Return to Video

“双重差分法”之简介

  • 0:00 - 0:03
    从原因到结果的路径
  • 0:03 - 0:06
    既黑暗且危险的
  • 0:06 - 0:09
    但是计量经济学的武器非常强大
  • 0:09 - 0:14
    当目睹平行趋势时
    我们掌握了双重差分法
  • 0:14 - 0:17
    ♪ [] ♪
  • 0:20 - 0:21
    计量经济学大师在寻找
  • 0:21 - 0:25
    令人信服的
    「其他条件不变的比较」
  • 0:25 - 0:29
    理想的对比是
  • 0:29 - 0:31
    看起来相似的处理组和对照组
    形成对照
  • 0:31 - 0:35
    但有时这种可比性是难以捉摸的
  • 0:35 - 0:37
    在没有处理的情况下
  • 0:37 - 0:40
    当处理组及对照组类似地演变时
  • 0:40 - 0:42
    即使起点不同
  • 0:42 - 0:45
    也有望进行因果推断
  • 0:46 - 0:48
    针对平行演化的武器
  • 0:49 - 0:51
    大师说的「平行趋势」
  • 0:51 - 0:53
    叫做「双重差分法」…
  • 0:53 - 0:54
    - 双重差分法...
  • 0:54 - 0:57
    - ...或简称为DD
    - 好的
  • 0:57 - 1:00
    - 现在让我们看看 DD
  • 1:00 - 1:03
    如何帮助我们了解美国历史上
  • 1:03 - 1:04
    最重要的经济事件之一
  • 1:05 - 1:08
    - 现在我们一起回顾大萧条的情況—
  • 1:09 - 1:12
    我国有史以来最严重的经济灾难
  • 1:13 - 1:16
    在 1933 年失业率达到 25%—
  • 1:17 - 1:19
    这是之前或之后从未见过的水平
  • 1:19 - 1:22
    数百万国民失去了家园或土地
  • 1:23 - 1:25
    Suicide spiked, and hungry families
  • 1:25 - 1:27
    relied on soup kitchens
    and bread lines
  • 1:27 - 1:28
    to keep from starving.
  • 1:29 - 1:32
    - Economists argue fiercely
  • 1:32 - 1:34
    over the causes
    of the Great Depression.
  • 1:34 - 1:37
    Most agree, however,
    that a key piece of the puzzle
  • 1:37 - 1:39
    is an epidemic of bank failures.
  • 1:40 - 1:42
    This was before deposit insurance.
  • 1:42 - 1:47
    So if your bank went bankrupt,
    your savings disappeared with it.
  • 1:47 - 1:48
    - [Cashier] Closing your account?
  • 1:48 - 1:49
    - [Customer] Yes, sir.
    I'm closing my account.
  • 1:49 - 1:51
    I wouldn't leave a nickel
    in this bank.
  • 1:53 - 1:56
    - Faced with a banking crisis,
    the Central Bank has a choice:
  • 1:56 - 1:59
    lend freely to troubled banks
  • 1:59 - 2:01
    or stand aside and refuse to lend.
  • 2:02 - 2:05
    Lending freely to banks in trouble
    is called "easy money."
  • 2:05 - 2:08
    Refusing to lend
    is called "tight money."
  • 2:10 - 2:13
    - [Joshua] Monetarist masters
    Milton Friedman and Anna Schwartz
  • 2:13 - 2:15
    famously called
    the Great Depression
  • 2:15 - 2:16
    the "Great Contraction,"
  • 2:17 - 2:18
    accusing the Federal Reserve
  • 2:18 - 2:21
    of inflicting a misguided policy
    of tight money
  • 2:21 - 2:24
    on the nation's teetering
    financial institutions.
  • 2:24 - 2:26
    They argued that easy money
  • 2:26 - 2:28
    would have kept
    many banks in business,
  • 2:28 - 2:30
    shortening the Great Depression.
  • 2:30 - 2:32
    But others disagree!
  • 2:32 - 2:34
    If banks are insolvent
  • 2:34 - 2:36
    because of unwise
    lending decisions,
  • 2:36 - 2:39
    then bailouts just encourage
    more foolishness.
  • 2:40 - 2:43
    Economists called this problem
    "moral hazard."
