1
00:00:00,130 --> 00:00:02,200
♪ [music] ♪

2
00:00:03,645 --> 00:00:05,600
- [Narrator] Welcome
to Nobel Conversations.

3
00:00:07,250 --> 00:00:10,240
In this episode, Josh Angrist 
and Guido Imbens,

4
00:00:10,240 --> 00:00:11,920
sit down with Isaiah Andrews

5
00:00:11,920 --> 00:00:14,303
to discuss how their research
was initially received

6
00:00:14,999 --> 00:00:17,090
and how they responded 
to criticism.

7
00:00:18,700 --> 00:00:20,380
- [Isaiah] At the time, 
did you feel like

8
00:00:20,380 --> 00:00:21,627
you were on to something,

9
00:00:21,627 --> 00:00:25,152
you felt this was the beginning
of a whole line of work

10
00:00:25,152 --> 00:00:27,202
that you felt like was going 
to be important or...?

11
00:00:27,600 --> 00:00:30,000
- [Guido] Not so much
that it was a whole line of work,

12
00:00:30,000 --> 00:00:31,894
but certainly I felt like, 
"Wow, this--"

13
00:00:32,277 --> 00:00:35,045
- [Josh] We've proved something 
we didn't know before,

14
00:00:35,045 --> 00:00:36,114
that it was worth knowing.

15
00:00:36,114 --> 00:00:38,033
- Yeah, going back to the...

16
00:00:38,741 --> 00:00:41,080
compared to my job market
paper or something--

17
00:00:41,080 --> 00:00:45,560
No, I felt this was actually 
a very clear, crisp result.

18
00:00:46,400 --> 00:00:49,530
- But there was definitely 
a mixed reception

19
00:00:49,530 --> 00:00:52,420
and I don't think anybody 
said that,

20
00:00:52,420 --> 00:00:55,487
"Oh, well, this is 
already something

21
00:00:56,043 --> 00:00:59,386
which is the nightmare scenario
for a researcher

22
00:01:00,230 --> 00:01:02,003
where you think
you've discovered something

23
00:01:02,003 --> 00:01:04,461
and then somebody else says, 
"Oh, I knew that."

24
00:01:05,000 --> 00:01:07,220
But there definitely was 
a need to convince people

25
00:01:07,220 --> 00:01:10,370
that this was worth knowing,
that instrumental variables

26
00:01:10,370 --> 00:01:12,687
estimates a causal effect 
for compliers.

27
00:01:13,200 --> 00:01:16,178
- Yeah, but even though
it took a long time

28
00:01:16,178 --> 00:01:19,348
to convince a bigger audience,

29
00:01:19,820 --> 00:01:24,346
sometimes even fairly quickly, 
the reception was pretty good

30
00:01:24,800 --> 00:01:26,645
among a small group of people.

31
00:01:27,200 --> 00:01:31,297
Gary clearly liked it a lot 
from the beginning,

32
00:01:31,800 --> 00:01:33,289
and I remember...

33
00:01:33,289 --> 00:01:35,645
because at that point
Josh had left for Israel,

34
00:01:35,645 --> 00:01:38,886
but I remember explaining it 
to Don Rubin,

35
00:01:39,696 --> 00:01:43,700
and he was like, "You know, 
this really is something here."

36
00:01:43,700 --> 00:01:45,197
- Not right away though.

37
00:01:45,932 --> 00:01:47,173
Don took some convincing.

38
00:01:47,500 --> 00:01:49,150
By the time you got to Don,

39
00:01:49,150 --> 00:01:51,226
there have been 
some back and forth with him

40
00:01:51,226 --> 00:01:53,304
and in correspondence, actually.

41
00:01:53,700 --> 00:01:57,103
- But I remember at some point 
getting a call or email from him

42
00:01:57,103 --> 00:02:00,020
saying that he was sitting 
at the airport in Rome

43
00:02:00,020 --> 00:02:03,700
and looking at the paper 
and thinking,

44
00:02:03,700 --> 00:02:07,000
"Yeah, no actually, 
you guys are onto something."

45
00:02:07,490 --> 00:02:08,594
- We were happy about that.

46
00:02:08,594 --> 00:02:10,550
But that took longer 
than I think you remember.

47
00:02:11,030 --> 00:02:12,500
It wasn't right away.

