SLIDE 1
Diff-in-diff II
March 11, 2020
PMAP 8521: Program Evaluation for Public Service Andrew Young School of Policy Studies Spring 2020 Fill out your reading report
- n iCollege!
Diff-in-diff II March 11, 2020 Fill out your reading report PMAP - - PowerPoint PPT Presentation
Diff-in-diff II March 11, 2020 Fill out your reading report PMAP - - PowerPoint PPT Presentation
Diff-in-diff II March 11, 2020 Fill out your reading report PMAP 8521: Program Evaluation for Public Service on iCollege! Andrew Young School of Policy Studies Spring 2020 Plan for today Quick talk about COVID-19 DiD review DiD full
SLIDE 2
SLIDE 3
Quick talk about COVID-19
SLIDE 4
New virus in the coronavirus family
What is all this?
Officially named SARS-COV-2 Causes respiratory disease named COVID-19
SLIDE 5
Originated in Wuhan, Hubei Province, China
What is all this?
Don’t call it “Chinese Coronavirus”
- r “Kung Flu” or other
xenophobic names!
SLIDE 6
SLIDE 7
Fever and dry cough initially; pneumonia-like respiratory failure later for vulnerable people
Symptoms
Up to two weeks can pass between exposure and symptoms Asymptomatic transmission likely possible
SLIDE 8
Lethality
SLIDE 9
Lethality
SLIDE 10
Why is everything shutting down?
Flattening the curve
SLIDE 11
If you’re young and healthy, all these cancellations and precautions are not about you!
Social distancing, staying home, washing your hands, etc. protects the vulnerable Huge collective action problem!
SLIDE 12
Wash hands for 20 seconds, disinfect phone, don’t touch your face
What you can do
Stay home if you’re sick Practice social distancing Limit non-essential travel Don’t buy masks Stock up on essentials but don’t hoard
SLIDE 13
flattenthecurve.com
SLIDE 14
I HAVE NO IDEA YET What does this mean for our class?
GSU hasn’t made any official decisions I’m committed to helping you all succeed and keep learning! I’ll continue to stream class via WebEx 2-week late work window is eliminated
SLIDE 15
Two wrongs make a right
SLIDE 16
SLIDE 17
Economic theory says there should be fewer jobs
What happens if you raise the minimum wage? New Jersey in 1992 $4.25 → $5.05
Raising the minimum wage
SLIDE 18
Average fast food jobs in NJ Before: 20.44 After: 21.03 ∆: 0.59 Is this the causal effect?
Before vs. after
SLIDE 19
Average fast food jobs in states PAafter: 21.17 NJafter: 21.03 ∆: −0.14 Is this the causal effect?
Treatment vs. control
SLIDE 20
Comparing only before/after Comparing only treatment/control
Impossible to know if growth happened because of treatment or just naturally Impossible to know if any changes happened because of natural growth
Problems
SLIDE 21
Being in New Jersey Time Minimum wage Jobs
SLIDE 22
Pre mean Post mean ∆ (post−pre) Treatment A (not yet treated) B (treated) B−A Control C (never treated) D (never treated) D−C ∆ (trtmt−ctrl) A−C B−D (B−A) − (D−C)
SLIDE 23
Pre mean Post mean ∆ (post−pre) Treatment A (not yet treated) B (treated) B−A Control C (never treated) D (never treated) D−C ∆ (trtmt−ctrl) A−C B−D (B−A) − (D−C)
Growth!
SLIDE 24
Pre mean Post mean ∆ (post−pre) Treatment A (not yet treated) B (treated) B−A Control C (never treated) D (never treated) D−C ∆ (trtmt−ctrl) A−C B−D (B−A) − (D−C)
Within-group effects
SLIDE 25
Pre mean Post mean ∆ (post−pre) Treatment A (not yet treated) B (treated) B−A Control C (never treated) D (never treated) D−C ∆ (trtmt−ctrl) A−C B−D (B−A) − (D−C)
Growth of treatment − growth of control (DiD!)
SLIDE 26
=(¯ x − ¯ x ) − (¯ x − ¯ x )
<latexit sha1_base64="(nul)">(nul)</latexit><latexit sha1_base64="(nul)">(nul)</latexit><latexit sha1_base64="(nul)">(nul)</latexit><latexit sha1_base64="(nul)">(nul)</latexit> SLIDE 27
Pre mean Post mean ∆ (post−pre) NJ A 20.44 B 21.03 B−A 0.59 PA C 23.33 D 21.17 D−C −2.16 ∆ (trtmt−ctrl) A−C −2.89 B−D −0.14 (0.59) − (−2.16) = 2.76
SLIDE 28
A C B D
SLIDE 29
A C B D
SLIDE 30
Finding all the group means is tedious though! What if there are other backdoors to worry about? Regression to the rescue!
SLIDE 31
Being in New Jersey Time Minimum wage Jobs
SLIDE 32
Group = 1/TRUE if treatment
Yit =↵ + Groupi + Timet+ (Groupi × Timet) + ✏it
<latexit sha1_base64="tPctye95c/TWQ7QaqhaC+TK3+c=">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</latexit>Time = 1/TRUE if after
SLIDE 33
Yit =↵ + Groupi + Timet+ (Groupi × Timet) + ✏it
<latexit sha1_base64="tPctye95c/TWQ7QaqhaC+TK3+c=">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</latexit>α = Mean of control, pre-treatment β = Increase in outcome across groups γ = Increase in outcome across time δ = Difference in differences!
SLIDE 34
Pre mean Post mean ∆ (post−pre) Control α α + γ γ Treatment α + β α + β + γ + δ γ + δ ∆ (trtmt−ctrl) β β + δ δ
Yit =↵ + Groupi + Timet + (Groupi × Timet) + ✏it
<latexit sha1_base64="5lDjK/m0Q2HKJ3tx76YpE80WMco=">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</latexit> SLIDE 35