Econ 388 Exam 2

Front 1

log-likelihood function

Back 1

the sum of the log-likelihoods, where the log-likelihood for each observation is the log of the density of the dependent variable given the explanatory variables; the log-likelihood function is viewed as a function of the parameters to be estimated

Front 2

beta coefficient or standardized coefficient

Back 2

regression coefficient that measures the standard deviation change in the dependent variable given a one standard deviation increase in an independent variable

Front 3

Goldfeld-Quandt test

Back 3

assumes that you know the form of the regression so that you know how to partition the data. But, gives an exact test for even small samples.

Front 4

variance of the prediction error

Back 4

the variance in the error that arises when predicting a future value of the dependent variable based on an estimated multiple regression equation

Front 5

maximum likelihood estimate (mle)

Back 5

a broadly applicable estimation method where the parameter estimates are chosen to maximize the log-likelihood function

Front 6

dummy variable trap

Back 6

the mistake of including too many dummy variables (variables that take on the value of 0 or 1) among the independent variables. Occurs when an overall intercept is in the model and a dummy variable is included FOR EACH GROUP.

Front 7

Breusch-Pagan test

Back 7

a test for heteroskedasticity where the squared OLS residuals are regressed on the explanatory variables in the model

Front 8

asymptotic efficient

Back 8

for consistent estimators with asymptotically normal distributions, the estimator with the smallest asymptotic variance

Front 9

LaGrange-Multiplier Test (aka score test)

Back 9

used to estimate the improvement in model fit if additional variables were included in the model, an test for omitted variables.

Front 10

central limit theorem (CLT)

Back 10

a key result from probability theory that implies that the sum of independent random variables, or even weakly dependent random variables, when standardized by its standard deviation, has a distribution that tends to standard normal as the sample size grows

Front 11

adjusted R-square

Back 11

a goodness-of-fit measure in multiple regression analysis that penalizes additional explanatory variables by using a degrees of freedom adjustment in estimating the error variance

Front 12

oblique v. orthogonal projections

Back 12

oblique: graphical projection using 2-dimensional depictions of 3-d objects
orthogonal: maps it in 3-d space (so oblique matrices have only (x,y); orthogonal have (x,y,z)

Front 13

method of moment estimators

Back 13

an estimator obtained by using the sample analog of population moments; OLS and two-stage least squares are both method of moments estimators

Front 14

probit model (of being married)

Back 14

a model for binary responses where the response probability is the standard normal cdf evaluated at a linear function of the explanatory variables

Front 15

law of large numbers

Back 15

theorem: the average from a random sample converges in probability to the population average; also holds for stationary and weakly dependent time series

Front 16

variance inflation factor

Back 16

in multiple regression analysis under the Gauss-Markov assumptions, the term in the sampling variance affected by correlation among the explanatory variables

Front 17

prediction interval for forecast

Back 17

a confidence interval for an unknown outcome on a dependent variable in a multiple regression model

Front 18

instrumental variables

Back 18

in an equation with an endogenous explanatory variable, an IV is an ommitted variable, is uncorrelated with the error in the equation, and is partially correlated with the endogenous explanatory variable

Front 19

two-sided alternative

Back 19

you're saying that the independent variable WILL have an effect, but you're not saying in which direction. It could be positively or negatively correlated.

Front 20

exclusion restrictions

Back 20

restrictions that state that certain variables are excluded from the model (or have zero population coefficients)

Front 21

Breusch-Godfrey test for AR(q)

Back 21

an asymptotically justified test for AR(p) serial correlation, with AR(1) being the most popular; the test allows for lagged dependent variables as well as other regressors that are not strictly exogenous

Front 22

pure v. impure heteroskedasticity (Butler's notes)

Back 22

Pure- there are no correlated omitted variables that cause the variance to change (o2=o2zi2)
Impure- The omitted variable is correlated with the independent variable (o2=f(zi,zi))

Front 23

"robust" option in STATA

Back 23

a STATA code that keeps the OLS coefficientes but uses robust standard errors.

Front 24

"prais y x1 x2 x3" procedure in STATA

Back 24

stata junk

Front 25

between-group v. within-group estimators

Back 25

dunno about the estimator part...but you basically want your between-group differences to be much higher than within-group for your independent variable. Like if I was doing a study where I changed your blood to gasoline, I'd want there to be more variance between your blood and the control group's than between your blood and the other sap with gas in his veins. Get it?

Front 26

dprobit in STATA

Back 26

stata crap

Front 27

marginal effect from a logit regression

Back 27

dP(X)/dXj = g(B0+XB)Bj where g(z) = dG/dz (z)

Front 28

STATA "test" statements for this model: regress y x1 x2 x3; test (x1=x2) (x3=x0)

Back 28

stata stratosphere

Front 29

weighted least squares estimator

Back 29

an estimator used to adjust for a known form of heteroskedasticity, where each squared residual is weighted by the inverse of the estimated variance of the error

Front 30

"hettest, rhs" in STATA

Back 30

tests for heteroskedasticity in gression model for a right hand sided test.