  • 2:43 - 2:46
    The debate over bailouts
    and moral hazard continues today.
  • 2:46 - 2:49
    Should financial behemoth
    Lehman Brothers
  • 2:49 - 2:52
    had been allowed to fail
    on the eve of the Great Recession,
  • 2:52 - 2:55
    in an ideal world,
    we'd answer this question
  • 2:55 - 2:58
    by applying different Fed policies
    to randomly selected regions.
  • 2:59 - 3:00
    But we can still learn a lot
  • 3:00 - 3:02
    by using differences-in-differences
  • 3:02 - 3:06
    to compare trends across areas
    with different monetary policies.
  • 3:11 - 3:13
    - [Camilla] How's that even possible?
  • 3:13 - 3:16
    Don't the same Fed policies
    apply to all banks in the U.S.?
  • 3:16 - 3:17
    - [Man] Yeah.
    - Good question.
  • 3:18 - 3:21
    The Federal Reserve System
    is divided into 12 districts,
  • 3:21 - 3:24
    each headed by a regional bank.
  • 3:24 - 3:27
    Today, Fed policy is set
    at the national level.
  • 3:27 - 3:32
    But in the 1930s, regional Feds
    could do pretty much as they liked.
  • 3:32 - 3:33
    - [Man] Ah, interesting.
  • 3:33 - 3:36
    - And here's what's
    so awesome about that.
  • 3:36 - 3:39
    In 1930, the Atlanta Fed,
    running the 6th district,
  • 3:39 - 3:41
    followed an easy money policy,
  • 3:41 - 3:45
    sending wheelbarrows of cash
    to rescue insolvent institutions.
  • 3:46 - 3:49
    The St. Louis Fed,
    running the 8th district,
  • 3:49 - 3:51
    followed a tight money policy.
  • 3:51 - 3:54
    "Let fail the foolish!"
    they said in St. Louis.
  • 3:54 - 3:58
    And so a natural experiment
    in monetary policy was born.
  • 3:59 - 4:02
    Even better, this is
    a within-state experiment.
  • 4:02 - 4:04
    The border between the 6th
    and the 8th districts
  • 4:04 - 4:07
    ran smack through
    the middle of Mississippi.
  • 4:07 - 4:09
    So northern Mississippi
    had tight money,
  • 4:09 - 4:12
    while southern Mississippi
    had easy money,
  • 4:12 - 4:15
    but under the same state laws
    and banking regulations in both.
  • 4:16 - 4:17
    - [Teacher] The treatment group
  • 4:17 - 4:20
    is the district 6 part
    of Mississippi,
  • 4:20 - 4:23
    which had access to easy money
    during the crisis.
  • 4:24 - 4:25
    The control group
  • 4:25 - 4:28
    is the district 8 part
    of Mississippi,
  • 4:28 - 4:30
    which had tight money
    during the crisis.
  • 4:31 - 4:34
    The key year
    in our natural experiment
  • 4:34 - 4:35
    was 1930.
  • 4:36 - 4:37
    Caldwell & Company,
  • 4:37 - 4:40
    a massive financial empire
    in the South,
  • 4:40 - 4:42
    came crashing down.
  • 4:43 - 4:46
    Banking is a business
    built on confidence and trust.
  • 4:46 - 4:49
    The Caldwell meltdown
    caused a panic
  • 4:49 - 4:53
    that led to a widespread
    bank run all at once.
  • 4:53 - 4:55
    Depositors wanted their money back,
  • 4:55 - 4:58
    causing banks to go bankrupt
    and shut their doors.
  • 5:01 - 5:03
    We'll use differences-in-differences
  • 5:03 - 5:07
    to measure the effect
    of contrasting monetary policies
  • 5:07 - 5:09
    in response to the Caldwell crisis.
  • 5:12 - 5:16
    This figure plots the number
    of banks in Mississippi by year,
  • 5:16 - 5:19
    for the 8th and 6th districts.
  • 5:19 - 5:21
    Let's start in 1929,
  • 5:21 - 5:24
    a year before the Caldwell crash.
  • 5:24 - 5:28
    There are 169 banks
    open in the 8th,
  • 5:28 - 5:31
    and 141 banks open in the 6th.
