Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
62 Cards in this Set
- Front
- Back
General Likelihood function of Binary DVs |
|
|
Logistic vs. Logit |
|
|
Cumulative normal vs. Probit
|
|
|
Formula: Logistic |
|
|
Formula: Logit |
|
|
Link function for Logit Regression |
|
|
Link function for Probit Regression |
|
|
Formula for Odds in Logit Regression |
|
|
Formula for P in Logit Regression |
|
|
Odds vs. P in Logit Regression |
|
|
Marginal effects: Logit Regression |
|
|
What does it mean to identify b? |
Write b as a function of observable variables |
|
|
|
|
|
|
|
Central Limit Theorem |
|
|
Asymptotic Normality |
|
|
Two assumptions of OLS |
|
|
Formula for A and B |
|
|
cov(x, y) = |
E(xy) - E(x)E(y) |
|
Var(x) = |
E(x^2) - E^2(x) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
GLS vs. OLS |
GLS has 1. nonconstant variances 2. nonzero covariances in the variance-covariance matrix (u) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
FGLS: Omega |
(SOLS residuals) |
|
FGLS: Beta |
|
|
FGLS: Fully robust sandwich FGLS variance |
|
|
FGLS: Non-robust "usual" FGLS variance |
|
|
Assumption SGLS3: When is the "usual" FGLS variance valid? |
|
|
SIV: Visualize Z_i and Dimensions |
|
|
SIV (Simultaneous equation) vs. SOLS |
|
|
SIV: Estimator beta hat |
|
|
Assumption SIV.1 Moments condition |
|
|
Pooled OLS |
OLS on panel data |
|
STATA: Pooled OLS |
reg y x, cluster(id) |
|
STATA: Random effects |
xtreg y x, re cluster(id) |
|
STATA: Fixed effects |
xtreg y x, fe cluster(id) |
|
Pooled OLS vs. RE |
Pooled OLS assume independence between v_{it} (error terms) |
|
RE vs. FE |
RE only solve the problems of autocorrelation between v_{it} (due to c_i) FE solve endogeneity as well |
|
Fully robust RE vs. Usual RE |
RE solve autocorrelation between v_{it}, but Usual RE assume constant variance and independence across u_{it} |
|
Wide vs long form data |
Wide: Years are wide (var2000, var2001, etc.) Long: "Year" is a column |
|
IIA Assumption - Independence from Irrelevant Alternatives |
An assumption of the multinomial logit model |
|
The assumption that RE makes but FE does not |
E(c|X) = E(c) = 0 |
|
FE makes fewer assumptions than RE. Why not FE all the time? |
Time-invariant characteristics. |
|
Pooled OLS: Assumptions |
|
|
RE: Assumptions |
|
|
RE: Omega |
|
|
|
|
|
|
|
|
E[Y_i] vs. Avg[Y_i] |
E[Y_i]: Population parameter: There is only one Avg[Y_i]: Sample statistics: There are many |
|
What is sampling variance? |
Variance of sample means from REPEATED sampling |
|
What is a standard error? |
The standard deviation of a sample statistic |