3 ways to spot a bad statistic | Mona Chalabi

244,278 views ใƒป 2017-04-17

TED


์•„๋ž˜ ์˜๋ฌธ์ž๋ง‰์„ ๋”๋ธ”ํด๋ฆญํ•˜์‹œ๋ฉด ์˜์ƒ์ด ์žฌ์ƒ๋ฉ๋‹ˆ๋‹ค.

๋ฒˆ์—ญ: Ju Hye Lim ๊ฒ€ํ† : Jihyeon J. Kim
00:12
I'm going to be talking about statistics today.
0
12704
2763
์˜ค๋Š˜์€ ํ†ต๊ณ„์— ๋Œ€ํ•ด ๋ง์”€๋“œ๋ฆด ๊ฑฐ์˜ˆ์š”.
00:15
If that makes you immediately feel a little bit wary, that's OK,
1
15491
3138
์•ฝ๊ฐ„ ๋ถˆ์•ˆํ•ดํ•˜์…”๋„ ๊ดœ์ฐฎ์•„์š”.
00:18
that doesn't make you some kind of crazy conspiracy theorist,
2
18653
2859
๊ทธ๋ ‡๋‹ค๊ณ  ํ•ด์„œ ์ •์‹ ๋‚˜๊ฐ„ ์Œ๋ชจ๋ก ์ž์ธ ๊ฒƒ์ด ์•„๋‹ˆ๋ผ
00:21
it makes you skeptical.
3
21536
1296
๋‹จ์ง€ ํšŒ์˜์ ์ธ ๋ถ„์ธ ๊ฒƒ์ด๋‹ˆ๊นŒ์š”.
00:22
And when it comes to numbers, especially now, you should be skeptical.
4
22856
3886
์ˆซ์ž์— ๊ด€ํ•ด์„œ๋Š”, ํŠนํžˆ๋‚˜ ์ง€๊ธˆ์€ ์˜์‹ฌ์„ ํ•˜์…”์•ผ ํ•ฉ๋‹ˆ๋‹ค.
00:26
But you should also be able to tell which numbers are reliable
5
26766
3011
ํ•˜์ง€๋งŒ ์–ด๋–ค ์ˆซ์ž๋ฅผ ์‹ ๋ขฐํ•ด๋„ ๋˜๊ณ  ์–ด๋–ค ์ˆซ์ž๋ฅผ ์‹ ๋ขฐํ•˜๋ฉด ์•ˆ ๋˜๋Š”์ง€๋ฅผ
00:29
and which ones aren't.
6
29801
1160
๊ตฌ๋ถ„ํ•  ์ค„ ์•Œ์•„์•ผ ํ•ด์š”.
00:30
So today I want to try to give you some tools to be able to do that.
7
30985
3206
๊ทธ๋ž˜์„œ ๊ตฌ๋ถ„ํ•  ์ˆ˜ ์žˆ๊ฒŒ ํ•ด์ฃผ๋Š” ๋ช‡ ๊ฐ€์ง€ ๋ฐฉ๋ฒ•์„ ์•Œ๋ ค๋“œ๋ฆฌ๋ ค๊ณ  ํ•ด์š”.
00:34
But before I do,
8
34215
1169
ํ•˜์ง€๋งŒ ๊ทธ ์ „์—
00:35
I just want to clarify which numbers I'm talking about here.
9
35408
2839
์ œ๊ฐ€ ๋ง์”€๋“œ๋ฆด ์ˆซ์ž๋“ค์ด ์–ด๋–ค ๊ฑด์ง€ ๋ช…ํ™•ํžˆ ์งš๊ณ  ๋„˜์–ด๊ฐˆ๊ฒŒ์š”.
00:38
I'm not talking about claims like,
10
38271
1635
"10๋ช… ์ค‘ 9๋ช…์˜ ์—ฌ์„ฑ์ด
00:39
"9 out of 10 women recommend this anti-aging cream."
11
39930
2449
์•ˆํ‹ฐ์—์ด์ง• ํฌ๋ฆผ์„ ์ถ”์ฒœํ•œ๋‹ค."๊ฐ™์€ ๊ฑธ ๋งํ•˜๋Š” ๊ฒŒ ์•„๋‹ˆ์—์š”.
00:42
I think a lot of us always roll our eyes at numbers like that.
12
42403
2972
๊ทธ๋Ÿฐ ์ˆซ์ž๋ฅผ ๋ณด๋ฉด ๋งŽ์€ ๋ถ„๋“ค์ด ๋ˆˆ์„ ๊ตด๋ฆฌ์‹œ์ฃ .
00:45
What's different now is people are questioning statistics like,
13
45399
2984
์š”์ƒˆ ์™€์„œ ๋‹ฌ๋ผ์ง„ ๊ฑด ์‚ฌ๋žŒ๋“ค์ด ์ด๋Ÿฐ ํ†ต๊ณ„์— ์˜๋ฌธ์„ ๊ฐ–๊ฒŒ ๋œ ๊ฒ๋‹ˆ๋‹ค.
00:48
"The US unemployment rate is five percent."
14
48407
2014
"๋ฏธ๊ตญ์˜ ์‹ค์—…๋ฅ ์€ 5%๋‹ค."
00:50
What makes this claim different is it doesn't come from a private company,
15
50445
3516
์ด ์ฃผ์žฅ์ด ํŠน๋ณ„ํ•œ ์ด์œ ๋Š” ์‚ฌ๊ธฐ์—…์ด ํ•˜๋Š” ๋ง์ด ์•„๋‹ˆ๋ผ
00:53
it comes from the government.
16
53985
1388
์ •๋ถ€๊ฐ€ ํ•œ ๋ง์ด๊ธฐ ๋•Œ๋ฌธ์ž…๋‹ˆ๋‹ค.
00:55
About 4 out of 10 Americans distrust the economic data
17
55397
3336
๋ฏธ๊ตญ์ธ 10๋ช… ์ค‘ 4๋ช…์ด ์ •๋ถ€์—์„œ ๋ณด๊ณ ํ•˜๋Š” ๊ฒฝ์ œ์  ๋ฐ์ดํ„ฐ๋ฅผ
00:58
that gets reported by government.
18
58757
1573
์‹ ๋ขฐํ•˜์ง€ ์•Š์Šต๋‹ˆ๋‹ค.
01:00
Among supporters of President Trump it's even higher;
19
60354
2491
์ด ๋น„์œจ์€ ํŠธ๋Ÿผํ”„ ๋Œ€ํ†ต๋ น ์ง€์ง€์ž๋“ค์˜ ๊ฒฝ์šฐ์—๋Š” ๋” ๋†’์Šต๋‹ˆ๋‹ค.
01:02
it's about 7 out of 10.
20
62869
1633
10๋ช… ์ค‘์— 7๋ช…์ด์—์š”.
01:04
I don't need to tell anyone here
21
64526
1804
์ œ๊ฐ€ ๊ตณ์ด ๋ง์”€๋“œ๋ฆฌ์ง€ ์•Š์•„๋„
01:06
that there are a lot of dividing lines in our society right now,
22
66354
3011
์ง€๊ธˆ ์‚ฌํšŒ์— ๋‚˜๋ˆ„์–ด์ง„ ์„ ๋“ค์ด ๋งŽ๋‹ค๋Š” ๊ฑด ๋‹ค๋“ค ์•Œ๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
01:09
and a lot of them start to make sense,
23
69389
1825
์ •๋ถ€์˜ ์ˆ˜์น˜์™€ ์‚ฌ๋žŒ๋“ค ๊ฐ„์˜ ๊ด€๊ณ„๋ฅผ
01:11
once you understand people's relationships with these government numbers.
24
71238
3687
์ดํ•ดํ•˜๊ณ ๋‚˜๋ฉด ๊ทธ ์„ ๋“ค์ด ๋งŽ์ด ๋ง์ด ๋˜๊ธฐ ์‹œ์ž‘ํ•ฉ๋‹ˆ๋‹ค.
01:14
On the one hand, there are those who say these statistics are crucial,
25
74949
3336
๋ฐ˜๋ฉด์— ํ†ต๊ณ„๊ฐ€ ๋งค์šฐ ์ค‘์š”ํ•˜๋‹ค๊ณ  ๋งํ•˜๋Š” ์‚ฌ๋žŒ๋“ค๋„ ์žˆ์Šต๋‹ˆ๋‹ค.
01:18
that we need them to make sense of society as a whole
26
78309
2630
์‚ฌํšŒ๋ฅผ ์ „์ฒด์ ์œผ๋กœ ์ดํ•ดํ•˜๋ ค๋ฉด ํ•„์š”ํ•˜๋‹ค๊ณ  ๋งํ•ฉ๋‹ˆ๋‹ค.
01:20
in order to move beyond emotional anecdotes
27
80963
2164
๊ฐ์ •์ ์ธ ์ง„์ˆ ๋“ค์„ ๋„˜์–ด
01:23
and measure progress in an [objective] way.
28
83151
2410
๋ฐœ์ „์„ ๊ฐ๊ด€์ ์œผ๋กœ ์ธก์ •ํ•˜๊ธฐ ์œ„ํ•ด์„œ์š”.
01:25
And then there are the others,
29
85585
1467
๊ทธ๋ฆฌ๊ณ  ๋˜ ๋‹ค๋ฅธ ์ง‘๋‹จ๋„ ์žˆ์Šต๋‹ˆ๋‹ค.
01:27
who say that these statistics are elitist,
30
87076
2156
ํ†ต๊ณ„๋Š” ์—˜๋ฆฌํŠธ์ฃผ์˜์ ์ด๋ฉฐ
01:29
maybe even rigged;
31
89256
1208
์กฐ์ž‘๋๋‹ค๊ณ ๊นŒ์ง€๋„ ๋งํ•˜๊ณ 
01:30
they don't make sense and they don't really reflect
32
90488
2394
๋ง๋„ ์•ˆ ๋˜๋ฉฐ ์‚ฌ๋žŒ๋“ค์˜ ์ผ์ƒ์—์„œ ์ผ์–ด๋‚˜๋Š”
01:32
what's happening in people's everyday lives.
33
92906
2296
์ผ๋“ค์„ ๋ฐ˜์˜ํ•˜์ง€ ์•Š๋Š”๋‹ค๊ณ  ํ•ฉ๋‹ˆ๋‹ค.