48
00:02:12,500 --> 00:02:13,700
[laughter]

49
00:02:13,700 --> 00:02:15,325
Because I know
that I was back in Israel

50
00:02:15,325 --> 00:02:16,627
by the time that happened.

51
00:02:16,627 --> 00:02:18,750
I'd left for Israel 
in the summer of--

52
00:02:19,390 --> 00:02:21,190
I was only at Harvard 
for two years.

53
00:02:21,190 --> 00:02:22,540
We had that one year.

54
00:02:22,540 --> 00:02:25,700
It is remarkable, I mean, that
one year was so fateful for us.

55
00:02:25,900 --> 00:02:27,200
- [Guido] Yes.

56
00:02:27,690 --> 00:02:30,200
I think we understood there was
something good happening,

57
00:02:30,200 --> 00:02:33,700
but maybe we didn't think it was
life-changing, only in retrospect.

58
00:02:33,700 --> 00:02:35,620
♪ [music] ♪

59
00:02:35,620 --> 00:02:37,495
- [Isaiah] As you said, it sounds
like a small group of people

60
00:02:37,495 --> 00:02:39,190
were initially quite receptive,

61
00:02:39,190 --> 00:02:42,190
perhaps took some time
for a broader group of people

62
00:02:43,090 --> 00:02:45,912
to come around to seeing 
the LATE framework

63
00:02:45,912 --> 00:02:47,620
as a valuable way to look 
at the world.

64
00:02:47,620 --> 00:02:50,100
I guess, in over
the course of that,

65
00:02:50,100 --> 00:02:52,128
were their periods 
where you thought,

66
00:02:52,128 --> 00:02:54,450
maybe the people saying 
this wasn't a useful way

67
00:02:54,450 --> 00:02:55,751
to look at the world were right?

68
00:02:55,751 --> 00:02:58,360
Did you get discouraged? 
How did you think about?

69
00:02:58,360 --> 00:02:59,755
- I don't think I was discouraged,

70
00:02:59,755 --> 00:03:02,271
but the people who were saying
that we're smart people,

71
00:03:02,784 --> 00:03:06,117
well-informed econometricians,

72
00:03:06,117 --> 00:03:07,800
sophisticated readers,

73
00:03:08,900 --> 00:03:11,324
and I think the substance
of the comment

74
00:03:11,324 --> 00:03:14,297
was this is not what 
econometrics is about.

75
00:03:14,297 --> 00:03:20,572
Econometrics being transmitted 
at that time was about structure.

76
00:03:21,300 --> 00:03:24,490
There was this idea that
there's structure in the economy,

77
00:03:25,100 --> 00:03:27,200
and it's our job to discover it,

78
00:03:27,200 --> 00:03:30,952
and what makes its structure
is it's essentially invariant.

79
00:03:32,570 --> 00:03:34,900
And so we're saying, 
in the LATE theorem,

80
00:03:34,900 --> 00:03:37,699
that every instrument produces
its own causal effect,

81
00:03:37,699 --> 00:03:41,386
which is in contradiction to that
to some extent,

82
00:03:41,386 --> 00:03:43,640
and so that was 
where the tension was.

83
00:03:43,640 --> 00:03:45,551
People didn't want 
to give up that idea.

84
00:03:46,300 --> 00:03:50,369
- Yeah, I remember once 
people were started

85
00:03:51,200 --> 00:03:55,664
arguing more vocally against that,

86
00:03:56,900 --> 00:03:59,483
that never really 
bothered me that much.

87
00:03:59,483 --> 00:04:03,051
It seemed clear that 
we had a result there,

88
00:04:03,051 --> 00:04:05,878
and it became somewhat 
controversial,

89
00:04:05,878 --> 00:04:08,395
but controversial in a good way.

90
00:04:08,620 --> 00:04:10,190
It was clear that people felt

91
00:04:10,820 --> 00:04:13,835
they had to come out
against it because--

92
00:04:13,970 --> 00:04:15,649
- Well, I think we think
it's good now.

93
00:04:17,426 --> 00:04:19,238
We might not have loved it 
at the time.

