{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

Practical 3

# Practical 3 - • Assumption 2 X values fixed in repeated...

This preview shows pages 1–6. Sign up to view the full content.

Practical 3 January 20, 2010

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

View Full Document
More on OLS on GRETL • Generating random variables • Run a regression! • There is a possibility of a  Type-I error.
Verifying the OLS  assumptions • Use Stock & Watson [CASCHOOL] • From <CONSOLE> ; ols testscr const  str • testscr _hat  = 698.933       2.27981 str (9.4675)       (0.47983) • Note R-squared = RSS/TSS = 0.05124 • Hypothesis testing (2-sided test): H 0 β 1  = 0 vs. H a β 1    0 H 0 β 2  = 0 vs. H a β 2    0 • Note: t-stat =  β _hat /SE( β _hat )

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

View Full Document
• Assumption 1: Linear Regression Model

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.

Unformatted text preview: • Assumption 2: X values fixed in repeated sampling • Assumption 3: Zero mean value of disturbance • Assumption 4: Homoskedasticity (constant variance) • Assumption 5: No autocorrelation between disturbances • Assumption 6: Zero covariance between u and X So are we happy with the regression? • No! There could be a possibility of omitted variable bias! • Chk corr(el_pct,str) and corr(el_pct,testscr). The F-test • F-stat...
View Full Document

{[ snackBarMessage ]}