01:35
It kind of feels like that second group is winning the argument right now.
34
95226
3487
๋‘ ๋ฒˆ์งธ ๋ถ€๋ฅ˜์˜ ์‚ฌ๋žŒ๋“ค์˜ ์ฃผ์žฅ์ด ์ด๊ธฐ๊ณ  ์žˆ๋Š” ๊ฒƒ ๊ฐ™๊ธด ํ•ด์š”.
01:38
We're living in a world of alternative facts,
35
98737
2108
์šฐ๋ฆฐ ๋Œ€์•ˆ์  ์‚ฌ์‹ค์˜ ์„ธ์ƒ์— ์‚ด๊ณ  ์žˆ๊ณ 
01:40
where people don't find statistics this kind of common ground,
36
100869
2935
์‚ฌ๋žŒ๋“ค์€ ํ†ต๊ณ„๋ฅผ ๊ณต๋™ ์ „์ œ๋‚˜ ํ† ๋ก ์˜ ์‹œ์ž‘์ ์œผ๋กœ
01:43
this starting point for debate.
37
103828
1636
์—ฌ๊ธฐ์ง€ ์•Š์Šต๋‹ˆ๋‹ค.
01:45
This is a problem.
38
105488
1286
์ด๊ฑด ๋ฌธ์ œ์ž…๋‹ˆ๋‹ค.
01:46
There are actually moves in the US right now
39
106798
2067
์‚ฌ์‹ค ์ผ๋ถ€ ์ •๋ถ€ ํ†ต๊ณ„๋ฅผ ์•„์˜ˆ ์—†์• ์ž๋Š” ์›€์ง์ž„์ด
01:48
to get rid of some government statistics altogether.
40
108889
2861
์ง€๊ธˆ ์กด์žฌํ•ฉ๋‹ˆ๋‹ค.
01:51
Right now there's a bill in congress about measuring racial inequality.
41
111774
3387
์ง€๊ธˆ ์˜ํšŒ์— ์ธ์ข… ์ฐจ๋ณ„์„ ์ธก์ •ํ•˜๋Š” ๊ฒƒ์— ๋Œ€ํ•œ ๋ฒ•์•ˆ์ด ์žˆ์Šต๋‹ˆ๋‹ค.
01:55
The draft law says that government money should not be used
42
115185
2801
์ดˆ์•ˆ์— ๋”ฐ๋ฅด๋ฉด ๊ตญ๊ณ ๊ฐ€ ์ธ์ข…์ฐจ๋ณ„์— ๊ด€ํ•œ ๋ฐ์ดํ„ฐ๋ฅผ ์ˆ˜์ง‘ํ•˜๋Š” ๋ฐ
01:58
to collect data on racial segregation.
43
118010
1902
์“ฐ์ด๋ฉด ์•ˆ ๋œ๋‹ค๊ณ  ํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
01:59
This is a total disaster.
44
119936
1885
์ •๋ง ๋”์ฐํ•œ ์ผ์ด์—์š”.
02:01
If we don't have this data,
45
121845
1748
๋ฐ์ดํ„ฐ ์—†์ด ์–ด๋–ป๊ฒŒ ์ฐจ๋ณ„์„ ๊ด€์ฐฐํ•  ์ˆ˜ ์žˆ์ฃ ?
02:03
how can we observe discrimination,
46
123617
1778
02:05
let alone fix it?
47
125419
1278
๊ฒŒ๋‹ค๊ฐ€ ์–ด๋–ป๊ฒŒ ์‹œ์ •ํ•˜์ฃ ?
02:06
In other words:
48
126721
1188
๋‹ค์‹œ ๋งํ•˜๋ฉด
02:07
How can a government create fair policies
49
127933
2059
์ •๋ถ€๊ฐ€ ํ˜„์žฌ์˜ ๋ถˆ๊ณต์ •์˜ ์ •๋„๋ฅผ
02:10
if they can't measure current levels of unfairness?
50
130016
2771
์ธก์ •ํ•  ์ˆ˜ ์—†์œผ๋ฉด ์–ด๋–ป๊ฒŒ ๊ณต์ •ํ•œ ์ •์ฑ…์„ ๋งŒ๋“ค ์ˆ˜ ์žˆ์ฃ ?
02:12
This isn't just about discrimination,
51
132811
1794
๋น„๋‹จ ์ฐจ๋ณ„๋งŒ ๋ฌธ์ œ์ธ ๊ฒƒ์ด ์•„๋‹™๋‹ˆ๋‹ค.
02:14
it's everything -- think about it.
52
134629
1670
๋ชจ๋“  ๊ฒŒ ๋ฌธ์ œ์˜ˆ์š”. ์ƒ๊ฐํ•ด๋ณด์„ธ์š”.
02:16
How can we legislate on health care
53
136323
1690
๋ณด๊ฑด๊ณผ ๊ฑด๊ฐ•์— ๋Œ€ํ•œ ์–‘์งˆ์˜ ๋ฐ์ดํ„ฐ๊ฐ€ ์—†์œผ๋ฉด
02:18
if we don't have good data on health or poverty?
54
138037
2271
์–ด๋–ป๊ฒŒ ์˜๋ฃŒ๋ณดํ—˜ ๋ฒ•์„ ์ œ์ •ํ•  ์ˆ˜ ์žˆ์ฃ ?
02:20
How can we have public debate about immigration
55
140332
2198
์–ผ๋งˆ๋‚˜ ๋งŽ์€ ์‚ฌ๋žŒ๋“ค์ด ์ด ๋‚˜๋ผ์— ๋“ค์–ด์˜ค๊ณ 
02:22
if we can't at least agree
56
142554
1250
๋‚˜๊ฐ€๋Š”์ง€์— ๋Œ€ํ•ด์„œ๋„
02:23
on how many people are entering and leaving the country?
57
143828
2643
์˜๊ฒฌ์ด ์ผ์น˜ํ•˜์ง€ ์•Š๋Š”๋ฐ ์–ด๋–ป๊ฒŒ ๊ณต๊ฐœ ํ† ๋ก ์ด ์ด๋ฃจ์–ด์งˆ ์ˆ˜ ์žˆ์ฃ ?
02:26
Statistics come from the state; that's where they got their name.
58
146495
3058
ํ†ต๊ณ„๋Š” ๊ตญ๊ฐ€์—์„œ๋ถ€ํ„ฐ ๋‚˜์˜ต๋‹ˆ๋‹ค. ๊ทธ๊ฒŒ ํ†ต๊ณ„์˜ ์–ด์›์ด์—์š”.
02:29
The point was to better measure the population
59
149577
2157
๊ตญ๋ฏผ์„ ๋” ์ž˜ ์„ฌ๊ธฐ๊ธฐ ์œ„ํ•ด ๋” ์ž˜ ์ธก์ •ํ•˜๋Š” ๊ฒƒ์ด
02:31
in order to better serve it.
60
151758
1357
๋ชฉ์ ์ด์—ˆ์Šต๋‹ˆ๋‹ค.
02:33
So we need these government numbers,
61
153139
1725
๊ทธ๋ž˜์„œ ์ •๋ถ€์˜ ์ˆ˜์น˜๊ฐ€ ํ•„์š”ํ•ฉ๋‹ˆ๋‹ค.
02:34
but we also have to move beyond either blindly accepting
62
154888
2647
ํ•˜์ง€๋งŒ ๋งน๋ชฉ์ ์œผ๋กœ ๋ฐ›์•„๋“ค์ด๊ฑฐ๋‚˜ ๋ฐ˜๋Œ€ํ•˜๋Š” ๊ฑด
02:37
or blindly rejecting them.
63
157559
1268
๋„˜์–ด์„œ์•ผ ํ•ฉ๋‹ˆ๋‹ค.
02:38
We need to learn the skills to be able to spot bad statistics.
64
158851
2997
์ž˜๋ชป๋œ ํ†ต๊ณ„๋ฅผ ์žก์•„๋‚ด๋Š” ๋ฐฉ๋ฒ•์„ ์•Œ์•„์•ผ ํ•ฉ๋‹ˆ๋‹ค.
02:41
I started to learn some of these
65
161872
1528
์ €๋Š” ๊ทธ ์ค‘ ์ผ๋ถ€๋ฅผ
02:43
when I was working in a statistical department
66
163424
2166
UN์‚ฐํ•˜์˜ ํ†ต๊ณ„๋ถ€์„œ์—์„œ ์ผํ•˜๋ฉด์„œ ๋ฐฐ์› ์Šต๋‹ˆ๋‹ค.
02:45
that's part of the United Nations.
67
165614
1643
02:47
Our job was to find out how many Iraqis had been forced from their homes
68
167281
3406
์ €ํฌ ์ผ์€ ์ด๋ผํฌ ์ „์Ÿ์œผ๋กœ ์–ผ๋งˆ๋‚˜ ๋งŽ์€ ์ด๋ผํฌ์ธ์ด ํ”ผ๋‚œ์„ ๊ฐ”๋Š”์ง€์™€
02:50
as a result of the war,
69
170711
1158
๋ฌด์—‡์„ ํ•„์š”๋กœ ํ•˜๋Š”์ง€๋ฅผ
02:51
and what they needed.
70
171893
1158
์•Œ์•„๋‚ด๋Š” ๊ฒƒ์ด์—ˆ์Šต๋‹ˆ๋‹ค.
02:53
It was really important work, but it was also incredibly difficult.
71
173075
3178
์ •๋ง ์ค‘์š”ํ•œ ์ผ์ด์—ˆ๋Š”๋ฐ ๋™์‹œ์— ๋งค์šฐ ์–ด๋ ค์šด ์ผ์ด์—ˆ์Šต๋‹ˆ๋‹ค.
02:56
Every single day, we were making decisions
72
176277
2018
๋งค์ผ ์šฐ๋ฆฌ๋Š” ์ˆ˜์น˜์˜ ์ •ํ™•๋„์— ์˜ํ–ฅ์„ ๋ฏธ์น˜๋Š” ๊ฒฐ์ •๋“ค์„ ๋‚ด๋ ธ์Šต๋‹ˆ๋‹ค.
