Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

PPD 558 > Final Exam > Flashcards

Final Exam Flashcards

1
Q

The classical assumptions must be

A

met in order for OLS estimators to be the best available

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Classical Assumption #1

A

The regression model is linear, is correctly specified, and has an additive error term

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Classical Assumption #2

A

The error term has a zero population mean

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Classical Assumption #3

A

All explanatory variables are uncorrelated with the error term

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Classical Assumption #4

A

Observations of the error term are uncorrelated with each other (no serial correlation)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Classical Assumption #5

A

The error term has a constant variance (no heteroskedasticity)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Classical Assumption #6

A

No explanatory variable is a perfect linear function of any other explanatory variable(s) (no perfect multicollinearity)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Classical Assumption #7

A

The error term is normally distributed

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Omitted Variable Bias (Conditions)

A

relevant (β2 ≠ 0) – X1 and X2 are correlated

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Expected bias

A

Expected bias in መ 𝛽1 has two components: the sign of β2 and the sign of Corr(X1, X2)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Limited Dependent Variables

A

We have discussed dummy variables (indicator variables, binary variables) as a tool for measuring qualitative/categorical independent variables (gender, race, etc.)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

linear probability model

A

simply running OLS for a regression, where the dependent variable is a dummy (i.e. binary) variable:
where Di is a dummy variable, and the Xs, βs, and ε are typical independent variables, regression coefficients, and an error term, respectively

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

the term, linear probability model

A

comes from the fact that the right side of the equation is linear while the expected value of the left side measures the probability that Di = 1

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Some issues with LPM

A

෠ 𝑌 𝑖 ≤ 0 or ෠ 𝑌 𝑖 ≥ 1 a more fundamental problem with the linear probability model: nothing in the model requires ෠ 𝑌 to be between 0 and 1!  If ෠ 𝑌 is not between 0 and 1, how do we interpret it as a probability?  A related limitation is that the marginal effect of a 1-unit increase in any X is forced to be constant, which cannot possibly be true for all values of X  E.g., if increasing X by 1 always increases Y by a particular amount, ෠ 𝑌 must exceed 1 when X is sufficiently large

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

The Binomial Logit Model

A

The binomial logit is an estimation technique for equations with dummy dependent variables that avoids the unboundedness problem of the linear probability model

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Logits cannot be estimated using OLS

A

but are instead estimated by maximum likelihood (ML), an iterative estimation technique that is especially useful for equations that are nonlinear in the coefficients  Again, for the logit model is bounded by 1 and 0

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

Basic Procedure for Random Assignment Experiments

A

 Recruit sample of subjects  Randomly assign some to treatment group and some to control group ◼ Random assignment makes treatment uncorrelated with individual characteristics  Measure average difference in outcomes between treatment and control groups

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

natural experiments (or quasi-experiments

A

attempt to utilize the “treatment-control” framework in the absence of actual random assignment to treatment and control groups

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

Difference-in-difference estimator:

A

Policy impact = (Tpost – Tpre) – (Cpost– Cpre)  T: treatment group outcome, C: control group outcome  The DD estimate is the amount by which the change for the treatment group exceeded the change for the control grou

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

Panel data:

A

repeated observations of multiple units over time (combination of cross-sectional and time-series)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

Main advantages of panel data

A

 Increased sample size  Ability to answer types of questions that cross-sectional and time-series data cannot accommodate  Enables use of additional methods to eliminate omitted variables bias

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

Panel Data Notation

A

 𝑖 subscript indexes the cross-sectional unit (individual, county, state, etc.)  t subscript indexes the time period in which the unit is observe

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

First-differenced estimator

A

∆𝑌 𝑖 = 𝛼0 + 𝛽1∆𝑋𝑖 + ∆𝜀𝑖

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Q

Advantages of random effects estimator (if assumption about 𝑎𝑖 is correct):

A

 Allows time-invariant regressors to be included  More degrees of freedom (only estimates parameters of distribution from which 𝑎𝑖 is assumed to be drawn; fixed effects estimator uses one degree of freedom per fixed effect)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
Q

Disadvantages of random effects estimator:

A

 Biased if assumption that 𝑎𝑖 is uncorrelated with regressors is incorrect (while FE estimator allows arbitrary correlation between 𝑎𝑖 and regressors)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
26
Q

❑ Fixed effects estimator widely preferred when regressors of interest are time-varying

A

 It rarely seems likely that 𝑎𝑖 is uncorrelated with any regressors; fixed effects model is generally far more convincing

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
27
Q

Hausman test

A

❑ Fixed and random effect estimators can be compared with a Hausman test (previously seen in instrumental variables context as test for endogeneity)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
28
Q

Fixed vs. random effects - General Advice

A

 Under random effects hypothesis, both RE and FE estimators are consistent (should give similar results); under alternative hypothesis, FE consistent but RE is not  Therefore, if estimates are significantly different, can reject null hypothesis of random effects

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
29
Q

Fixed vs. random effects - Concept

A

❑ General advice: use fixed effects estimator if it’s feasible

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
30
Q

T-test

A

Divide the coefficient by the standard error to get the t-value

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
31
Q

Omitted Variables – Bias Assessment

A

Sign (β2) * Sign (Corr (X1, X2)) = Sign of Bias (β1)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
32
Q

Irrelevant Variables - Inclusion Criteria

A

Theory: is there sound justification for including the variable?

