♪ [music] ♪
- [Narrator] Welcome
to Nobel Conversations.
In this episode, Josh Angrist
and Guido Imbens,
sit down with Isaiah Andrews
to discuss how their research
was initially received
and how they responded
to criticism.
- [Isaiah] At the time,
did you feel like
you were on to something,
you felt this was the beginning
of a whole line of work
that you felt like was going
to be important or...?
- [Guido] Not so much
that it was a whole line of work,
but certainly I felt like,
"Wow, this --"
- [Josh] We've proved something
we didn't know before,
that it was worth knowing.
- Yeah, going back to the...
compared to my job market
paper or something --
No, I felt this was actually
a very clear, crisp result.
- But there was definitely
a mixed reception
and I don't think anybody
said that,
"Oh, well, this is
already something
which is the nightmare scenario
for a researcher
where you think
you've discovered something
and then somebody else says,
"Oh, I knew that."
But there definitely was
a need to convince people
that this was worth knowing,
that instrumental variables
estimates a causal effect
for compliers.
- Yeah, but even though
it took a long time
to convince a bigger audience,
sometimes even fairly quickly,
the reception was pretty good
among a small group of people.
Gary clearly liked it a lot
from the beginning,
and I remember...
because at that point
Josh had left for Israel,
but I remember explaining it
to Don Rubin,
and he was like, "You know,
this really is something here."
- Not right away though.
Don took some convincing.
By the time you got to Don,
there have been
some back and forth with him
and in correspondence, actually.
- But I remember at some point
getting a call or email from him
saying that he was sitting
at the airport in Rome
and looking at the paper
and thinking,
"Yeah, no actually,
you guys are onto something."
- We were happy about that.
But that took longer
than I think you remember.
It wasn't right away.
[laughter]
Because I know
that I was back in Israel
by the time that happened.
I'd left for Israel
in the summer of --
I was only at Harvard
for two years.
We had that one year.
It is remarkable, I mean, that
one year was so fateful for us.
- [Guido] Yes.
I think we understood there was
something good happening,
but maybe we didn't think it was
life-changing, only in retrospect.
♪ [music] ♪
- [Isaiah] As you said, it sounds
like a small group of people
were initially quite receptive,
perhaps took some time
for a broader group of people
to come around to seeing
the LATE framework
as a valuable way to look
at the world.
I guess, in over
the course of that,
were their periods
where you thought,
maybe the people saying
this wasn't a useful way
to look at the world were right?
Did you get discouraged?
How did you think about?
- I don't think I was discouraged,
but the people who were saying
that we're smart people,
well-informed econometricians,
sophisticated readers,
and I think the substance
of the comment
was this is not what
econometrics is about.
Econometrics being transmitted
at that time was about structure.
There was this idea that
there's structure in the economy,
and it's our job to discover it,
and what makes its structure
is it's essentially invariant.
And so we're saying,
in the LATE theorem,
that every instrument produces
its own causal effect,
which is in contradiction to that
to some extent,
and so that was
where the tension was.
People didn't want
to give up that idea.
- Yeah, I remember once
people were started
arguing more vocally against that,
that never really
bothered me that much.
It seemed clear that
we had a result there,
and it became somewhat
controversial,
but controversial in a good way.
It was clear that people felt
they had to come out
against it because --
- Well, I think we think
it's good now.
We might not have loved it
at the time.
I remember being
somewhat more upset --
there was some dinner
where someone said,
"No, no, no,
that paper with Josh --
that was doing a disservice
to the profession."
- We definitely had
reactions like that.
- At some level, that may be
indicative of the culture
in general in economics
at the time.
I thought back later,
what if that happened now?
If I was a senior person
sitting in that conversation,
I would call that out because
it really was not appropriate --
- [Josh] It wasn't so bad.
I think the criticism is...
It wasn't completely misguided.
It was maybe wrong.
No, no, but you can say
that paper is wrong,
but it's saying that
it's a disservice
to the profession --
- that's not really --
- [Isaiah] It's a bit personal.
- Yes, and doing that not to me
but in front of
my senior colleagues.
- But nobody was saying
the result was wrong,
and I remember also,
some of the comments
were thought-provoking.
So we had some negative reviews,
I think, on the average
causal response paper.