02:58
that affected the accuracy of our numbers --
73
178319
2157
03:00
decisions like which parts of the country we should go to,
74
180500
2744
์ด๋ผํฌ์˜ ์–ด๋Š ์ง€์—ญ์„ ๊ฐ€์•ผ ํ• ์ง€
03:03
who we should speak to,
75
183268
1156
๋ˆ„๊ตฌ์™€ ์–˜๊ธฐํ• ์ง€
03:04
which questions we should ask.
76
184448
1568
์–ด๋–ค ์งˆ๋ฌธ์„ ๋ฌผ์–ด์•ผํ• ์ง€๋ฅผ์š”.
03:06
And I started to feel really disillusioned with our work,
77
186040
2680
๊ทธ๋Ÿฐ๋ฐ ์ €๋Š” ์šฐ๋ฆฌ์˜ ์ผ์— ํ™˜๋ฉธ์„ ๋Š๋ผ๊ธฐ ์‹œ์ž‘ํ–ˆ์Šต๋‹ˆ๋‹ค.
03:08
because we thought we were doing a really good job,
78
188744
2518
์šฐ๋ฆฌ๋Š” ์ผ์„ ์ž˜ํ•˜๊ณ  ์žˆ๋‹ค๊ณ  ์ƒ๊ฐํ–ˆ์—ˆ์–ด์š”.
03:11
but the one group of people who could really tell us were the Iraqis,
79
191286
3278
๊ทธ๋Ÿฐ๋ฐ ๊ทธ๊ฑธ ์ •๋ง ํ™•์ธ์‹œ์ผœ์ค„ ์ˆ˜ ์žˆ๋Š” ์‚ฌ๋žŒ์€ ์ด๋ผํฌ์ธ๋“ค ๋ฟ์ธ๋ฐ
03:14
and they rarely got the chance to find our analysis, let alone question it.
80
194588
3540
๊ทธ๋“ค์€ ์šฐ๋ฆฌ ๋ถ„์„์— ์˜๋ฌธ์„ ์ œ๊ธฐํ•˜๋Š” ๊ฑด ๊ณ ์‚ฌํ•˜๊ณ  ๋ณผ ๊ธฐํšŒ๋„ ๊ฑฐ์˜ ์—†์—ˆ์–ด์š”.
03:18
So I started to feel really determined
81
198152
1831
๊ทธ๋ž˜์„œ ์ €๋Š” ์ˆ˜์น˜๋ฅผ ๋” ์ •ํ™•ํ•˜๊ฒŒ ๋งŒ๋“ค์–ด ์ค„ ์œ ์ผํ•œ ๋ฐฉ๋ฒ•์ด
03:20
that the one way to make numbers more accurate
82
200007
2311
03:22
is to have as many people as possible be able to question them.
83
202342
3053
์ตœ๋Œ€ํ•œ ๋งŽ์€ ์‚ฌ๋žŒ๋“ค์ด ์˜๋ฌธ์„ ์ œ๊ธฐํ•˜๊ฒŒ ํ•˜๋Š” ๊ฑฐ๋ผ๊ณ  ์ƒ๊ฐํ•˜๊ฒŒ ๋์–ด์š”.
03:25
So I became a data journalist.
84
205419
1434
๊ทธ๋ž˜์„œ ์ €๋Š” ๋ฐ์ดํ„ฐ ๊ธฐ์ž๊ฐ€ ๋์Šต๋‹ˆ๋‹ค.
03:26
My job is finding these data sets and sharing them with the public.
85
206877
3904
์ œ ์ผ์€ ๋ฐ์ดํ„ฐ ์ง‘ํ•ฉ๋“ค์„ ์ฐพ์•„ ๋Œ€์ค‘์—๊ฒŒ ๊ณต์œ ํ•˜๋Š” ๊ฒƒ์ž…๋‹ˆ๋‹ค.
03:30
Anyone can do this, you don't have to be a geek or a nerd.
86
210805
3173
๊ณต๋ถ€๋ฒŒ๋ ˆ๋‚˜ ๊ดด์งœ๊ฐ€ ์•„๋‹ˆ์–ด๋„ ๋ˆ„๊ตฌ๋‚˜ ํ•  ์ˆ˜ ์žˆ๋Š” ์ผ์ด์—์š”.
03:34
You can ignore those words; they're used by people
87
214002
2355
์ด ๋‹จ์–ด๋“ค์€ ๋ฌด์‹œํ•˜์„ธ์š”. ๊ฒธ์†ํ•œ ์ฒ™ ํ•˜๋ฉด์„œ
03:36
trying to say they're smart while pretending they're humble.
88
216381
2822
์ž๊ธฐ๊ฐ€ ๋˜‘๋˜‘ํ•˜๋‹ค๋Š” ๊ฑธ ๋งํ•˜๋ ค๋Š” ์‚ฌ๋žŒ๋“ค์ด ์“ฐ๋Š” ๋‹จ์–ด๋“ค์ด์—์š”.
03:39
Absolutely anyone can do this.
89
219227
1589
์ •๋ง ๋ˆ„๊ตฌ๋‚˜ ํ•  ์ˆ˜ ์žˆ์–ด์š”.
03:40
I want to give you guys three questions
90
220840
2067
์ž˜๋ชป๋œ ํ†ต๊ณ„๋ฅผ ์žก์•„๋‚ด๋Š” ๊ฑธ ๋„์™€์ฃผ๋Š”
03:42
that will help you be able to spot some bad statistics.
91
222931
3005
์„ธ ๊ฐ€์ง€ ์งˆ๋ฌธ์„ ์—ฌ๋Ÿฌ๋ถ„๊ป˜ ๋“œ๋ฆฌ๊ณ  ์‹ถ์–ด์š”.
03:45
So, question number one is: Can you see uncertainty?
92
225960
3507
์ฒซ ๋ฒˆ์งธ ์งˆ๋ฌธ, ๋ถˆํ™•์‹ค์„ฑ์ด ๋ณด์ด์‹œ๋‚˜์š”?
03:49
One of things that's really changed people's relationship with numbers,
93
229491
3364
์‚ฌ๋žŒ๊ณผ ์ˆซ์ž์˜ ๊ด€๊ณ„์™€, ์‚ฌ๋žŒ๋“ค์˜ ๋ฏธ๋””์–ด์— ๋Œ€ํ•œ ์‹ ๋ขฐ๋ฅผ
03:52
and even their trust in the media,
94
232879
1641
๋ฐ”๊พธ์–ด๋†“์€ ๊ฒƒ ์ค‘ ํ•˜๋‚˜๋Š”
03:54
has been the use of political polls.
95
234544
2258
์ •์น˜ ๋ถ„์•ผ์˜ ์—ฌ๋ก ์กฐ์‚ฌ์ž…๋‹ˆ๋‹ค.
03:56
I personally have a lot of issues with political polls
96
236826
2538
์ €๋Š” ๊ฐœ์ธ์ ์œผ๋กœ ์—ฌ๋ก ์กฐ์‚ฌ์— ๋ถˆ๋งŒ์ด ๋งŽ์•„์š”.
03:59
because I think the role of journalists is actually to report the facts
97
239388
3376
๊ธฐ์ž์˜ ์—ญํ• ์€ ์‚ฌ์‹ค์„ ๋ณด๋„ํ•˜๋Š” ๊ฑฐ์ง€ ์˜ˆ์ธกํ•˜๋Š” ๊ฒŒ ์•„๋‹ˆ๋ผ๊ณ  ์ƒ๊ฐํ•˜๊ฑฐ๋“ ์š”.
04:02
and not attempt to predict them,
98
242788
1553
04:04
especially when those predictions can actually damage democracy
99
244365
2996
ํŠนํžˆ๋‚˜ ๊ทธ ์˜ˆ์ธก๋“ค์ด ์‚ฌ๋žŒ๋“ค์—๊ฒŒ ์ด๋Ÿฐ ์‹ ํ˜ธ๋ฅผ ์ฃผ์–ด
๋ฏผ์ฃผ์ฃผ์˜๋ฅผ ํ›ผ์†ํ•  ์ˆ˜ ์žˆ๋Š” ๊ฒฝ์šฐ์—๋Š”์š”.
04:07
by signaling to people: don't bother to vote for that guy,
100
247385
2732
"์ € ์‚ฌ๋žŒํ•œํ…Œ ํˆฌํ‘œํ•  ํ•„์š” ์—†์–ด. ๊ฐ€๋ง์ด ์—†๊ฑฐ๋“ ."
04:10
he doesn't have a chance.
101
250141
1205
04:11
Let's set that aside for now and talk about the accuracy of this endeavor.
102
251370
3654
ํ•˜์ง€๋งŒ ๊ทธ๊ฑด ์ œ์ณ๋‘๊ณ  ์—ฌ๋ก ์กฐ์‚ฌ์˜ ์ •ํ™•์„ฑ์— ๋Œ€ํ•ด ์–˜๊ธฐํ•ด๋ด…์‹œ๋‹ค.
04:15
Based on national elections in the UK, Italy, Israel
103
255048
4608
์˜๊ตญ, ์ดํƒˆ๋ฆฌ์•„, ์ด์Šค๋ผ์—˜์˜ ์ด์„ ๊ณผ
04:19
and of course, the most recent US presidential election,
104
259680
2764
๊ฐ€์žฅ ์ตœ๊ทผ์— ์žˆ์—ˆ๋˜ ๋ฏธ๊ตญ ๋Œ€์„ ์— ๊ธฐ๋ฐ˜ํ•ด์„œ ๋ณผ ๋•Œ
04:22
using polls to predict electoral outcomes
105
262468
2137
์„ ๊ฑฐ์˜ ๊ฒฐ๊ณผ๋ฅผ ์—ฌ๋ก ์กฐ์‚ฌ๋กœ ์˜ˆ์ธกํ•˜๋Š” ๊ฑด
04:24
is about as accurate as using the moon to predict hospital admissions.
106
264629
3812
๋‹ฌ๋กœ ๋ณ‘์›์˜ ์ž…์›์ž ์ˆ˜๋ฅผ ์ ์น˜๋Š” ๊ฒƒ๋งŒํผ์ด๋‚˜ ๋ถ€์ •ํ™•ํ•ฉ๋‹ˆ๋‹ค.
