FinalSheet

# FinalSheet - Regression Stata Output (Lecture 30): - R^2=...

This preview shows pages 1–2. Sign up to view the full content.

Regression Stata Output (Lecture 30): - R^2= accounts for X% variation in model - Root MSE=+/-2Se (Range or interval of variability of a specific calculated variable) - If significant use model to predict specific values o Input into equation - Or bound predictions (Prediction intervals) o (output) +/- 1.96 (Root MSE) Prediction Intervals (Lecture 30): - Calculating specific predicted values is less accurate than calculating average values - Account for Epsilon (Random Noise) in Prediction intervals Multiple Regression (Lectures 30 & 31): - Described by “k” independent variables - Slope of a given variable is the change in Y given a unit change in X holding ALL OTHER VARIABLES CONSTANT - Se=sqrt(SSE/(n-k-1)) - SST= SSR + SSE - R^2= SSR/SST - Adding X variable increases R^2, decreases SSE (be careful about adding in random variables) - Accept variables with t-statistic> abs. value(1.96), P<.05 - Overall F-Test: o Hnull:B1=B2=…=Bk=0 o Ha: At least 1 B does not = 0 o F-Test Statistic= (SSR/k)/(SSE/(n-k-1))

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

## This note was uploaded on 04/05/2012 for the course STAT 104 taught by Professor Stanley during the Spring '08 term at Harvard.

### Page1 / 2

FinalSheet - Regression Stata Output (Lecture 30): - R^2=...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online