The following equation explains weekly hours of television viewing by a child in terms of the...

Transcribed Image Text:

The following equation explains weekly hours of television viewing by a child in terms of the number of hours of homework assigned at school: tvhours* = B0 + B1hmwk* + u Where tvhours*and hmwk* represent the true values of the underlying variables, and tvhours and hmwk represent what you observe. (a) Suppose tvhours* is measured with measured with random error that is uncorrelated with the explanatory variables. Are either of your estimates of B0 and B1 biased? If yes, can you sign the bias? (b) Now suppose instead that hmwk* is measured with random error that is uncorrelated with the other explanatory variables. Is your estimate of ß1 biased? If yes, can you sign the bias? The following equation explains weekly hours of television viewing by a child in terms of the number of hours of homework assigned at school: tvhours* = B0 + B1hmwk* + u Where tvhours*and hmwk* represent the true values of the underlying variables, and tvhours and hmwk represent what you observe. (a) Suppose tvhours* is measured with measured with random error that is uncorrelated with the explanatory variables. Are either of your estimates of B0 and B1 biased? If yes, can you sign the bias? (b) Now suppose instead that hmwk* is measured with random error that is uncorrelated with the other explanatory variables. Is your estimate of ß1 biased? If yes, can you sign the bias?