Bias: do the coefficients for other variables change noticeably when the variable is included?

T-Test: is the variable’s estimated coefficient statistically significant?

R-square: has the R-square (adjusted R-square) improved?

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
33
Q

Serial Correlation

A

First-order serial correlation occurs when the value of the error term in one period is a function of its value in the previous period; the current error term is correlated with the previous error term.

34
Q

DW Test

A

compare DW(d) to the critical values (𝐝_𝐋, 𝐝_𝐔)

35
Q

Pure Heteroskedasticity

A

occurs in correctly specified equations

36
Q

Impure Heteroskedasticity

A

arises due to model misspecification

37
Q

Multicollinearity

A

Multicollinearity exists in every equation & the severity can change from sample to sample.

There are no generally accepted true statistical tests for multicollinearity.

VIF > 5 as a rule of thumb

38
Q

Binary Dependent Variable Models

A

Linear Probability Model (LPM)
&
Logit / Probit Model

39
Q

Linear Probability Model (LPM)

A
  • Similar to OLS regression
  • R-squared is no longer an accurate goodness-of-fit measure
  • Interpretation: probability that Y=1 on a percentage point scale
40
Q

Logit / Probit Model

A
  • Restricted between 0 and 1
  • Automatically corrects for heteroskedasticity
  • Marginal effect of X is not constant
  • Not linear in the coefficients
41
Q

LPM Interpretation (example)

A

On average, a 1-unit increase in DISTANCE is associated with a negative 7.2 percentage point change in the probability of choosing Cedars Sinai, holding all else constant

42
Q

LPM Limitation #1

A

Unboundedness

The linear probability model produces nonsensical forecasts (>1 and <0)

43
Q

LPM Limitation #2

A

Adj-R^2 is no longer accurate measure of overall fit

44
Q

LPM Limitation #3

A

Marginal Effect (slope) of a 1-unit increase in X is forced to be constant

45
Q

LPM Limitation #4

A

Error term is neither homoskedastic nor normally distributed

46
Q

Logit Model Interpretation -

Coefficient Interpretation:

A

The sign and significance can be interpreted just as in linear models. B1 is the effect of a 1-unit increase in X1 on the log-odds ratio

47
Q

Calculating Marginal Effects

A

margin, dydx (X) at mean

48
Q

LPM Interpretations

A

B*100 percentage point change in the probability that Y=1

49
Q

Logit Interpretations

A

B change in the log-odds ratio of Y=1

50
Q

Marginal Effects Interpretations

A

(dy/dx)*100 percentage point change in the probability that Y=1

51
Q

Experimental Methods -

Selection Problems

A

Treatment is not necessarily randomly assigned because of other systematic differences in the error term (endogeneity) which would cause bias in the treatment’s effect. We need a valid counterfactual to truly understand the effect of the intervention / treatment.

52
Q

Valid Counterfactual

A

a control group that is exactly the same as the treatment group except it does not receive the treatment

53
Q

Solution to Selection Problems

A

Randomization

-Researcher randomly assigns subjects to either a treatment or control group to estimate the treatment effect

54
Q

Natural / Quasi-Experiments

A

Randomized experiments are hard to do in the social sciences, so researchers often rely upon natural experiments where an exogenous event mimics the treatment and control group framework in the absence of actual random assignment

55
Q

Counterfactual Challenge

A

Counterfactual Challenge

Hard to find an untreated group that really is otherwise identical to the treated group

56
Q

Panel Data - definitions expanded

A

Formed when cross-sectional and time-series data sets are combined to create a single data set. Main reason for working with panel data (beyond increasing sample size) is to provide insight into analytical questions that can’t be answered by using time-series or cross-sectional data alone

57
Q

Panel Data Advantages

A

Increased sample size so more degrees of freedom & sample variability
Able to answer new research questions
Can eliminate omitted variable bias with fixed effects (controlling for unobserved heterogeneity)

58
Q

Panel Data Concerns

A

Heteroskedasticity & Serial Correlation

59
Q

Panel Data - Fixed Effects Model

A

Does a good job of estimating panel data equations, and it also helps avoid omitted variable bias due to unobserved heterogeneity.

60
Q

Fixed Effects Model Assumptions

A

Each cross sectional unit has its own intercept. A fixed effects analysis will allow arbitrary correlation between all time-varying explanatory variables and 𝑎_𝑖

61
Q

Fixed Effects Model Drawback

A

measurement error, autocorrelation, heteroskedasticity

62
Q

Fixed Effects Model

A

The omitted variable bias arising from unobserved heterogeneity can be mitigated with panel data and the fixed effects model.

