Question

Demand can be estimated with experimental data, time-series data, or cross-section data. In this case, cross-section data appear in the Excel file. Soft drink consumption in cans per capita per year is related to six-pack price, income per capita, and mean temperature across the 48 contiguous states in the United States.

TABLE 1.  SOFT DRINK DEMAND DATA
State	Cans/Capita/Yr	6-Pack Price ($)	Income/Capita ($1,000)	Mean Temp. (F)
Alabama	200	3.19	35.1	66
Arizona	150	2.99	45.9	62
Arkansas	237	2.93	29.7	63
California	135	3.59	67.5	56
Colorado	121	3.29	51.3	52
Connecticut	118	3.49	72.9	50
Delaware	217	2.99	75.6	52
Florida	242	3.29	48.6	72
Georgia	295	2.89	37.8	64
Idaho	85	3.39	43.2	46
Illinois	114	3.35	64.8	52
Indiana	184	3.19	54	52
Iowa	104	3.21	43.2	50
Kansas	143	3.17	45.9	56
Kentucky	230	3.05	35.1	56
Louisiana	269	2.97	40.5	69
Maine	111	3.19	43.2	41
Maryland	217	3.11	56.7	54
Massachusetts	114	3.29	59.4	47
Michigan	108	3.25	56.7	47
Minnesota	108	3.31	48.6	41
Mississippi	248	2.98	27	65
Missouri	203	2.94	51.3	57
Montana	77	3.31	51.3	44
Nebraska	97	3.28	43.2	49
Nevada	166	3.19	64.8	48
New Hampshire	177	3.27	48.6	35
New Jersey	143	3.31	64.8	54
New Mexico	157	3.17	40.5	56
New York	111	3.43	67.5	48
North Carolina	330	2.89	35.1	59
North Dakota	63	3.33	37.8	39
Ohio	165	3.21	59.4	51
Oklahoma	184	3.19	43.2	82
Oregon	68	3.25	51.3	51
Pennsylvania	121	3.31	54	50
Rhode Island	138	3.23	54	50
South Carolina	237	2.93	32.4	65
South Dakota	95	3.34	35.1	45
Tennessee	236	3.19	35.1	60
Texas	222	3.08	45.9	69
Utah	100	3.37	43.2	50
Vermont	64	3.36	43.2	44
Virginia	270	3.04	43.2	58
Washington	77	3.19	54	49
West Virginia	144	3.11	40.5	55
Wisconsin	97	3.38	51.3	46
Wyoming	102	3.31	51.3	46

QUESTIONS 1. Given the data, please construct the demand estimation for soft drink consumption in the United States by

(1) a multiple-linear regression equation and

(2) a log-linear (exponential) regression equation

2. Given the MS Excel output in Question 1, please compare the two regression equations’ coefficient of determination (R-square), F-test and t-test. Which equation is a good (better) fit? Which equation shows the stronger overall significance to predict the future demand? Which equation will you choose as a better estimation for quantity demanded? Which equation will you choose as a better estimation for elasticities? Explain your answer in the language of statistics.

Answer 1