{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

HW5 - the VIFs Based on VIF values find out which...

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

View Full Document Right Arrow Icon
Econ 444 Elementary Econometrics (Winter 2010) HOMEWORK EXERCISE: 5 Due in class on Wed, March 3 1. State with reasons whether the following statements are true or false. (1.a) Despite perfect multicollinearity, OLS estimators are BLUE. (1.b) One of the consequences of heteroskedasticity is that OLS estimators are no longer unbiased and hence are not BLUE. (1.c) If heteroskedasticity is present the conventional t and F tests are invalid. 2. Download Multi.xls from Carmen. It provides data on following variables: Y : New passenger Cars Sold ( in thousands). X1 : New Cars Consumer price index ( 1967=100). X2 : Consumer Price Index for all Items( 1967=100). X3 : Personal Disposable Income( in billions of $). X4 : Interest rate (in %). X5 : Labor force. ( in thousands). Suppose we want to estimate, Y i = β 0 + β 1 X 1 i + β 2 X 2 i + β 3 X 3 i + β 4 X 4 i + β 5 X 5 i + i (1) (2.a) Estimate (1) in Eviews and submit your computer output for the same. 1
Background image of page 1

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

View Full Document Right Arrow Icon
(2.b) Calculate the VIF for each of the estimated coefficient. Report these and also your Eviews output for all the equations you estimate for calculating
Background image of page 2
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: the VIFs. Based on VIF values find out which variables are most affected by multicollinearity. 3. Consider the following regression equation, Y i = β + β 1 X i + ± i (2) Now suppose, V ar ( ± i ) = σ 2 X 3 i (3) (3.a) How would you transform the model to achieve homoskedastic ( or constant) error variance? Explain. (3.b) Is the OLS estimator of the transformed regression BLUE? 4. Download RD.xls from Carmen. The file contains cross section data on Research and Development expenditure in US in 1988 for different industries: Sales i- sales in the industry i. RDexp i- R&D expenditure in industry i. Now suppose you want to estimate, RDexp i = β + β 1 Sales i + ± i (4) 4.a Estimate (4) using Eviews. Submit your output. 4.b Using Park’s test, test whether there is heteroskedasticity in (4) at 5% level of significance. Report your eviews output for this test and state clearly whether you find heteroskedasticity in the data. 2...
View Full Document

{[ snackBarMessage ]}