Question

Suppose that you are interested in buying an Apple iPod (either a new or used one) on eBay (the auction website) but you want to avoid overbidding. One possible way to get an insight into how much to bid would be to run a regression on the prices for which iPods were sold in previous auctions. This is an example of hedonic model of pricing. Assume you choose the following specification: Pricei = β0 + β1Newi + β2Scratchi + β3Bidrsi + i where: P ricei = the price in dollars at which the i th iPod sold on eBay Newi = a dummy variable equal to 1 if the i th iPod was new, and 0 otherwise Scratchi = a dummy variable equal to 1 if the i th iPod had a minor cosmetic defect, 0 otherwise Bidrsi = the number of bidders for the i th iPod Now answer the following questions: (a) Estimate the above regression equation using the dataset IPOD.xls. Check whether the estimated coefficients correspond to your expectations. Explain. (b) Which of the regression coefficients are statistically significant? Interpret the estimated coefficient of Bidrs. (c) One of your friends told you that each additional bidder increases price by more than 1 $. How will you test veracity of your friend’s claim using the given data? Explain. (d) Another friend of yours told you that minor cosmetic defect and number of bidders both do not matter for iPod pricing. How will you test veracity of your friend’s claim using the given data? Explain. (e) Using the estimated regression equation predict the price of a new iPod without any cosmetic defect when you know it has 3 bidders. Data: Regression Statistics Multiple R 0.662743904 R Square 0.439229482 Adjusted R Square 0.431256442 Standard Error 30.64061972 Observations 215 ANOVA df SS MS F Significance F Regression 3 155161.4594 51720.49 55.08933 2.43434E-26 Residual 211 198096.8387 938.8476 Total 214 353258.2981 Coefficients Standard Error t Stat P-value Lower 95% Upper 95% Intercept 109.2351254 4.478863692 24.38903 2.56E-63 100.4060729 118.0642 NEW 54.98653093 5.344129198 10.28915 2.2E-20 44.45180591 65.52126 SCRATCH -20.44182363 5.114388385 -3.99692 8.87E-05 -30.52366733 -10.36 BIDRS 0.725029464 0.58826868 1.23248 0.219141 -0.434607316 1.884666

          Suppose that you are interested in buying an Apple iPod (either
a new or used one) on eBay (the auction website) but you want to
avoid overbidding. One possible way to get an insight into how much
to bid would be to run a regression on the prices for which iPods
were sold in previous auctions. This is an example of hedonic model
of pricing. Assume you choose the following specification: Pricei =
β0 + β1Newi + β2Scratchi + β3Bidrsi + i where: P ricei = the price
in dollars at which the i th iPod sold on eBay Newi = a dummy
variable equal to 1 if the i th iPod was new, and 0 otherwise
Scratchi = a dummy variable equal to 1 if the i th iPod had a minor
cosmetic defect, 0 otherwise Bidrsi = the number of bidders for the
i th iPod Now answer the following questions: (a) Estimate the
above regression equation using the dataset IPOD.xls. Check whether
the estimated coefficients correspond to your expectations.
Explain. (b) Which of the regression coefficients are statistically
significant? Interpret the estimated coefficient of Bidrs. (c) One
of your friends told you that each additional bidder increases
price by more than 1 $. How will you test veracity of your friend’s
claim using the given data? Explain. (d) Another friend of yours
told you that minor cosmetic defect and number of bidders both do
not matter for iPod pricing. How will you test veracity of your
friend’s claim using the given data? Explain. (e) Using the
estimated regression equation predict the price of a new iPod
without any cosmetic defect when you know it has 3 bidders.
Data: 
Regression Statistics
Multiple
R
0.662743904
R
Square
0.439229482
Adjusted
R Square
0.431256442
Standard
Error
30.64061972
Observations
215
ANOVA
df
SS
MS
F
Significance F
Regression
3
155161.4594
51720.49
55.08933
2.43434E-26
Residual
211
198096.8387
938.8476
Total
214
353258.2981
Coefficients
Standard Error
t Stat
P-value
Lower 95%
Upper 95%
Intercept
109.2351254
4.478863692
24.38903
2.56E-63
100.4060729
118.0642
NEW
54.98653093
5.344129198
10.28915
2.2E-20
44.45180591
65.52126
SCRATCH
-20.44182363
5.114388385
-3.99692
8.87E-05
-30.52366733
-10.36
BIDRS
0.725029464
0.58826868
1.23248
0.219141
-0.434607316
1.884666

Added by Patricia R.

Question

Please give Ace some feedback