94
00:04:20,168 --> 00:04:22,984
I remember being
somewhat more upset--

95
00:04:22,984 --> 00:04:24,780
there was some dinner 
where someone said,

96
00:04:24,780 --> 00:04:27,455
"No, no, no, 
that paper with Josh --

97
00:04:28,855 --> 00:04:30,749
that was doing a disservice
to the profession."

98
00:04:32,050 --> 00:04:33,850
- We definitely had 
reactions like that.

99
00:04:35,410 --> 00:04:38,200
- At some level, that may be 
indicative of the culture

100
00:04:38,400 --> 00:04:40,000
in general in economics 
at the time.

101
00:04:41,400 --> 00:04:44,097
I thought back later, 
what if that happened now?

102
00:04:44,600 --> 00:04:47,682
If I was a senior person
sitting in that conversation,

103
00:04:48,200 --> 00:04:51,898
I would call that out because
it really was not appropriate--

104
00:04:53,000 --> 00:04:54,200
- [Josh] It wasn't so bad.

105
00:04:54,600 --> 00:04:56,600
I think the criticism is...

106
00:04:57,700 --> 00:04:59,298
It wasn't completely misguided.

107
00:05:00,070 --> 00:05:01,351
It was maybe wrong.

108
00:05:01,800 --> 00:05:04,485
No, no, but you can say 
that paper is wrong,

109
00:05:05,280 --> 00:05:06,440
but it's saying that

110
00:05:06,440 --> 00:05:08,128
it's a disservice 
to the profession --

111
00:05:08,128 --> 00:05:10,300
- that's not really--
- [Isaiah] It's a bit personal.

112
00:05:10,300 --> 00:05:12,646
- Yes, and doing that not to me

113
00:05:12,646 --> 00:05:14,442
but in front of 
my senior colleagues.

114
00:05:15,191 --> 00:05:17,369
- But nobody was saying 
the result was wrong,

115
00:05:17,369 --> 00:05:18,700
and I remember also,

116
00:05:18,700 --> 00:05:21,579
some of the comments 
were thought-provoking.

117
00:05:21,579 --> 00:05:23,059
So we had some negative reviews,

118
00:05:23,059 --> 00:05:25,861
I think, on the average 
causal response paper.

119
00:05:26,500 --> 00:05:30,361
Somebody said, "These compliers,
you can't figure out who they are."

120
00:05:31,967 --> 00:05:33,891
It's one thing to say
you're estimating

121
00:05:33,891 --> 00:05:35,678
the effect of treatment
on the treated

122
00:05:35,678 --> 00:05:36,840
or something like that.

123
00:05:36,840 --> 00:05:38,400
You can tell me who's treated

124
00:05:38,700 --> 00:05:42,289
people in the CPS,
you can't tell me who's a complier.

125
00:05:42,929 --> 00:05:44,679
So that was a legitimate challenge.

126
00:05:44,679 --> 00:05:47,800
- That's certainly fair,
and I can see why

127
00:05:49,880 --> 00:05:53,502
that part made people
a little uneasy and uncomfortable.

128
00:05:54,300 --> 00:05:56,400
But at the same time,

129
00:05:56,900 --> 00:06:00,244
because it showed that you couldn't
really go beyond that,

130
00:06:00,800 --> 00:06:03,775
it was a very useful thing 
to realize.

131
00:06:04,630 --> 00:06:08,831
I remember on the day
we got to the key result

132
00:06:09,238 --> 00:06:13,113
that I was thinking,
"Wow, this is as good as it gets.

133
00:06:14,221 --> 00:06:16,978
Here we actually have
an insight, but it clearly--"

134
00:06:17,500 --> 00:06:19,250
- And we had to sell it 
at some point.

135
00:06:19,480 --> 00:06:21,261
For quite a few years, 
we had to sell it,

136
00:06:23,480 --> 00:06:24,892
and it's proven to be quite useful.

137
00:06:25,500 --> 00:06:28,761
I don't think we understood that
it would be so useful at the time.

138
00:06:28,761 --> 00:06:29,871
- No.

139
00:06:30,170 --> 00:06:34,600
- I did feel early on
this was a substantial insight.

140
00:06:34,600 --> 00:06:36,440
- [Josh] Yeah we'd done something.

141
00:06:36,440 --> 00:06:40,041
- But I did not think 
goals were there.

142
00:06:40,700 --> 00:06:42,600
- I don't think we were aiming 
for the Nobel.