04:28
No, seriously, I used actual data from an academic study to draw this.
107
268465
4200
์•„๋‹ˆ ์ •๋ง ์ œ๊ฐ€ ํ•™์ˆ  ์—ฐ๊ตฌ์˜ ๋ฐ์ดํ„ฐ๋กœ ๋„์ถœํ•œ ๊ฒฐ๋ก ์ด์—์š”.
04:32
There are a lot of reasons why polling has become so inaccurate.
108
272689
3727
์—ฌ๋ก ์กฐ์‚ฌ๊ฐ€ ๋ถ€์ •ํ™•ํ•ด์ง„ ๋ฐ์—๋Š” ๋งŽ์€ ์ด์œ ๊ฐ€ ์žˆ์Šต๋‹ˆ๋‹ค.
04:36
Our societies have become really diverse,
109
276440
1970
์šฐ๋ฆฌ ์‚ฌํšŒ๊ฐ€ ๋งค์šฐ ๋‹ค์–‘ํ•ด์ ธ์„œ
04:38
which makes it difficult for pollsters to get a really nice representative sample
110
278434
3821
์—ฌ๋ก ์กฐ์‚ฌ์›๋“ค์ด ์—ฌ๋ก  ์กฐ์‚ฌ์˜ ๋ชจ์ง‘๋‹จ์—์„œ ์ •๋ง๋กœ ๋Œ€ํ‘œ์„ฑ ์žˆ๋Š” ํ‘œ๋ณธ์„
04:42
of the population for their polls.
111
282279
1627
์–ป๊ธฐ๊ฐ€ ๋งค์šฐ ํž˜๋“ค์–ด์กŒ์–ด์š”.
04:43
People are really reluctant to answer their phones to pollsters,
112
283930
3006
์‚ฌ๋žŒ๋“ค์€ ์—ฌ๋ก ์กฐ์‚ฌ์›๋“ค์˜ ์ „ํ™”๋ฅผ ๋ฐ›๊ธฐ ๊บผ๋ คํ•˜๊ณ 
04:46
and also, shockingly enough, people might lie.
113
286960
2276
๋†€๋ž๊ฒŒ๋„ ๊ฑฐ์ง“์œผ๋กœ ๋‹ตํ•  ์ˆ˜๋„ ์žˆ์Šต๋‹ˆ๋‹ค.
04:49
But you wouldn't necessarily know that to look at the media.
114
289260
2811
ํ•˜์ง€๋งŒ ์‚ฌ๋žŒ๋“ค์€ ๋ณด๋„์ž๋ฃŒ๋ฅผ ๋ณผ ๋•Œ ๊ทธ๊ฑธ ์˜์‹ํ•˜์ง„ ์•Š์ฃ .
04:52
For one thing, the probability of a Hillary Clinton win
115
292095
2761
ํž๋Ÿฌ๋ฆฌ ํด๋ฆฐํ„ด์ด ์šฐ์Šนํ•  ํ™•๋ฅ ์€
04:54
was communicated with decimal places.
116
294880
2791
์†Œ์ˆ˜์ ๊นŒ์ง€ ๊ณ„์‚ฐ๋์—ˆ์–ด์š”.
04:57
We don't use decimal places to describe the temperature.
117
297695
2621
์†Œ์ˆ˜์ ์€ ๊ธฐ์˜จ์„ ๋‚˜ํƒ€๋‚ผ ๋•Œ๋„ ์•ˆ ์จ์š”.
05:00
How on earth can predicting the behavior of 230 million voters in this country
118
300340
4228
๊ทธ๋Ÿฐ๋ฐ ์–ด๋–ป๊ฒŒ ๋ฏธ๊ตญ์˜ 2์–ต3์ฒœ๋งŒ ์œ ๊ถŒ์ž์˜ ํ–‰๋™์„ ์˜ˆ์ธกํ•˜๋Š” ๊ฒŒ
05:04
be that precise?
119
304592
1829
๊ทธ๋ ‡๊ฒŒ ์ •ํ™•ํ•  ์ˆ˜ ์žˆ์ฃ ?
05:06
And then there were those sleek charts.
120
306445
2002
๋ฒˆ์ง€๋ฅด๋ฅดํ•œ ๋„ํ‘œ๋„ ์žˆ์—ˆ์ฃ .
05:08
See, a lot of data visualizations will overstate certainty, and it works --
121
308471
3973
๋ฐ์ดํ„ฐ๋ฅผ ์‹œ๊ฐํ™”ํ•œ ๋„ํ‘œ๋“ค์€ ๋งŽ์ด๋“ค ํ™•์‹ค์„ฑ์„ ๊ณผ์žฅํ•ด์š”. ํšจ๊ณผ๋„ ์žˆ๊ณ ์š”.
05:12
these charts can numb our brains to criticism.
122
312468
2620
์ฐจํŠธ๋“ค์€ ๋น„ํŒ์„ ๋ฌด๋””๊ฒŒ ํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
05:15
When you hear a statistic, you might feel skeptical.
123
315112
2558
ํ†ต๊ณ„๋ฅผ ๋“ค์œผ๋ฉด ์˜์‹ฌ์„ ํ’ˆ์„ ์ˆ˜๋„ ์žˆ์ง€๋งŒ
05:17
As soon as it's buried in a chart,
124
317694
1635
์ฐจํŠธ๋กœ ๋‚˜ํƒ€๋‚ด์–ด์ง€๋Š” ์ˆœ๊ฐ„
05:19
it feels like some kind of objective science,
125
319353
2129
๊ฐ๊ด€์ ์ธ ๊ณผํ•™๊ฐ™์ด ๋Š๊ปด์ง‘๋‹ˆ๋‹ค.
05:21
and it's not.
126
321506
1249
๊ทธ๋ ‡์ง€ ์•Š์€๋ฐ๋„์š”.
05:22
So I was trying to find ways to better communicate this to people,
127
322779
3103
๊ทธ๋ž˜์„œ ์ €๋Š” ์ด ์ด์•ผ๊ธฐ๋ฅผ ์‚ฌ๋žŒ๋“ค์—๊ฒŒ ๋” ์ž˜ ์ „๋‹ฌํ•  ์ˆ˜ ์žˆ๊ณ 
05:25
to show people the uncertainty in our numbers.
128
325906
2504
์ˆซ์ž์˜ ๋ถˆํ™•์‹ค์„ฑ์„ ๋ณด์—ฌ์ค„ ์ˆ˜ ์žˆ๋Š” ๋ฐฉ๋ฒ•์„ ์ฐพ์œผ๋ ค ํ–ˆ์–ด์š”.
05:28
What I did was I started taking real data sets,
129
328434
2246
๊ทธ๋ž˜์„œ ์ €๋Š” ์‹ค์ œ ๋ฐ์ดํ„ฐ ๋ชจ์Œ์„ ๊ฐ–๋‹ค๊ฐ€
05:30
and turning them into hand-drawn visualizations,
130
330704
2652
์†์œผ๋กœ ๊ทธ๋ฆฐ ๋„ํ‘œ๋กœ ๋ณ€ํ™˜์‹œ์ผฐ์–ด์š”.
05:33
so that people can see how imprecise the data is;
131
333380
2672
์‚ฌ๋žŒ๋“ค์ด ๋ฐ์ดํ„ฐ๊ฐ€ ์–ผ๋งˆ๋‚˜ ๋ถ€์ •ํ™•ํ•œ์ง€ ๋ณผ ์ˆ˜ ์žˆ๊ฒŒ์š”.
05:36
so people can see that a human did this,
132
336076
1996
์ธ๊ฐ„์ด ์ด๊ฑธ ๊ทธ๋ ธ๊ณ 
05:38
a human found the data and visualized it.
133
338096
1972
์ธ๊ฐ„์ด ๋ฐ์ดํ„ฐ๋ฅผ ์ฐพ๊ณ  ์‹œ๊ฐํ™”ํ–ˆ๋‹ค๊ณ ์š”.
05:40
For example, instead of finding out the probability
134
340092
2672
์ผ๋ก€๋กœ ๊ฐ๊ธฐ์— ๊ฑธ๋ฆด ์›”๋ณ„ ํ™•๋ฅ ์„ ๋ณด๋Š” ๊ฒƒ ๋Œ€์‹ ์—
05:42
of getting the flu in any given month,
135
342788
2126
05:44
you can see the rough distribution of flu season.
136
344938
2792
๋…๊ฐ์ด ์œ ํ–‰ํ•˜๋Š” ์ฒ ์ด ์–ธ์  ์ง€๋ฅผ ๋Œ€๋žต์ ์œผ๋กœ ์•Œ ์ˆ˜ ์žˆ์ฃ .
05:47
This is --
137
347754
1167
์ด๊ฒƒ์€...
05:48
(Laughter)
138
348945
1018
(์›ƒ์Œ)
05:49
a bad shot to show in February.
139
349987
1486
2์›”์— ๋ณด์—ฌ์ฃผ๊ธฐ ๋‚˜์œ ์ด๋ฏธ์ง€์ฃ .
05:51
But it's also more responsible data visualization,
140
351497
2455
ํ•˜์ง€๋งŒ ๋™์‹œ์— ๋” ์ฑ…์ž„๊ฐ์žˆ๋Š” ๋„ํ‘œ์˜ˆ์š”.
05:53
because if you were to show the exact probabilities,
141
353976
2455
์ •ํ™•ํ•œ ํ™•๋ฅ ๋กœ ๋ณด์—ฌ์ฃผ๋ฉด
05:56
maybe that would encourage people to get their flu jabs
142
356455
2592
์‚ฌ๋žŒ๋“ค์ด ์ž˜๋ชป๋œ ์‹œ๊ธฐ์— ๋…๊ฐ ์˜ˆ๋ฐฉ์ฃผ์‚ฌ๋ฅผ ๋งž๋„๋ก
05:59
at the wrong time.
143
359071
1456
์žฅ๋ คํ•  ์ˆ˜ ์žˆ์œผ๋‹ˆ๊นŒ์š”.