  • 5:31 - 5:33
    Over the next year,
  • 5:33 - 5:37
    we see a similar handful
    of banks fail, in both districts.
  • 5:37 - 5:40
    The change in the number
    of banks in operation
  • 5:40 - 5:42
    is remarkably similar --
  • 5:42 - 5:45
    that's what parallel trends look like.
  • 5:46 - 5:49
    In November 1930, Caldwell crashes,
  • 5:49 - 5:50
    and the panic begins.
  • 5:51 - 5:54
    Banks failed frequently
    in the 8th district,
  • 5:54 - 5:55
    which had tight money.
  • 5:56 - 5:59
    But the decline is slower
    in the 6th district,
  • 5:59 - 6:00
    which had easy money.
  • 6:01 - 6:03
    Diverging trends in this period
  • 6:03 - 6:07
    might be attributable
    to easy versus tight money.
  • 6:07 - 6:12
    In July of 1931, the 8th district
    abandons tight money,
  • 6:12 - 6:14
    so now both districts are easy.
  • 6:15 - 6:17
    Parallel trends are restored.
  • 6:17 - 6:19
    In a counterfactual world,
  • 6:19 - 6:22
    where the 6th district
    follows a tight money policy,
  • 6:22 - 6:24
    what might have happened?
  • 6:24 - 6:29
    If we extrapolate the trend
    of the 8th district to the 6th,
  • 6:29 - 6:30
    it would look like this.
  • 6:30 - 6:33
    So the treatment-effective
    easy money
  • 6:33 - 6:36
    is how much the 6th district
    deviated from the path
  • 6:36 - 6:39
    implied by the 8th district trend.
  • 6:41 - 6:44
    How many banks
    did the easy money treatment save?
  • 6:44 - 6:49
    This table reports data
    for the treatment group, district 6,
  • 6:49 - 6:50
    in the first row,
  • 6:50 - 6:54
    and data for the control group,
    district 8, in the second row.
  • 6:54 - 6:57
    The first column shows
    the number of banks in business
  • 6:57 - 7:01
    before the crisis began in 1930.
  • 7:01 - 7:04
    The second column shows 1931.
  • 7:04 - 7:06
    This is the key period
  • 7:06 - 7:09
    when each district
    had differing monetary policies
  • 7:09 - 7:10
    during the crisis.
  • 7:10 - 7:14
    The rightmost column
    reports changes within the district.
  • 7:14 - 7:20
    District 6 lost 14 banks,
    while district 8 lost 33.
  • 7:20 - 7:24
    The mathematical formula
    for the treatment effect is simple.
  • 7:24 - 7:28
    We subtract the change in banks
    in operation in the 8th district
  • 7:29 - 7:32
    from the change in banks
    in operation in the 6th.
  • 7:33 - 7:36
    Hence, the name
    "differences-in-differences."
  • 7:37 - 7:42
    -14 minus -33 equals 19.\]
  • 7:42 - 7:47
    We estimate that 19 banks
    were saved by easy money.
  • 7:47 - 7:51
    In practice, tables and figures
    like those shown here
  • 7:51 - 7:53
    are the beginning
    rather than the end
  • 7:53 - 7:54
    of a DD analysis.
  • 7:55 - 7:57
    The problem of how to gauge
  • 7:57 - 8:00
    the statistical significance
    of DD estimates
  • 8:00 - 8:02
    turns out to be exceedingly tricky,
  • 8:02 - 8:06
    and a regression is typically
    part of the solution.
  • 8:09 - 8:12
    The key assumption
    behind a valid DD analysis
  • 8:12 - 8:15
    is that of parallel trends.
  • 8:15 - 8:18
    Recall the principle
    of ceteris paribus.
  • 8:18 - 8:21
    Our ideal comparison
    would have the two districts
  • 8:21 - 8:24
    experience an identical
    business environment,
  • 8:24 - 8:26
    except for one factor:
  • 8:26 - 8:28
    easy or tight money.
  • 8:29 - 8:32
    Both districts would have
    identical types of customers
  • 8:32 - 8:35
    who would go bankrupt
    at exactly the same rate.
  • 8:36 - 8:39
    The skill of their employees
    would be equal, and so on.
  • 8:39 - 8:43
    Perfect ceteris paribus comparisons
    would allow us to clearly see
  • 8:43 - 8:47
    the causal effect
    of different Fed policies.