143
00:06:42,600 --> 00:06:43,730
[laughter]

144
00:06:43,730 --> 00:06:46,243
We were very happy to get
that note in <i>Econometrica.</i>

145
00:06:46,859 --> 00:06:48,829
♪ [music] ♪

146
00:06:49,770 --> 00:06:51,560
- [Isaiah] Are there factors 
or are ways of approaching problems

147
00:06:51,560 --> 00:06:54,186
that lead people to be better 
at recognizing the good stuff

148
00:06:54,186 --> 00:06:56,600
and taking the time to do it 
as opposed to dismissing it?

149
00:06:56,600 --> 00:06:57,830
- [Josh] Sometimes 
I think it's helpful.

150
00:06:57,830 --> 00:06:59,478
If you're trying to 
convince somebody

151
00:06:59,478 --> 00:07:01,247
that you have something 
useful to say

152
00:07:01,900 --> 00:07:04,176
and maybe they don't 
speak your language,

153
00:07:04,894 --> 00:07:06,761
you might need 
to learn their language.

154
00:07:06,761 --> 00:07:07,910
- Yes, yes, exactly.

155
00:07:07,910 --> 00:07:11,736
- That's what we did with Don,
we figured out how to--

156
00:07:11,736 --> 00:07:14,052
I remember we had a very hard time

157
00:07:14,052 --> 00:07:16,058
explaining the exclusion
restriction to Don,

158
00:07:17,430 --> 00:07:18,993
maybe rightfully so,

159
00:07:19,804 --> 00:07:21,948
I think Guido and I 
eventually figured out

160
00:07:21,948 --> 00:07:24,420
that it wasn't formulated 
very clearly,

161
00:07:25,400 --> 00:07:27,450
and we came up 
with a way to do that

162
00:07:27,450 --> 00:07:29,316
in the potential outcomes framework

163
00:07:29,316 --> 00:07:32,218
that I think worked
for the three of us.

164
00:07:32,218 --> 00:07:33,419
- [Guido] Yeah.

165
00:07:33,419 --> 00:07:35,454
Well, it worked
for the bigger literature,

166
00:07:35,454 --> 00:07:37,639
but I think what you're saying 
there is exactly right,

167
00:07:37,639 --> 00:07:40,860
you need to figure out 
how not just say,

168
00:07:40,860 --> 00:07:43,894
"Okay, I've got this language,
and this this works great,

169
00:07:43,894 --> 00:07:45,900
and I've got to convince
someone else to use the language.

170
00:07:45,900 --> 00:07:48,188
You could first figure out 
what language they're using,

171
00:07:48,680 --> 00:07:51,028
and then, only then, 
can you try to say,

172
00:07:51,028 --> 00:07:53,140
"Well, but here you're thinking
of it this way."

173
00:07:53,140 --> 00:07:56,880
But that's actually 
a pretty hard thing to do.

174
00:07:56,880 --> 00:07:59,098
You get someone
from a different discipline,

175
00:07:59,098 --> 00:08:02,300
convincing them, two junior faculty
in a different department

176
00:08:02,300 --> 00:08:04,366
actually have something 
to say to you

177
00:08:04,596 --> 00:08:06,516
that takes a fair amount of effort.

178
00:08:07,500 --> 00:08:09,782
- Yeah, I wrote Don 
a number of times,

179
00:08:10,420 --> 00:08:11,868
in fairly long letters.

180
00:08:11,868 --> 00:08:13,805
I remember thinking 
this is worth doing,

181
00:08:14,600 --> 00:08:16,006
that if I could convince Don,

182
00:08:16,780 --> 00:08:19,444
that would validate
the framework to some extent.

183
00:08:20,300 --> 00:08:22,522
- I think both you and Don

184
00:08:22,522 --> 00:08:25,000
were a little bit more confident 
that you were right.

185
00:08:25,000 --> 00:08:26,438
- Well, we used to argue a lot,

186
00:08:26,438 --> 00:08:28,320
and you would sometimes 
referee those.

187
00:08:28,320 --> 00:08:29,500
[laughter]

188
00:08:29,800 --> 00:08:30,800
That was fun.

189
00:08:32,760 --> 00:08:34,125
It wasn't hurtful.

