## Introduction to econometrics |

### From inside the book

Results 1-3 of 45

Page 127

What this says is that if the

is < 1, we can increase R2 by dropping that set of variables. Since for 1 degree of

freedom in the numerator, F = f2, what this means is that if the absolute value of ...

What this says is that if the

**F**-**ratio**associated with a set of explanatory variablesis < 1, we can increase R2 by dropping that set of variables. Since for 1 degree of

freedom in the numerator, F = f2, what this means is that if the absolute value of ...

Page 128

However, if there are k or more independent variables with absolute f-values less

than yfk, the

be able to increase R2 by discarding these variables. But if the R2 is increased ...

However, if there are k or more independent variables with absolute f-values less

than yfk, the

**F ratio**may or may not be less than 1, and hence we may or may notbe able to increase R2 by discarding these variables. But if the R2 is increased ...

Page 448

In Section 12.8 we discuss the critical

selection of regressors. We show that F(R2) = 1 < F(PC) < F(Cp) = 2 < F(Sp) We

also present the

In Section 12.8 we discuss the critical

**F**-**ratios**implied by the different criteria forselection of regressors. We show that F(R2) = 1 < F(PC) < F(Cp) = 2 < F(Sp) We

also present the

**F**-**ratios**implied by Leamer's posterior odds analysis.### What people are saying - Write a review

We haven't found any reviews in the usual places.

### Other editions - View all

### Common terms and phrases

2SLS adaptive expectations analysis assumptions autocorrelation autoregressive Chapter compute confidence interval consider consistent estimates constant term criterion defined degrees of freedom demand function denote dependent variable dummy variables DW test Econometrica Econometrics economic endogenous error term error variances estimates of ft exogenous variables expectations model explanatory variables f-distribution f-ratios F-test Figures in parentheses Hence heteroskedasticity Illustrative Example income instance instrumental variable least squares estimators least squares residuals linear probability model logit model measure multicollinearity multiple regression normal distribution Note observations obtained OLS estimation omitted variables parameters plim prediction error probit problem procedure proxy rational expectations recursive residuals regression coefficient regression equation regression model regressors relationship residual sum ridge regression sample serial correlation significance level simple regression standard errors studentized residuals suggested sum of squares supply function Suppose Table test statistic test the hypothesis uncorrelated values variance a2 zero