Empirical Tools

Question 1

Correlation

Answer 1

when two variables move together
- useful for passive prediction

Question 2

Causation

Answer 2

when one variable causes (or affects) another variable

Question 3

Identification problem

Answer 3

the question of whether one variable causes another

Question 4

Treatment variable

Answer 4

Di : the variable that generates the causal effect we’re interested in

Question 5

Outcome Variable

Answer 5

Yi : the var. that is affected by the treatment variable

Question 6

the concept of potential outcomes

Answer 6

The outcomes that a person would have under different values of the treatment

Question 7

the individual treatment effect

Answer 7

The difference in i’s potential outcomes in the case in which i does v. doesn’t receive the treatment

Question 8

the fundamental problem of casual interference

Answer 8

we can only ever observe one potential outcome per person. We can see i’s potential outcome in the observed state
- It is equal to the person’s realized outcome, Yi

Question 9

Average treatment effect

Answer 9

the average of the individual treatment effects in a population

Question 10

selection bias

Answer 10

when the selection of subjects into a study (or their likelihood of remaining in the study) leads to a result that is systematically different to the target population
- the difference in what average outcomes would be absent the treatment
- prevents us from identifying the average treatment effect

Question 11

observed state

Answer 11

state we do observe

Question 12

the counterfactual state

Answer 12

the state we do not observe

Question 13

treatment group

Answer 13

those with Di = 1

Question 14

control group

Answer 14

those with Di = 0

Question 15

naive method

Answer 15

Compare outcomes for people who in the real world happened to get a treatment v. those for people who didn’t
- fails due to selection bias

Question 16

randomized trial

Answer 16

the scientific term for an experiment
- In a rand. trial, the treatment, Di, is assigned via random chance

Question 17

Independence

Answer 17

the difference in avg. outcomes is the ATE

Question 18

Indirect Random Assignment

Answer 18

Randomly assign a variable that is related to, but not exactly the same as our variable of interest

Question 19

External Validity

Answer 19

results are valid only for the experiment’s participants
– The same experiment in U.S. and Sweden may generate different results
– But this suggests running lots of experiments and comparing them

Question 20

Attrition

Answer 20

When participants leave an experiment before it is complete
– If attrition is non-random, it can generate bias
-> Compare all of the treatment group with only some of the control
– Deal with attrition by finding a dataset with universal coverage
– apply for access to a database, instead of just conducting a survey

Question 21

Observational Data

Answer 21

Data that does not come from a deliberately designed experiment

Question 22

Time series

Answer 22

data on a particular variable over time

Question 23

Cross-sectional data

Answer 23

data on many people at one point in time

Question 24

Time-Series Analysis

Answer 24

the study of how series co-vary over time

Question 25

Cross-sectional regression

Answer 25

-- the study of how variables co-vary across people -- A statistical method for studying how variables co-vary across people -- Both a model and an estimation strategy -- both a representation of how variables are related and a means of fitting that representation to the data

Question 26

With observational data, there is an ever-present threat of

Answer 26

bias

Question 27

Difference-in-Difference model

Answer 27

A strategy that applies when: 1. Treatment & control groups form an imperfect comparison 2. We have data on these groups over time

Question 28

Quasi-experiments

Answer 28

A naturally occurring situation that resembles an experiment -- A situation where a change in the economic/political environment creates nearly identical treatment and control groups -- These T & C groups can then be used to measure a causal effect -- Often called “natural experiments” and often arise due to policy changes

Question 29

Imperfect Comparison

Answer 29

the difference in average outcomes contains bias

Question 30

Post-Period Difference

Answer 30

a non-experimental comparison of avg. outcomes -- the naive approach for recovering a treatment effect -- From before, δpst = ATE + bias(pst)

Question 31

Pre-period difference

Answer 31

just a bias term! I δpre = bias(pre) -- Because no one has received the treatment yet

Question 32

Parallel trends assumption

Answer 32

assume that the bias is stable over time -- bias(pre) = bias(pst) - The difference in average outcomes between T&C in the pre-period would have carried over to the post-period if the policy change had not occurred

Question 33

T&C is stable during the pre-period

Answer 33

-- If it is, then can assume would continue to be stable into the post-period -- If it isn’t, then know DID is invalid. Look for a new strategy

Question 34

Regression Discontinuity

Answer 34

a situation where a person gets the treatment if above a cutoff but not if below

Question 35

Insight of the Regression Discontinuity design

Answer 35

people right around a cutoff are similar -- If people have imperfect control over their scores, then scoring just above / below the cutoff is nearly random ⇒ Treatment assignment is approx. random for people close to the cutoff ⇒ Can recover an ATE for these people, just as in a randomized trial

Question 36

- However, we can’t see i’s potential outcome in the _____

Answer 36

counterfactual state & thus, we cant calculate the average treatment affect