I see the authors have written a partial response. However, I'm not persuaded. We've already written a thorough response-to-the-response here: dropbox.com/s/8yn8woym7qw5…
Here's a quick recap of why I'm not persuaded. Originally, I was unhappy that the authors did not plot any relevant data. A simple plot of pre-treatment trends suggested no impact at all of Chinese competition (Quota group, rising after 2002) on patents per firm.
In their response, the authors still don't plot any data, or even try to explain why a simple plot of pre-treatment trends appears to refute their results. Nor do they say how it was that they forgot to disclose that their patent data converges to zero in their sample.
In lieu of simple evidence, their MO is always to go into as-complex-as-possible econometrics, so people won't quite understand what is going on. Math serves the point not to clarify, but to obfuscate.
They can't admit they were wrong, so they take the view that, yes, there were two coding errors in our previous table (plus we described what we did incorrectly), but we also made a 4th error which flips
our results back to being significant. To get significance, though, they provide a textbook example of multi-collinearity. (Just think about this example next time you get rejected from RESTud w/out making such an obvious error.)
They add in the variable "initial Chinese imports" which is very highly correlated with "Chinese imports", especially since country*year & sectoral FEs are all controlled for. They haven't a clue what is driving their results, nor do they furnish any legitimate reason to include
initial Chinese imports in a panel regression w/ Chinese imports and year FEs. They also don't control for trends in patents, which is obviously necessary in the context of a diff-in-diff looking at our graph above.
Also, in the authors response, they talk about their "9 results". With apologies, we have shown that most of the results in their paper were not robust to slight changes in specifications, such as adding in trend controls, differing the FEs, or "un-winsorizing" half-winsored data
I can't help but wonder if someone not affiliated w/ Stanford or MIT could publish a difference-in-difference in a Top 5 w/out plotting pre-treatment trends? And in papers rife w/ other blatant errors? That is what just happened. Twice.
I'm probably going to get some more blowback for writing this, but from my vantage it looks to me like the "con" is still strong in academic "eCONomics".
So, to just fix ideas, here is the new BDvR-20 table where Chinese competition has a yuge impact on innovation in Europe. You see they get significance in column 3 by including Initial Chinese imports (large neg. sign), and 4 dig SIC FEs (which weren't mentioned in original).
Thus their new favored regression differs in four! ways from their initial paper. I can understand we all make mistakes, but four acknowledged errors in one regression is pushing it. And these four errors are not counting the lack of sectoral trends.
However, you won't be surprised to know that that "Current" and "Initial" Chinese imports are highly correlated (R-squared is .6 & t score is 350).
But, their column (3) above also includes 4-digit SIC FEs (the initial Chinese imports variable varies also at the country level), and they have country-year FEs. Added together, we get an R-squared of .76.
How much multi-collinearity is "too much"? Well, we can calculate a VIF of 4.2 for this case, which is greater than a danger zone cutoff of around 2.5 according to this article: statisticalhorizons.com/multicollinear…@johnvanreenen please explain.
As you can see, you have to wake up pretty early in the morning to sneak a slow-ball past RESTud referees and the editorial board.
• • •
Missing some Tweet in this thread? You can try to
force a refresh
I just wasted my morning watching the stimulus debate between @LHSummers and @paulkrugman. It's crazy Summers was ever influential. 1/
First, Summers concedes the 2009 stimulus was too small. He then tries to whitewash his own complicity by blaming Congress for shrinking the package slightly. But, it was he himself who advised to kneecap the package before sending it to Congress. 2/
Secondly, Summers himself is a fan of the theory that democrats should not throw stones and criticize a Dem. administration. I don't hold this theory, obviously, but this is what Larry is doing with the goal of slightly shrinking this stimulus. It's an odd hill to die on. 3/
A few things he doesn't mention is that the Stage 3 trials only took around two months to reach statistical significance and could have been approved in early Oct. instead of mid-December, particularly minus the 5-6 week data review by the FDA.
Second, one could have done the same trials, but layered them a bit so that we get through them all a lot faster. I.e., start Stage 2 before stage 1 approval is complete, and take a large control group from Stage 1 and make it into part of the Stage 3 group, etc., so we get
Re: Pfizer vaccine. It's clear something big happens around day 11. Nothing of import happens around day 32. #firstdosesfirst
Pfizer does a ridiculous time split when they look at one shot vs. two. First, there's no statistically significant difference in the first 7 days after the 2nd shot. Had they used an 11 day cut-off instead, one shot would clearly have won.
And, one shot would also likely have won had they looked within a 7 day window in either direction of shot #2.
Good news! I just got my first "Top 5" journal publication, in the Review of Economic Studies. Top 5 journals in econ are fetishized beyond belief. This publication helps show why we might want a more balanced attitude. #Econtwitterideas.repec.org/p/abo/neswpt/w…
In our paper, we find several coding errors which overturn a seminal paper in the "Chinese competition caused a huge increase in innovation" lit by Bloom et al (BDvR). From the beginning, I knew the BDvR paper had problems. Why? nbloom.people.stanford.edu/sites/g/files/…
Well, first I should say that I am actually somewhat empathetic about the coding errors, common in published papers--a reason we need replication. Any empirical researcher will make mistakes on occasion. But, there is a lot to chew on in this case besides the coding errors.
A bit of good news, after 19 submissions spanning six years, two months, two weeks, and four days, my job market paper on the collapse in US manufacturing has been accepted for publication in the European Economic Review. Here's a thread on the topic. 1/
The original title was "Relative Prices, Hysteresis, and the Decline of American Manufacturing", which later got shortened, with the most recent draft up on Ideas/Repec here: ideas.repec.org/p/cfr/cefirw/w… 2/
The tale of US manufacturing in the 2000s itself is an old bedtime story some economists tell when trying to scare their children. So, listen up. 3/
It's official, the Review of Economic Studies does not accept comment papers (unless they point out actual factual errors), according to my correspondence with an editor. In important ways, it's not really an academic journal. @RevEconStud#EconTwitter#EconReplicationCrisis
This isn't hard. If the RESTud doesn't accept comment papers, then people who do publish there now have an incentive to sneak papers past the referees which are obviously flawed. And people don't have incentive to replicate papers, since they cannot be published. #EconTwitter
It's no mystery why the editorial board refuses to accept comment papers. The benefit of being an editor is not the pride one takes in leaving one's intellectual stamp on the field, but rather the benefit one gets from giving favors to powerful people in the field. #Econtwitter