06:00
The point of these shaky lines
144
360983
1693
๊ตฌ๋ถˆ๊ตฌ๋ถˆํ•œ ์„ ์œผ๋กœ ๊ทธ๋ฆฐ ์ด์œ ๋Š”
06:02
is so that people remember these imprecisions,
145
362700
2911
์‚ฌ๋žŒ๋“ค์ด ์ด ํ†ต๊ณ„๊ฐ€ ์ •ํ™•ํ•˜์ง„ ์•Š๋‹ค๋Š” ๊ฑธ ์•Œ๊ฒŒ ํ•˜๊ณ 
06:05
but also so they don't necessarily walk away with a specific number,
146
365635
3227
ํŠน์ • ์ˆซ์ž๊ฐ€ ์•„๋‹Œ ์ค‘์š”ํ•œ ์‚ฌ์‹ค์„ ๊ธฐ์–ตํ•˜๋„๋ก
06:08
but they can remember important facts.
147
368886
1866
ํ•˜๊ธฐ ์œ„ํ•ด์„œ์ž…๋‹ˆ๋‹ค.
06:10
Facts like injustice and inequality leave a huge mark on our lives.
148
370776
4024
๋ถˆ์˜์™€ ๋ถˆํ‰๋“ฑ๊ฐ™์€ ์‚ฌ์‹ค๋“ค์€ ์šฐ๋ฆฌ ์ธ์ƒ์— ํฐ ์ž๊ตญ์„ ๋‚จ๊น๋‹ˆ๋‹ค.
06:14
Facts like Black Americans and Native Americans have shorter life expectancies
149
374824
4189
ํ‘์ธ ๋ฏธ๊ตญ์ธ๊ณผ ๋ถ๋ฏธ ์›์ฃผ๋ฏผ๋“ค์ด ๋‹ค๋ฅธ ์ธ์ข…๋ณด๋‹ค
06:19
than those of other races,
150
379037
1400
์ˆ˜๋ช…์ด ๋” ์งง์œผ๋ฉฐ,
06:20
and that isn't changing anytime soon.
151
380461
2138
์ด๊ฑด ๋น ๋ฅธ ์‹œ์ผ ๋‚ด์— ๋ณ€ํ•˜์ง€ ์•Š์„ ๊ฑฐ๋ผ๋Š” ์‚ฌ์‹ค๋„์š”.
06:22
Facts like prisoners in the US can be kept in solitary confinement cells
152
382623
3901
๋ฏธ๊ตญ์˜ ์ฃ„์ˆ˜๋“ค์ด ์ฃผ์ฐจ์žฅ์˜ ์ผ๋ฐ˜์ ์ธ ํฌ๊ธฐ๋ณด๋‹ค
06:26
that are smaller than the size of an average parking space.
153
386548
3342
๋” ์ž‘์€ ๋…๋ฐฉ์— ์ˆ˜๊ฐ๋  ์ˆ˜ ์žˆ๋‹ค๋Š” ์‚ฌ์‹ค๋„์š”.
06:30
The point of these visualizations is also to remind people
154
390355
3335
์ด ๋„ํ‘œ๋“ค์˜ ๋˜ ๋‹ค๋ฅธ ์š”์ ์€ ์‚ฌ๋žŒ๋“ค์—๊ฒŒ ๋งค์šฐ ์ค‘์š”ํ•œ
06:33
of some really important statistical concepts,
155
393714
2350
๋ช‡ ๊ฐ€์ง€ ํ†ต๊ณ„์  ๊ฐœ๋…์„ ์•Œ๋ ค์ฃผ๊ธฐ ์œ„ํ•ด์„œ์ž…๋‹ˆ๋‹ค.
06:36
concepts like averages.
156
396088
1636
ํ‰๊ท ๊ฐ™์€ ๊ฐœ๋…์ด์š”.
06:37
So let's say you hear a claim like,
157
397748
1668
์ด๋Ÿฐ ์ฃผ์žฅ์„ ๋“ฃ๋Š”๋‹ค๊ณ  ์ƒ๊ฐํ•ด๋ณด์„ธ์š”.
06:39
"The average swimming pool in the US contains 6.23 fecal accidents."
158
399440
4434
"๋ฏธ๊ตญ์˜ ์ˆ˜์˜์žฅ์—๋Š” ํ‰๊ท ์ ์œผ๋กœ 6.23๊ฑด์˜ ๋ฐฐ์„ค๋ฌผ ์‚ฌ๊ณ ๊ฐ€ ์ผ์–ด๋‚œ๋‹ค."
06:43
That doesn't mean every single swimming pool in the country
159
403898
2797
์ด๊ฑด ๊ตญ๋‚ด์˜ ๋ชจ๋“  ์ˆ˜์˜์žฅ์— ์ •ํ™•ํžˆ 6.23๊ฐœ์˜ ๋˜ฅ์ด
06:46
contains exactly 6.23 turds.
160
406719
2194
๋“ค์–ด์žˆ๋‹ค๋Š” ๊ฑธ ์˜๋ฏธํ•˜๋Š” ๊ฒŒ ์•„๋‹™๋‹ˆ๋‹ค.
06:48
So in order to show that,
161
408937
1417
๊ทธ๊ฑธ ์ฆ๋ช…ํ•˜๊ธฐ ์œ„ํ•ด์„œ
06:50
I went back to the original data, which comes from the CDC,
162
410378
2841
์ €๋Š” ๋ฏธ๊ตญ ์งˆ๋ณ‘๊ด€๋ฆฌ๋ณธ๋ถ€ ์ถœ์ €์˜ 47๊ฐœ ์ˆ˜์˜์‹œ์„ค์„ ์กฐ์‚ฌํ•œ
06:53
who surveyed 47 swimming facilities.
163
413243
2065
๋ฐ์ดํ„ฐ ์›๋ณธ์œผ๋กœ ๋Œ์•„๊ฐ€์„œ
06:55
And I just spent one evening redistributing poop.
164
415332
2391
ํ•˜๋ฃป๋ฐค ๊ผฌ๋ฐ• ๋˜ฅ์„ ์žฌ๋ถ„๋ฐฐํ–ˆ์–ด์š”.
06:57
So you can kind of see how misleading averages can be.
165
417747
2682
ํ‰๊ท ์ด ์–ผ๋งˆ๋‚˜ ์‚ฌ๋žŒ๋“ค์„ ์˜ค๋„ํ•  ์ˆ˜ ์žˆ๋Š”์ง€ ๋ณผ ์ˆ˜ ์žˆ์ฃ .
07:00
(Laughter)
166
420453
1282
(์›ƒ์Œ)
07:01
OK, so the second question that you guys should be asking yourselves
167
421759
3901
์ž˜๋ชป๋œ ์ˆซ์ž๋ฅผ ๋ฐœ๊ฒฌํ•˜๊ธฐ ์œ„ํ•ด ์Šค์Šค๋กœ์—๊ฒŒ ๋ฌผ์–ด์•ผ ํ• 
07:05
to spot bad numbers is:
168
425684
1501
๋‘ ๋ฒˆ์งธ ์งˆ๋ฌธ์€ ์ด๊ฒ๋‹ˆ๋‹ค.
07:07
Can I see myself in the data?
169
427209
1967
๋ฐ์ดํ„ฐ ์†์—์„œ ๋‚˜๋ฅผ ๋ณผ ์ˆ˜ ์žˆ๋Š”๊ฐ€?
07:09
This question is also about averages in a way,
170
429200
2913
์–ด๋–ป๊ฒŒ ๋ณด๋ฉด ์ด ์งˆ๋ฌธ๋„ ํ‰๊ท ์— ๊ด€ํ•œ ๊ฑฐ์˜ˆ์š”.
07:12
because part of the reason why people are so frustrated
171
432137
2605
์‚ฌ๋žŒ๋“ค์ด ๊ตญ๊ฐ€์  ํ†ต๊ณ„์— ๋Œ€ํ•ด ๋ถˆ๋งŒ์„ ๋Š๋ผ๋Š” ์ด์œ  ์ค‘์˜ ํ•˜๋‚˜๊ฐ€
07:14
with these national statistics,
172
434766
1495
07:16
is they don't really tell the story of who's winning and who's losing
173
436285
3273
๊ตญ๊ฐ€ ์ •์ฑ…์œผ๋กœ ๋ˆ„๊ฐ€ ์ด๋“์„ ์–ป๊ณ  ์žˆ๊ณ  ๋ˆ„๊ฐ€ ์†ํ•ด๋ฅผ ๋ณด๊ณ  ์žˆ๋Š”์ง€ ์•Œ ์ˆ˜๊ฐ€
07:19
from national policy.
174
439582
1156
์—†๋‹ค๋Š” ๊ฒƒ์ด๋‹ˆ๊นŒ์š”.
07:20
It's easy to understand why people are frustrated with global averages
175
440762
3318
์‚ฌ๋žŒ๋“ค์ด ์ „์„ธ๊ณ„ ํ‰๊ท ์ด ์ž์‹ ์˜ ๊ฒฝํ—˜๊ณผ ๋งž์ง€ ์•Š์„ ๋•Œ
07:24
when they don't match up with their personal experiences.
176
444104
2679
์™œ ๋ถˆ๋งŒ์Šค๋Ÿฌ์›Œํ•˜๋Š”์ง€๋Š” ์‰ฝ๊ฒŒ ์ดํ•ด๋ฉ๋‹ˆ๋‹ค.
07:26
I wanted to show people the way data relates to their everyday lives.
177
446807
3263
์ €๋Š” ๋ฐ์ดํ„ฐ๊ฐ€ ์‚ฌ๋žŒ๋“ค์˜ ์ผ์ƒ์— ์–ด๋–ป๊ฒŒ ๊ด€๋ จ์žˆ๋Š”์ง€๋ฅผ ๋ณด์—ฌ์ฃผ๊ธฐ ์œ„ํ•ด
07:30
I started this advice column called "Dear Mona,"
178
450094
2246
"๋ชจ๋‚˜์—๊ฒŒ"๋ผ๋Š” ๊ณ ๋ฏผ ์ƒ๋‹ด๋ž€์„ ๋งŒ๋“ค์—ˆ์–ด์š”.
07:32
where people would write to me with questions and concerns
179
452364
2726
์‚ฌ๋žŒ๋“ค์ด ์ œ๊ฒŒ ์งˆ๋ฌธ๊ณผ ๊ฑฑ์ •์„ ์ ์–ด๋ณด๋‚ด๋ฉด
07:35
and I'd try to answer them with data.