190
00:08:35,200 --> 00:08:37,492
- I remember it getting 
a little testy once.

191
00:08:37,935 --> 00:08:39,606
We had lunch in The Faculty Club,

192
00:08:40,600 --> 00:08:44,077
and we were talking about 
the draft lottery paper.

193
00:08:44,930 --> 00:08:47,430
We were talking about "never takes"

194
00:08:47,430 --> 00:08:49,761
as people wouldn't serve
in the military

195
00:08:49,761 --> 00:08:53,500
irrespective of whether
they were getting drafted,

196
00:08:54,500 --> 00:08:56,936
and you or Don said something

197
00:08:56,936 --> 00:08:58,800
about shooting yourself
in the foot...

198
00:08:58,800 --> 00:08:59,800
[laughter]

199
00:08:59,800 --> 00:09:01,530
...as a way of getting out
of the military

200
00:09:01,530 --> 00:09:03,230
and that may be 
the exclusion restriction

201
00:09:03,230 --> 00:09:05,743
for never takes wasn't working,

202
00:09:06,300 --> 00:09:08,520
and then the other one was going,

203
00:09:08,520 --> 00:09:09,791
"Well, yes, you could do that,

204
00:09:09,791 --> 00:09:12,008
but why would you want 
to shoot yourself in the foot?"

205
00:09:12,008 --> 00:09:13,225
[laughter]

206
00:09:13,225 --> 00:09:15,400
It got a little there...

207
00:09:15,400 --> 00:09:17,860
- I usually go for moving
to Canada for my example,

208
00:09:18,690 --> 00:09:20,096
when I'm teaching that.

209
00:09:20,096 --> 00:09:21,365
[laughter]

210
00:09:22,030 --> 00:09:23,575
But things are tricky,

211
00:09:24,860 --> 00:09:26,595
I get students coming
from Computer Science,

212
00:09:26,595 --> 00:09:29,943
and they want to do things 
on causal inference,

213
00:09:30,566 --> 00:09:33,460
and it takes a huge amount 
of effort to figure out

214
00:09:33,460 --> 00:09:35,230
how they're actually thinking 
about a problem

215
00:09:35,230 --> 00:09:37,000
and whether
there's something there.

216
00:09:37,000 --> 00:09:38,310
And so, now over the years,

217
00:09:38,310 --> 00:09:40,302
I've got a little more appreciation
for the fact

218
00:09:40,302 --> 00:09:41,958
that Don was actually willing to--

219
00:09:42,630 --> 00:09:46,000
It took him a while, 
but he did engage first with Josh

220
00:09:46,400 --> 00:09:47,500
and then with both of us,

221
00:09:48,380 --> 00:09:50,245
rather than dismissing and saying,

222
00:09:50,245 --> 00:09:53,348
"Okay, well, I can't figure out
what these guys are doing,

223
00:09:53,348 --> 00:09:56,435
and it's probably just 
not really that interesting."

224
00:09:57,200 --> 00:09:59,736
- Everybody always wants 
to figure out quickly.

225
00:10:00,196 --> 00:10:01,376
You want to save time,

226
00:10:01,376 --> 00:10:03,410
and you want to save 
your brain cells

227
00:10:03,410 --> 00:10:04,583
for other things.

228
00:10:05,000 --> 00:10:07,000
The fastest route to that
is to figure out

229
00:10:07,000 --> 00:10:08,460
why you should dismiss something.

230
00:10:08,460 --> 00:10:09,560
- Yes.

231
00:10:09,560 --> 00:10:11,100
- I don't need
to spend time on this.

232
00:10:11,100 --> 00:10:12,498
♪ [music] ♪

233
00:10:12,498 --> 00:10:15,143
- [Narrator] If you'd like 
to watch more Nobel Conversations,

234
00:10:15,143 --> 00:10:16,207
click here,

235
00:10:16,207 --> 00:10:18,409
or if you'd like to learn
more about econometrics,

236
00:10:18,640 --> 00:10:21,240
check out Josh's
Mastering Econometrics series.

237
00:10:21,800 --> 00:10:24,540
If you'd like to learn more
about Guido, Josh, and Isaiah,

238
00:10:24,860 --> 00:10:26,502
check out the links 
in the description.

239
00:10:26,992 --> 00:10:28,697
♪ [music] ♪