Somebody said, "These compliers,
you can't figure out who they are."
It's one thing to say
you're estimating
the effect of treatment
on the treated
or something like that.
You can tell me who's treated
people in the CPS,
you can't tell me who's a complier.
So that was a legitimate challenge.
- That's certainly fair,
and I can see why
that part made people
a little uneasy and uncomfortable.
But at the same time,
because it showed that you couldn't
really go beyond that,
it was a very useful thing
to realize.
I remember on the day
we got to the key result
that I was thinking,
"Wow, this is as good as it gets.
Here we actually have
an insight, but it clearly --"
- And we had to sell it
at some point.
For quite a few years,
we had to sell it,
and it's proven to be quite useful.
I don't think we understood that
it would be so useful at the time.
- No.
- I did feel early on
this was a substantial insight.
- [Josh] Yeah we'd done something.
- But I did not think
goals were there.
- I don't think we were aiming
for the Nobel.
[laughter]
We were very happy to get
that note in Econometrica.
♪ [music] ♪
- [Isaiah] Are there factors
or are ways of approaching problems
that lead people to be better
at recognizing the good stuff
and taking the time to do it
as opposed to dismissing it?
- [Josh] Sometimes
I think it's helpful.
If you're trying to
convince somebody
that you have something
useful to say
and maybe they don't
speak your language,
you might need
to learn their language.
- Yes, yes, exactly.
- That's what we did with Don,
we figured out how to --
I remember we had a very hard time
explaining the exclusion
restriction to Don,
maybe rightfully so,
I think Guido and I
eventually figured out
that it wasn't formulated
very clearly,
and we came up
with a way to do that
in the potential outcomes framework
that I think worked
for the three of us.
- [Guido] Yeah.
Well, it worked
for the bigger literature,
but I think what you're saying
there is exactly right,
you need to figure out
how not just say,
"Okay, I've got this language,
and this this works great,
and I've got to convince
someone else to use the language.
You could first figure out
what language they're using,
and then, only then,
can you try to say,
"Well, but here you're thinking
of it this way."
But that's actually
a pretty hard thing to do.
You get someone
from a different discipline,
convincing them, two junior faculty
in a different department
actually have something
to say to you
that takes a fair amount of effort.
- Yeah, I wrote Don
a number of times,
in fairly long letters.
I remember thinking
this is worth doing,
that if I could convince Don,
that would validate
the framework to some extent.
- I think both you and Don
were a little bit more confident
that you were right.
- Well, we used to argue a lot,
and you would sometimes
referee those.
[laughter]
That was fun.
It wasn't hurtful.
- I remember it getting
a little testy once.
We had lunch in The Faculty Club,
and we were talking about
the draft lottery paper.
We were talking about "never takes"
as people wouldn't serve
in the military
irrespective of whether
they were getting drafted,
and you or Don said something
about shooting yourself
in the foot...
[laughter]
...as a way of getting out
of the military
and that may be
the exclusion restriction
for never takes wasn't working,
and then the other one was going,
"Well, yes, you could do that,
but why would you want
to shoot yourself in the foot?"
[laughter]
It got a little there...
- I usually go for moving
to Canada for my example,
when I'm teaching that.
[laughter]
But things are tricky,
I get students coming
from Computer Science,
and they want to do things
on causal inference,
and it takes a huge amount
of effort to figure out
how they're actually thinking
about a problem
and whether
there's something there.
And so, now over the years,
I've got a little more appreciation
for the fact
that Don was actually willing to --
It took him a while,
but he did engage first with Josh
and then with both of us,
rather than dismissing and saying,
"Okay, well, I can't figure out
what these guys are doing,
and it's probably just
not really that interesting."
- Everybody always wants
to figure out quickly.
You want to save time,
and you want to save
your brain cells
for other things.
The fastest route to that
is to figure out
why you should dismiss something.
- Yes.
- I don't need
to spend time on this.
♪ [music] ♪
- [Narrator] If you'd like
to watch more Nobel Conversations,
click here,
or if you'd like to learn
more about econometrics,
check out Josh's
Mastering Econometrics series.
If you'd like to learn more
about Guido, Josh, and Isaiah,
check out the links
in the description.
♪ [music] ♪