Term
| A stochastic error term must be added to all regression equations... |
|
Definition
| to account for variations in the dependent variable that are not explained completely by the independent variables. |
|
|
Term
| The components of the error term include: |
|
Definition
a. omitted variables
b. measurement errors in the data
c. an underlying theoretical equation that has a different functional form
d. purely random and unpredictable events |
|
|
Term
|
Definition
The difference between a particular observation of the dependent variable and the value estimated from the regression equation.
ei = Yi - Yihat |
|
|
Term
|
Definition
| Sum(Xi -Xbar)(Yi-Ybar)/Sum(Xi-Xbar)^2 |
|
|
Term
| Variation of dependent variable (TSS) |
|
Definition
|
|
Term
|
Definition
|
|
Term
|
Definition
|
|
Term
|
Definition
| Linear, Correctly Specified, Additive error |
|
|
Term
|
Definition
|
|
Term
|
Definition
All X's are uncorrelated with error term
If ability got dumped in the error term, it would be correlated with schooling, so there would be bias.
Most likely culprit for a change in sign. |
|
|
Term
|
Definition
No serial correlation of error term.
Most likely violated in time-series models.
Lingering effects of advertising, etc. |
|
|
Term
|
Definition
Constant Variance/No Heteroskedasticity
Violated in crosse-sectional data, like when comparing Rhode Island and Texas |
|
|
Term
|
Definition
No Perfect Multicollinearity
Happens if one variable is a multiple of the other, if they are off by a constant |
|
|
Term
|
Definition
| Error Normally Distributed (Not Required) |
|
|
Term
|
Definition
Best Linear Unbiased Estimator
-Minimum Variance
-Unbiased E(B) = B
-Consistent: B goes to B
-Normally Distributed |
|
|
Term
|
Definition
= E(Var) + B(theta)^2
efficient if minimized |
|
|
Term
|
Definition
| = Alpha2 * f(r ability, schooling) |
|
|
Term
|
Definition
| Ordinary Least Squares minimizes the sum of the squared residuals |
|
|
Term
|
Definition
| Sum(Yihat-Ybar)^2 + Sum(ei)^2 |
|
|
Term
|
Definition
|
|
Term
| Decomposition of Variance |
|
Definition
| Breakdown of TSS into ESS + RSS |
|
|
Term
|
Definition
| the excess of the number of observations (N) over the number of coefficients (including the incercept) estimated (K+1). |
|
|
Term
| Six Steps of Regression Analysis |
|
Definition
a. Review Lit
b. Specification
c. Hypothesize
d. Collect Data
e. Estimate equation
f. Document results |
|
|
Term
| Sampling Distribution of Bhat |
|
Definition
|
|