180
455114
1784
์ €๋Š” ๋ฐ์ดํ„ฐ๋กœ ๋‹ต์„ ํ•ด์ฃผ์—ˆ์Šต๋‹ˆ๋‹ค.
07:36
People asked me anything.
181
456922
1200
์ œ๊ฒŒ ๋ญ๋“ ์ง€ ๋ฌผ์–ด๋ดค์–ด์š”.
07:38
questions like, "Is it normal to sleep in a separate bed to my wife?"
182
458146
3261
"์•„๋‚ด์™€ ๋‹ค๋ฅธ ์นจ๋Œ€์—์„œ ์ž๋Š” ๊ฒŒ ์ •์ƒ์ธ๊ฐ€์š”?"
07:41
"Do people regret their tattoos?"
183
461431
1591
"์‚ฌ๋žŒ๋“ค์€ ๋ฌธ์‹  ์ƒˆ๊ธด ๊ฑธ ํ›„ํšŒํ•˜๋‚˜์š”?"
07:43
"What does it mean to die of natural causes?"
184
463046
2164
"์ž์—ฐ์‚ฌํ–ˆ๋‹ค๋Š” ๊ฒŒ ๋ฌด์Šจ ๋œป์ด์ฃ ?"
07:45
All of these questions are great, because they make you think
185
465234
2966
๋‹ค ์ข‹์€ ์งˆ๋ฌธ๋“ค์ด์—์š”. ์ด ์ˆ˜์น˜๋“ค๊ณผ ์†Œํ†ตํ• 
07:48
about ways to find and communicate these numbers.
186
468224
2336
๋ฐฉ๋ฒ•์— ๋Œ€ํ•ด ์ƒ๊ฐํ•ด๋ณด๊ฒŒ ํ•˜๋‹ˆ๊นŒ์š”.
07:50
If someone asks you, "How much pee is a lot of pee?"
187
470584
2503
๋ˆ„๊ตฐ๊ฐ€๊ฐ€ "์–ผ๋งŒํผ์ด ์˜ค์คŒ์„ ๋งŽ์ด ์‹ธ๋Š” ๊ฑด๊ฐ€์š”?"๋ผ๊ณ  ๋ฌผ์œผ๋ฉด
07:53
which is a question that I got asked,
188
473111
2458
์‹ค์ œ๋กœ ์ œ๊ฐ€ ๋ฐ›์•˜๋˜ ์งˆ๋ฌธ์ธ๋ฐ
07:55
you really want to make sure that the visualization makes sense
189
475593
2980
๊ทธ๋ž˜ํ”„๊ฐ€ ์ตœ๋Œ€ํ•œ ๋งŽ์€ ์‚ฌ๋žŒ๋“ค์—๊ฒŒ ์ดํ•ด๋˜๋„๋ก ๋…ธ๋ ฅํ•ด์•ผ ํ•ฉ๋‹ˆ๋‹ค.
07:58
to as many people as possible.
190
478597
1747
08:00
These numbers aren't unavailable.
191
480368
1575
์ด ์ˆ˜์น˜๋“ค์€ ์ฐพ์„ ์ˆ˜ ์žˆ์–ด์š”.
08:01
Sometimes they're just buried in the appendix of an academic study.
192
481967
3507
๋•Œ๋กœ๋Š” ํ•™์ˆ  ์—ฐ๊ตฌ์˜ ๋ถ€๋ก์— ๋ฌปํ˜€์žˆ์ฃ .
08:05
And they're certainly not inscrutable;
193
485498
1839
๊ทธ๋ฆฌ๊ณ  ์ ˆ๋Œ€ ๋ถˆ๊ฐ€ํ•ดํ•˜์ง€ ์•Š์•„์š”.
08:07
if you really wanted to test these numbers on urination volume,
194
487361
2975
์ด ์ˆ˜์น˜๋ฅผ ์†Œ๋ณ€์˜ ์–‘์— ํ…Œ์ŠคํŠธํ•ด๋ณด๊ณ  ์‹ถ์œผ๋ฉด
08:10
you could grab a bottle and try it for yourself.
195
490360
2257
๊ทธ๋ƒฅ ๋ณ‘์„ ๊ฐ€์ ธ๋‹ค ์ง์ ‘ ํ•ด๋ณด์„ธ์š”.
08:12
(Laughter)
196
492641
1008
(์›ƒ์Œ)
08:13
The point of this isn't necessarily
197
493673
1694
์ด๊ฒƒ์˜ ์š”์ง€๋Š” ๋ชจ๋“  ๋ฐ์ดํ„ฐ ์ง‘๋‹จ์ด
08:15
that every single data set has to relate specifically to you.
198
495391
2877
์—ฌ๋Ÿฌ๋ถ„๊ณผ ํŠน์ •ํ•œ ์—ฐ๊ด€์„ฑ์ด ์žˆ์–ด์•ผ ํ•œ๋‹ค๋Š” ๊ฒƒ์ด ์•„๋‹™๋‹ˆ๋‹ค.
08:18
I'm interested in how many women were issued fines in France
199
498292
2880
์ €๋Š” ํ”„๋ž‘์Šค์—์„œ ์–ผ๋งˆ๋‚˜ ๋งŽ์€ ์—ฌ์„ฑ์ด ๋‹ˆ์บ…์„ ์“ด ๊ฒƒ ๋•Œ๋ฌธ์—
08:21
for wearing the face veil, or the niqab,
200
501196
1959
๋ฒŒ๊ธˆ์„ ๋ฌผ์—ˆ๋Š”์ง€์— ๊ด€์‹ฌ์ด ์žˆ์–ด์š”.
08:23
even if I don't live in France or wear the face veil.
201
503179
2618
์ œ๊ฐ€ ํ”„๋ž‘์Šค์— ์‚ด๊ณ  ์žˆ์ง€ ์•Š๊ณ  ๋‹ˆ์บ…๋„ ์“ฐ์ง€ ์•Š๋Š”๋ฐ๋„์š”.
08:25
The point of asking where you fit in is to get as much context as possible.
202
505821
3835
๋‚ด๊ฐ€ ์–ด๋””์— ๋“ค์–ด๋งž๋Š”์ง€๋ฅผ ๋ฌป๋Š” ์ด์œ ๋Š” ์ตœ๋Œ€ํ•œ ๋งŽ์€ ๋งฅ๋ฝ์„ ์–ป๊ธฐ ์œ„ํ•ด์„œ์ž…๋‹ˆ๋‹ค.
08:29
So it's about zooming out from one data point,
203
509680
2191
๊ทธ๋ž˜์„œ ํ•œ ๋ฐ์ดํ„ฐ ์ง€์ ์œผ๋กœ๋ถ€ํ„ฐ ๋ฉ€๋ฆฌ ๋–จ์–ด์ ธ์„œ ๋ด์•ผ ํ•ฉ๋‹ˆ๋‹ค.
08:31
like the unemployment rate is five percent,
204
511895
2104
์ผ๋ก€๋กœ ์‹ค์—…๋ฅ ์ด 5%๋ผ๋ฉด
08:34
and seeing how it changes over time,
205
514023
1757
์ด๊ฒŒ ์‹œ๊ฐ„์ด ๊ฐˆ์ˆ˜๋ก ์–ด๋–ป๊ฒŒ ๋ณ€ํ•˜๋Š”์ง€
08:35
or seeing how it changes by educational status --
206
515804
2650
ํ•™๋ ฅ์— ๋”ฐ๋ผ ์–ด๋–ป๊ฒŒ ๋ณ€ํ•˜๋Š”์ง€
08:38
this is why your parents always wanted you to go to college --
207
518478
3104
์ฐธ๊ณ ๋กœ, ๊ทธ๋ž˜์„œ ๋ถ€๋ชจ๋‹˜๋“ค์ด ๋Œ€ํ•™์— ๊ฐ€๋ผ๊ณ  ํ•˜๋Š” ๊ฒ๋‹ˆ๋‹ค.
08:41
or seeing how it varies by gender.
208
521606
2032
๋˜๋Š” ์  ๋”์— ๋”ฐ๋ผ ์–ด๋–ป๊ฒŒ ๋‹ค๋ฅธ์ง€๋ฅผ ๋ด์•ผํ•˜์ฃ .
08:43
Nowadays, male unemployment rate is higher
209
523662
2127
์š”์ฆ˜์€ ๋‚จ์„ฑ ์‹ค์—…๋ฅ ์ด ์—ฌ์„ฑ ์‹ค์—…๋ฅ ๋ณด๋‹ค ๋†’์Šต๋‹ˆ๋‹ค.
08:45
than the female unemployment rate.
210
525813
1700
08:47
Up until the early '80s, it was the other way around.
211
527537
2695
80๋…„๋Œ€ ์ดˆ๋ฐ˜๊นŒ์ง€๋Š” ๋ฐ˜๋Œ€์˜€์–ด์š”.
08:50
This is a story of one of the biggest changes
212
530256
2117
์ด๊ฑด ๋ฏธ๊ตญ ์‚ฌํšŒ์— ์ผ์–ด๋‚œ
08:52
that's happened in American society,
213
532397
1720
๊ฐ€์žฅ ํฐ ๋ณ€ํ™” ์ค‘ ํ•˜๋‚˜์ž…๋‹ˆ๋‹ค.
08:54
and it's all there in that chart, once you look beyond the averages.
214
534141
3276
ํ‰๊ท  ๋„ˆ๋จธ๋ฅผ ๋ณด๊ฒŒ ๋˜๋ฉด ๋„ํ‘œ ์•ˆ์— ๋‹ค ๋“ค์–ด์žˆ๋Š” ๊ฒƒ์ž…๋‹ˆ๋‹ค.
08:57
The axes are everything;
215
537441
1165
X์ถ•๊ณผ Y์ถ•์ด ์ „๋ถ€์˜ˆ์š”.
08:58
once you change the scale, you can change the story.
216
538630
2669
๊ทœ๋ชจ๋ฅผ ๋ฐ”๊พธ๋ฉด ์ด์•ผ๊ธฐ๊ฐ€ ๋‹ฌ๋ผ์ง‘๋‹ˆ๋‹ค.