  • 8:47 - 8:49
    In this case, that's not possible.
  • 8:49 - 8:54
    But the idea of parallel trends
    is based on a similar concept.
  • 8:54 - 8:57
    If we see that the two regions
    experience similar trends
  • 8:57 - 9:00
    in the number of banks over time,
  • 9:00 - 9:01
    in the absence of treatment,
  • 9:01 - 9:04
    we can assume
    they are good comparisons.
  • 9:04 - 9:07
    We see that the two districts
    move in parallel,
  • 9:07 - 9:10
    both before the crisis and after,
  • 9:10 - 9:12
    when they have the same Fed policy.
  • 9:13 - 9:16
    The only time the districts
    behave differently
  • 9:16 - 9:18
    is when the Fed policy is different.
  • 9:19 - 9:21
    In view of this,
  • 9:21 - 9:24
    Fed policy is a likely cause
    of diverging trends
  • 9:24 - 9:27
    from 1930 to 1931.
  • 9:28 - 9:30
    But we should also check
    for other changes
  • 9:30 - 9:32
    unique to northern Mississippi.
  • 9:32 - 9:33
    - [Man] Huh?
    - What do you mean?
  • 9:34 - 9:35
    - [Teacher] Imagine that bad tornadoes
  • 9:35 - 9:39
    hit northern but not
    southern Mississippi in 1930.
  • 9:40 - 9:42
    These tornadoes devastate farms,
  • 9:42 - 9:44
    causing farmers
    to default on loans,
  • 9:45 - 9:47
    which drives their banks
    out of business.
  • 9:47 - 9:49
    Then the 6th and 8th districts
  • 9:49 - 9:52
    would differ in not one
    but two ways:
  • 9:53 - 9:55
    Fed policy and weather.
  • 9:55 - 9:58
    And we'd have trouble
    identifying Fed policy
  • 9:58 - 10:02
    as the causal factor
    behind increased bank failures
  • 10:02 - 10:03
    in the 8th.
  • 10:03 - 10:04
    - [Man] Ceteris is not paribus.
  • 10:07 - 10:09
    - DD credibility lives or dies
  • 10:09 - 10:11
    with the claim that the only reason
  • 10:11 - 10:14
    northern Mississippi
    was special in 1930
  • 10:14 - 10:16
    is differing regional Fed policy.
  • 10:17 - 10:21
    We're in DD heaven with strong,
    visual evidence of parallel trend.
  • 10:21 - 10:26
    - In general, the first step
    in evaluating whether to use DD
  • 10:26 - 10:30
    is usually this type of visual
    confirmation of parallel trends
  • 10:30 - 10:32
    outside of the period,
  • 10:32 - 10:35
    when we expect to see
    a treatment effect.
  • 10:35 - 10:37
    The treatment in our example
  • 10:37 - 10:40
    is easy money
    in the face of bank failures.
  • 10:40 - 10:45
    Metrics masters use DD
    to explore effects of many policies,
  • 10:46 - 10:48
    like the minimum legal drinking age,
  • 10:48 - 10:52
    and environmental changes,
    like access to clean water.
  • 10:53 - 10:54
    In our next video,
  • 10:54 - 10:57
    we'll see an example
    of how regression is used
  • 10:57 - 10:59
    to implement a DD approach.
  • 11:01 - 11:02
    - [Narrator] Are you a teacher?
  • 11:02 - 11:06
    Click to explore ways
    to use these videos in class.
  • 11:06 - 11:09
    If you're a learner,
    make sure this video sticks
  • 11:09 - 11:11
    by taking a few quick
    practice questions.
  • 11:12 - 11:14
    Or if you're ready,
    click for the next video.
  • 11:15 - 11:17
    You can also check out
    MRU's website
  • 11:17 - 11:20
    for more courses,
    teacher resources, and more.
  • 11:20 - 11:22
    ♪ [music] ♪
Tytuł:
“双重差分法”之简介
ASR Confidence:
0.86
Opis:

more » « less
Video Language:
English
Team:
Marginal Revolution University
Projekt:
Mastering Econometrics
Duration:
11:22

Chinese, Simplified subtitles

Revisions Compare revisions