at different times, I need to cluster by countries at least? Is it a must then? I have a topic [here](https://stats.stackexchange.com/questions/531939/asking-about-experimental-design-reason-for-clustering-following-abadie-2017), could you please have a look about my argument inside then ? – Louise Jun 23 '21 at 21:43

0 Answers0