09:01
OK, so the third and final question that I want you guys to think about
217
541323
3380
ํ†ต๊ณ„๋ฅผ ๋ณผ ๋•Œ ์—ฌ๋Ÿฌ๋ถ„์ด ์ƒ๊ฐํ•ด๋ณด๊ธธ ๋ฐ”๋ผ๋Š”
09:04
when you're looking at statistics is:
218
544727
1819
์„ธ ๋ฒˆ์งธ์ด์ž ๋งˆ์ง€๋ง‰ ์งˆ๋ฌธ์€ ์ด๊ฒ๋‹ˆ๋‹ค.
09:06
How was the data collected?
219
546570
1873
์–ด๋–ป๊ฒŒ ๋ฐ์ดํ„ฐ๋ฅผ ์ˆ˜์ง‘ํ–ˆ์ง€?
09:09
So far, I've only talked about the way data is communicated,
220
549487
2939
์—ฌํƒœ๊นŒ์ง€ ์ €๋Š” ๋ฐ์ดํ„ฐ๊ฐ€ ์ „๋‹ฌ๋˜๋Š” ๋ฐฉ์‹์— ๋Œ€ํ•ด์„œ๋งŒ ๋งํ–ˆ์–ด์š”.
09:12
but the way it's collected matters just as much.
221
552450
2276
ํ•˜์ง€๋งŒ ์ˆ˜์ง‘๋˜๋Š” ๋ฐฉ์‹๋„ ๋˜‘๊ฐ™์ด ์ค‘์š”ํ•ฉ๋‹ˆ๋‹ค.
09:14
I know this is tough,
222
554750
1167
์ด๊ฒŒ ์–ด๋ ต๋‹ค๋Š” ๊ฑฐ ์•Œ์•„์š”.
09:15
because methodologies can be opaque and actually kind of boring,
223
555941
3081
๋ฐฉ๋ฒ•๋ก ์ด ๋ถˆ๋ถ„๋ช…ํ•˜๊ฑฐ๋‚˜ ์‚ฌ์‹ค ์•ฝ๊ฐ„ ์ง€๋ฃจํ•  ์ˆ˜ ์žˆ๊ฑฐ๋“ ์š”.
09:19
but there are some simple steps you can take to check this.
224
559046
2873
ํ•˜์ง€๋งŒ ์ด๊ฑธ ํ™•์ธํ•˜๋Š” ๋ฐ ์“ธ ์ˆ˜ ์žˆ๋Š” ๊ฐ„๋‹จํ•œ ๋ฐฉ๋ฒ•์ด ์žˆ์Šต๋‹ˆ๋‹ค.
09:21
I'll use one last example here.
225
561943
1839
๋งˆ์ง€๋ง‰ ์˜ˆ์‹œ๋ฅผ ์—ฌ๊ธฐ์„œ ๋“ค๊ฒŒ์š”.
09:24
One poll found that 41 percent of Muslims in this country support jihad,
226
564129
3887
ํ•œ ์—ฌ๋ก ์กฐ์‚ฌ์—์„œ ๊ตญ๋‚ด ๋ฌด์Šฌ๋ฆผ์˜ 41%๊ฐ€ ์ง€ํ•˜๋“œ๋ฅผ ์ง€์ง€ํ•œ๋‹ค๋Š” ๊ฑธ ๋ฐœ๊ฒฌํ–ˆ์–ด์š”.
09:28
which is obviously pretty scary,
227
568040
1525
๋งค์šฐ ๋ฌด์„œ์šด ์ผ์ด์ฃ .
09:29
and it was reported everywhere in 2015.
228
569589
2642
2015๋…„์— ์ „๊ตญ์ ์œผ๋กœ ๋ฐœํ‘œ๋์–ด์š”.
09:32
When I want to check a number like that,
229
572255
2615
์ด๋Ÿฐ ์ˆ˜์น˜๋ฅผ ์ฒดํฌํ•ด๋ณด๊ณ  ์‹ถ์„ ๋•Œ
09:34
I'll start off by finding the original questionnaire.
230
574894
2501
์ €๋Š” ๋จผ์ € ์„ค๋ฌธ์ง€ ์›๋ณธ์„ ์ฐพ์•„๋ณด์•„์š”.
09:37
It turns out that journalists who reported on that statistic
231
577419
2926
์ด ํ†ต๊ณ„๋ฅผ ๋ณด๊ณ ํ•œ ๊ธฐ์ž๋“ค์€ ์„ค๋ฌธ์ง€ ํ•˜๋‹จ์— ์œ„์น˜ํ•œ
09:40
ignored a question lower down on the survey
232
580369
2231
์‘๋‹ต์ž์—๊ฒŒ ์ž์‹ ์ด "์ง€ํ•˜๋“œ"๋ฅผ ์–ด๋–ป๊ฒŒ ์ •์˜ํ•˜๋Š”์ง€๋ฅผ
09:42
that asked respondents how they defined "jihad."
233
582624
2346
๋ฌผ์–ด๋ณธ ์งˆ๋ฌธ์„ ๋ฌด์‹œํ–ˆ๋”๊ตฐ์š”.
09:44
And most of them defined it as,
234
584994
1981
๋Œ€๋ถ€๋ถ„์˜ ์‚ฌ๋žŒ๋“ค์ด ์ด๋ ‡๊ฒŒ ์ •์˜ํ–ˆ์–ด์š”.
09:46
"Muslims' personal, peaceful struggle to be more religious."
235
586999
3942
"๋” ๋…์‹คํ•ด์ง€๊ธฐ ์œ„ํ•œ ๋ฌด์Šฌ๋ฆผ์˜ ๊ฐœ์ธ์ ์ด๊ณ  ํ‰ํ™”์ ์ธ ํˆฌ์Ÿ."
09:50
Only 16 percent defined it as, "violent holy war against unbelievers."
236
590965
4194
16%๋งŒ์ด ์ด๋ ‡๊ฒŒ ์ •์˜ํ–ˆ์–ด์š”. "์ด๊ต๋„๋“ค๊ณผ์˜ ํญ๋ ฅ์ ์ธ ์„ฑ์ „."
09:55
This is the really important point:
237
595183
2430
์ด๊ฒŒ ์ง„์งœ ์ค‘์š”ํ•œ ์‚ฌ์‹ค์ธ๋ฐ์š”.
09:57
based on those numbers, it's totally possible
238
597637
2155
์ด ํ†ต๊ณ„์— ๊ธฐ๋ฐ˜ํ–ˆ์„ ๋•Œ ์„ค๋ฌธ์ง€์—์„œ ์ง€ํ•˜๋“œ๋ฅผ
09:59
that no one in the survey who defined it as violent holy war
239
599816
3105
ํญ๋ ฅ์ ์ธ ์„ฑ์ „์ด๋ผ๊ณ  ๋‹ตํ•œ ์‚ฌ๋žŒ ์ค‘ ๊ทธ ๋ˆ„๊ตฌ๋„ ๊ทธ๊ฑธ ์ง€์ง€ํ•œ๋‹ค๊ณ  ํ•˜์ง€ ์•Š์•˜์„
10:02
also said they support it.
240
602945
1332
๊ฐ€๋Šฅ์„ฑ์ด ์กด์žฌํ•ด์š”.
10:04
Those two groups might not overlap at all.
241
604301
2208
๋‘ ์ง‘ํ•ฉ์˜ ๊ต์ง‘ํ•ฉ์ด ์•„์˜ˆ ์—†์„ ์ˆ˜ ์žˆ์–ด์š”.
10:06
It's also worth asking how the survey was carried out.
242
606942
2637
์„ค๋ฌธ์กฐ์‚ฌ๊ฐ€ ์–ด๋–ป๊ฒŒ ์‹คํ–‰๋๋Š”์ง€๋ฅผ ๋ฌผ์–ด๋ณด๋Š” ๊ฒƒ๋„ ์ข‹์Šต๋‹ˆ๋‹ค.
10:09
This was something called an opt-in poll,
243
609603
1998
์ด๊ฑด ์˜ตํŠธ์ธ ์„ค๋ฌธ์กฐ์‚ฌ์˜€์–ด์š”.
10:11
which means anyone could have found it on the internet and completed it.
244
611625
3402
๋ˆ„๊ตฌ๋‚˜ ์ธํ„ฐ๋„ท์—์„œ ๋ณด๊ณ  ์‘๋‹ตํ•  ์ˆ˜ ์žˆ์—ˆ๋‹ค๋Š” ๋œป์ž…๋‹ˆ๋‹ค.
10:15
There's no way of knowing if those people even identified as Muslim.
245
615051
3339
์ด ์‚ฌ๋žŒ๋“ค์ด ์• ์ดˆ์— ๋ฌด์Šฌ๋ฆผ์กฐ์ฐจ ์•Œ ๋ฐฉ๋ฒ•์ด ์—†์–ด์š”.
10:18
And finally, there were 600 respondents in that poll.
246
618414
2612
๋งˆ์ง€๋ง‰์œผ๋กœ ์ด ์„ค๋ฌธ์กฐ์‚ฌ์˜ ์‘๋‹ต์ž ์ˆ˜๋Š” 600๋ช…์ด์—ˆ์Šต๋‹ˆ๋‹ค.
10:21
There are roughly three million Muslims in this country,
247
621050
2654
ํ“จ ์—ฐ๊ตฌ์„ผํ„ฐ์— ๋”ฐ๋ฅด๋ฉด ๊ตญ๋‚ด์—๋Š” ์•ฝ 300๋งŒ๋ช…์˜
10:23
according to Pew Research Center.
248
623728
1607
๋ฌด์Šฌ๋ฆผ์ด ์žˆ์Šต๋‹ˆ๋‹ค.
10:25
That means the poll spoke to roughly one in every 5,000 Muslims
249
625359
2993
์ด ๋ง์€ ์—ฌ๋ก ์กฐ์‚ฌ๊ฐ€ ๋Œ€๋žต 5000๋ช…์˜ ๋ฌด์Šฌ๋ฆผ ์ค‘ ํ•œ ๋ช… ๊ผด๋กœ
10:28
in this country.
250
628376
1168
์กฐ์‚ฌํ–ˆ๋‹ค๋Š” ๊ฒ๋‹ˆ๋‹ค.