63
Q

How Fixed Effect Model address Omitted Variable Bias

A

How? Estimates panel data by including enough dummy variables to allow each cross-sectional of individual i and time period t to have a different intercept. These dummy variables absorb the time-invariant, individual-specific omitted factors in the error term

64
Q

Panel Data - Random Effects Model

When to use

A

When the explanatory variable of interest is time-invariant

65
Q

Panel Data - Random Effects Model

Assumption

A

Ai and regressors (Xit) are uncorrelated

66
Q

Panel Data - Random Effects Model

Advantages

A
  • Can handle time-invariant variables

- Uses fewer degrees of freedom than FE because of the lack of subject dummies

67
Q

Hausman Test

A

Compares fixed and random effect estimators to see if their difference is statistically significant.
If different  fixed effects model preferred (reject the null hypothesis of random effects)
If not different  random effects model to conserve degrees of freedom
(or provide estimates of both the fixed effects and random effects models)

If both models predict VERY DIFFERENT results, it suggests RE model has omitted variable bias and endogeneity present, making FE more statistically accurate

68
Q

What is the purpose of determining the Cook’s D, what is it used to detect?

A

Cook’s D is used to detect influential outliers.

69
Q

Linear Probability Model Example

A

𝐻𝑆𝑖 = 0.42 + 0.028𝑚𝑒𝑑𝑢𝑐𝑖 + 0.002𝑚𝑒𝑑𝑢𝑐𝑖

2 + 0.06𝑤𝑜𝑟𝑘�

70
Q

Problems with Linear Probability Model

A

1) HS෢i could be ≤ 0 or ≥ 1. Linear probability model is difficult to interpret as a probability
because HS෢i
is not bounded by 0 and 1. The linear probability model produces nonsensical
forecasts (greater than 1 and less than 0).
2) The marginal effect of a 1-unit increase in any X is forced to be constant, which cannot possibly
be true for all values of X.
3) 𝑅ത2
is no longer an accurate goodness-of-fit measure. The predicted values of Y are forced to
change linearly with X, so you could obtain a low 𝑅ത2
for an accurate model.

71
Q

What is the difference between a random and natural experiment?

A

Random experiments involve researcher’s randomly assigned subjects to either a treatment or control
group to estimate the treatment effect. Natural experiments or quasi-experiments, attempt to utilize
the “treatment-control” framework in the absence of actual random assignment to treatment and
control groups. Instead of researcher randomly assigning treatment, rely on some exogenous event to
create treatment and control groups. When the event or the policy is truly exogenous, treatment is as
good as randomly assigned.

72
Q

Problems in random experiments.

A

1) Random experiments are often very costly or cannot be carried out due to being unethical.
2) Non-random samples. They often lack generalizability since the sample may not be randomly
drawn from the entire population of interest.
3) Attrition bias because treatment or control units non-randomly drop out of the experiment.
4) Hawthorne effects (people behave differently when observed, may respond to treatment/control
status).
5) Randomization failure (can only control for observed treatment-control differences; bias may
result if unobservable characteristics not perfectly balanced).

73
Q

Explain briefly the difference-in-differences estimator

A

This method estimates the impact of a treatment by comparing the outcomes of a treatment
group and a control group before and after the treatment is received.

74
Q

Main underlying assumption of difference-in-differences estimator

A

The main underlying
assumption: in the absence of the treatment, the difference between the outcomes of the two
groups would not have changed (i.e., they would have followed a common trend). The change
in outcomes of the control group is viewed as the counterfactual for the change in outcomes
of the treatment group.

75
Q

What is panel data?

A

Panel data are repeated observations of multiple units over time. It is a combination of cross-sectional
and time-series.

76
Q

Advantages of Panel Data

A

1) More degrees of freedom and more sample variability than cross sectional data alone or time
series data alone allow for more accurate inference of the model parameters and hence increase
the efficiency of estimates.
2) Eliminate omitted variables bias. It is often argued that the real reason someone finds an effect
is because of ignoring specific variables that are correlated with the explanatory variables when
specifying the model. Panel data allows us to control for missing or unobserved variables.
3) Ability to answer types of questions that cross-sectional and time-series data cannot
accommodate. For example transitions from employment to unemployment, from employment
to retirement, changes on health status or any other variables that can change through time.

77
Q

differences between the fixed effects and random effects panel data
models.

A

The fixed effects model allows for 𝑎𝑖
to be correlated with the regressors and the random effects
estimator assumes 𝑎𝑖
is not correlated with the regressors.

78
Q

Advantages of the random effects model

A

Advantages of the random effects model are that allows time-invariant regressors to be included and
it includes more degrees of freedom.

79
Q

Disadvantages of the random effects model

A

The main disadvantage of random effects estimator is that is
biased if the assumption that 𝑎𝑖
is uncorrelated with regressors is incorrect.

80
Q

Advantage of the fixed effects model

A

An advantage of the fixed effects model is that allows arbitrary correlation between 𝑎𝑖 and any
regressors

81
Q

Disadvantage of the fixed effects model

A

One of the main disadvantages is that drops out time-invariant regressors.

82
Q

Preference between fixed effects model and random effects model

A

Unless we
wish to estimate the effect of a time invariant variable, fixed effects are generally preferred over
random effects due to having less restrictive assumptions.

PPD 558 (2 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions