Data were collected from a random sample of

220

home sales from a community in 2003. Let Price denote the selling price (in $1,000), BDR denote the number of bedrooms, Bath denote the number of bathrooms, Hsize denote the size of the house (in square feet), Lsize denote the lot size (in square feet), Age denote the age of the house (in years), and Poor denote a binary variable that is equal to 1 if the condition of the house is reported as "poor."

An estimated regression yields:

ModifyingAbove Price with caret equals 118.0 plus 0.480 BDR plus 23.2 Bath plus 0.154 Hsize plus 0.004 Lsize

(23.7

)

(2.53

)

(8.85

)

(0.011

)

(0.00048

)

+ 0.089 Age minus 48.3 Poor comma Upper R overbar squared equals 0.71 comma SER equals 41.1

(0.308

)

(10.4

)

Part 2

The

t-statistic

for the coefficient on BDR is

enter your response here

.

(Round

your response to three decimal

places.)

Is the coefficient on BDR statistically significantly different from zero?

A.

Since the

t-statistic

< 1.96, the coefficient on BDR is not statistically significantly different from zero.

B.

Since the

t-statistic

< 0.05, the coefficient on BDR is statistically significantly different from zero.

C.

Since the

t-statistic

> 1.96, the coefficient on BDR is statistically significantly different from zero.

D.

Since the

t-statistic

> 0.05, the coefficient on BDR is not statistically significantly different from zero.

Part 3

Typically five-bedroom houses sell for much more than two-bedroom houses. Is this consistent with the regression?

A.

No, the coefficient on BDR measures the partial effect of the number of bedrooms, holding house size constant, and thus significantly underestimates the price of five-bedroom houses.

B.

Yes, the coefficients on BDR and Hsize accurately take into account that each additional bedroom changes not only the total number of bedrooms but the total house size and thus price.

Part 4

A homeowner purchases

1980

square feet from an adjacent lot. Construct a confidence interval of

99

%

for the change in the value of her house.

The

99

%

confidence interval for the effect of lot size on price is

(

enter your response here

,

enter your response here

)

(in

thousands of

dollars).

(Round

your responses to two decimal

places.)

Part 5

Lot size is measured in square feet. Do you think that another scale might be more appropriate?

A.

No, if the lot size were measured in thousands of square feet, the estimate coefficient would be

0.000004

instead of

0.004

,

thus making the regression results more difficult to read and interpret.

B.

Yes, if the lot size were measured in thousands of square feet, the estimate coefficient would be

4

instead of

0.004

,

thus making the regression results easy to read and interpret.

C.

No, choosing another scale would not affect the regression results because the estimate coefficient would remain unaffected.

D.

Yes, if the lot size were measured in thousands of square feet, the estimate coefficient would be 1,000 instead of

0.004

,

thus normalizing the regression results.

Part 6

The degree of freedom to test if the coefficients on BDR and Age are statistically different from zero at the

5

%

level is

enter your response here

.

The critical value for the preceding test using the

Upper F Subscript m comma infinity

distribution

table

LOADING...

is

enter your response here

.

(Enter

your values exactly as they appear in the

table.)

Part 7

The

F-statistic

for omitting BDR and Age from the regression is F =

0.08

.

Are the coefficients on BDR and Age statistically different from zero at the

5

%

level?

A.

Because

0.08

is less than the critical value, the coefficients are jointly significant at the

5

%

level.

B.

Because

0.08

is less than the critical value, the coefficients are not jointly significant at the

5

%

level.

C.

Because

0.08

is greater than the critical value, the coefficients are not jointly significant at the

5

%

level.

D.

Because

0.08

is greater than the critical value, the coefficients are jointly significant at the

5

%

level.