10:29
This is one of the reasons
251
629568
1266
๊ทธ๋ ‡๊ธฐ ๋•Œ๋ฌธ์—
10:30
why government statistics are often better than private statistics.
252
630858
3607
๊ตญ๊ฐ€ ํ†ต๊ณ„๊ฐ€ ๋•Œ๋กœ๋Š” ์‚ฌ์„ค ํ†ต๊ณ„๋ณด๋‹ค ๋‚ซ์Šต๋‹ˆ๋‹ค.
10:34
A poll might speak to a couple hundred people, maybe a thousand,
253
634489
3035
์—ฌ๋ก ์กฐ์‚ฌ๋Š” 200๋ช… ์ •๋„๋ฅผ ์กฐ์‚ฌํ•ฉ๋‹ˆ๋‹ค. 1000๋ช…์ผ ๋•Œ๋„ ์žˆ์–ด์š”.
10:37
or if you're L'Oreal, trying to sell skin care products in 2005,
254
637548
3058
2005๋…„์— ์Šคํ‚จ ์ผ€์–ด ์ œํ’ˆ์„ ํŒ๋งคํ•˜๋ ค๊ณ  ํ–ˆ๋˜ ๋กœ๋ ˆ์•Œ์€
10:40
then you spoke to 48 women to claim that they work.
255
640630
2417
48๋ช…์˜ ์—ฌ์„ฑ์„ ์กฐ์‚ฌํ•˜๊ณ  ํšจ๊ณผ๊ฐ€ ์žˆ๋‹ค๊ณ  ์ฃผ์žฅํ–ˆ์ฃ .
10:43
(Laughter)
256
643071
1026
(์›ƒ์Œ)
10:44
Private companies don't have a huge interest in getting the numbers right,
257
644121
3556
์‚ฌ๊ธฐ์—…์€ ์˜ฌ๋ฐ”๋ฅธ ์ˆ˜์น˜๋ฅผ ์–ป๋Š” ๋ฐ์—๋Š” ๊ทธ๋‹ค์ง€ ํฐ ๊ด€์‹ฌ์ด ์—†์–ด์š”.
10:47
they just need the right numbers.
258
647701
1755
์ž๊ธฐ๊ฐ€ ์›ํ•˜๋Š” ์ˆซ์ž๊ฐ€ ํ•„์š”ํ•œ๊ฑฐ์ฃ .
10:49
Government statisticians aren't like that.
259
649480
2020
์ •๋ถ€ ํ†ต๊ณ„๋Š” ๊ทธ๋ ‡์ง€ ์•Š์•„์š”.
10:51
In theory, at least, they're totally impartial,
260
651524
2447
์ ์–ด๋„ ์ด๋ก ์ƒ์œผ๋กœ๋Š” ์™„์ „ํžˆ ๊ณตํ‰ํ•ด์š”.
10:53
not least because most of them do their jobs regardless of who's in power.
261
653995
3501
๋ˆ„๊ฐ€ ๊ถŒ๋ ฅ์„ ๊ฐ–๊ฒŒ ๋˜๋“  ๋Œ€๋ถ€๋ถ„์ด ๊ทธ๋ƒฅ ์ž๊ธฐ ์ผ์„ ํ•˜๋Š” ๊ฒƒ๋„ ํ•œ ์ด์œ ์˜ˆ์š”.
10:57
They're civil servants.
262
657520
1162
๊ณต๋ฌด์›์ด๋‹ˆ๊นŒ์š”.
10:58
And to do their jobs properly,
263
658706
1964
์ž๊ธฐ ์ผ์„ ์ œ๋Œ€๋กœ ํ•˜๋ ค๋ฉด
11:00
they don't just speak to a couple hundred people.
264
660694
2363
200๋ช…๋งŒ ์„ค๋ฌธ์กฐ์‚ฌํ•˜์ง€ ์•Š์•„์š”.
11:03
Those unemployment numbers I keep on referencing
265
663081
2318
์ œ๊ฐ€ ์ž๊พธ ์–ธ๊ธ‰ํ•˜๋Š” ์ด ์‹ค์—…๋ฅ  ์ˆ˜์น˜๋Š”
11:05
come from the Bureau of Labor Statistics,
266
665423
2004
๋…ธ๋™ํ†ต๊ณ„์ฒญ์—์„œ ๋ฐœํ‘œํ•œ ๊ฑฐ์˜ˆ์š”.
11:07
and to make their estimates,
267
667451
1335
์ด ์ˆ˜์น˜๋ฅผ ๊ณ„์‚ฐํ•˜๊ธฐ ์œ„ํ•ด
11:08
they speak to over 140,000 businesses in this country.
268
668810
3489
๋…ธ๋™ํ†ต๊ณ„์ฒญ์€ 14๋งŒ ๊ฐœ๊ฐ€ ๋„˜๋Š” ๊ตญ๋‚ด ์‚ฌ์—…์žฅ์„ ์กฐ์‚ฌํ•ฉ๋‹ˆ๋‹ค.
11:12
I get it, it's frustrating.
269
672323
1725
์•Œ์•„์š”, ์ •๋ง ์งœ์ฆ๋‚˜์ฃ .
11:14
If you want to test a statistic that comes from a private company,
270
674072
3115
์‚ฌ๊ธฐ์—…์—์„œ ๋ฐœํ‘œํ•œ ํ†ต๊ณ„๋ฅผ ์‹œํ—˜ํ•ด๋ณด๊ณ  ์‹ถ๋‹ค๋ฉด
11:17
you can buy the face cream for you and a bunch of friends, test it out,
271
677211
3361
์นœ๊ตฌ๋“ค๊ณผ ์ง์ ‘ ๋กœ์…˜์„ ์‚ฌ์„œ ๋ฐœ๋ผ๋ณด๋ฉด ๋ฉ๋‹ˆ๋‹ค.
11:20
if it doesn't work, you can say the numbers were wrong.
272
680596
2591
ํšจ๊ณผ๊ฐ€ ์—†์œผ๋ฉด ํ†ต๊ณ„๊ฐ€ ํ‹€๋ ธ๋‹ค๊ณ  ๋งํ•  ์ˆ˜ ์žˆ์–ด์š”.
11:23
But how do you question government statistics?
273
683211
2146
๊ทธ๋Ÿฐ๋ฐ ์ •๋ถ€ ํ†ต๊ณ„๋Š” ์–ด๋–ป๊ฒŒ ์˜๋ฌธ์„ ์ œ๊ธฐํ•˜์ฃ ?
11:25
You just keep checking everything.
274
685381
1630
๋ชจ๋“  ๊ฒƒ์„ ๊ณ„์† ํ™•์ธํ•˜๋Š” ๊ฒ๋‹ˆ๋‹ค.
11:27
Find out how they collected the numbers.
275
687035
1913
์ˆ˜์น˜๋ฅผ ์–ด๋–ป๊ฒŒ ์ˆ˜์ง‘ํ–ˆ๋Š”์ง€
11:28
Find out if you're seeing everything on the chart you need to see.
276
688972
3125
๋‚ด๊ฐ€ ๋„ํ‘œ์—์„œ ๋ด์•ผ ํ•  ๋ชจ๋“  ๊ฒƒ์„ ๋‹ค ๋ณด๊ณ  ์žˆ๋Š”์ง€๋ฅผ ์•Œ์•„๋‚ด์„ธ์š”.
11:32
But don't give up on the numbers altogether, because if you do,
277
692121
2965
ํ•˜์ง€๋งŒ ์ˆ˜์น˜ ์ผ์ฒด๋ฅผ ํฌ๊ธฐํ•˜์ง„ ๋งˆ์„ธ์š”.
11:35
we'll be making public policy decisions in the dark,
278
695110
2439
๊ทธ๋ ‡๊ฒŒ ๋˜๋ฉด ์‚ฌ์ต์ด ์•Œ๋ ค์ฃผ๋Š” ๋ฐฉํ–ฅ๋งŒ ์‚ฌ์šฉํ•˜๋ฉด์„œ
11:37
using nothing but private interests to guide us.
279
697573
2262
๋ฌด์ง€ ์†์—์„œ ๊ณต๊ณต์ •์ฑ…์„ ๋งŒ๋“ค๊ณ  ์žˆ๊ฒŒ ๋  ํ…Œ๋‹ˆ๊นŒ์š”.
11:39
Thank you.
280
699859
1166
๊ณ ๋ง™์Šต๋‹ˆ๋‹ค.
11:41
(Applause)
281
701049
2461
(๋ฐ•์ˆ˜)
์ด ์›น์‚ฌ์ดํŠธ ์ •๋ณด

์ด ์‚ฌ์ดํŠธ๋Š” ์˜์–ด ํ•™์Šต์— ์œ ์šฉํ•œ YouTube ๋™์˜์ƒ์„ ์†Œ๊ฐœํ•ฉ๋‹ˆ๋‹ค. ์ „ ์„ธ๊ณ„ ์ตœ๊ณ ์˜ ์„ ์ƒ๋‹˜๋“ค์ด ๊ฐ€๋ฅด์น˜๋Š” ์˜์–ด ์ˆ˜์—…์„ ๋ณด๊ฒŒ ๋  ๊ฒƒ์ž…๋‹ˆ๋‹ค. ๊ฐ ๋™์˜์ƒ ํŽ˜์ด์ง€์— ํ‘œ์‹œ๋˜๋Š” ์˜์–ด ์ž๋ง‰์„ ๋”๋ธ” ํด๋ฆญํ•˜๋ฉด ๊ทธ๊ณณ์—์„œ ๋™์˜์ƒ์ด ์žฌ์ƒ๋ฉ๋‹ˆ๋‹ค. ๋น„๋””์˜ค ์žฌ์ƒ์— ๋งž์ถฐ ์ž๋ง‰์ด ์Šคํฌ๋กค๋ฉ๋‹ˆ๋‹ค. ์˜๊ฒฌ์ด๋‚˜ ์š”์ฒญ์ด ์žˆ๋Š” ๊ฒฝ์šฐ ์ด ๋ฌธ์˜ ์–‘์‹์„ ์‚ฌ์šฉํ•˜์—ฌ ๋ฌธ์˜ํ•˜์‹ญ์‹œ์˜ค.

https://forms.gle/WvT1wiN1qDtmnspy7