In: Statistics and Probability
In an effort to determine the cost of air conditioning, a resident in College Station,TX, recorded daily values of the variables
Tavg = mean temperature
Kwh = electricity consumption
for the period from September 19 through November 4.
tavg kwh tavg kwh tavg kwh tavg kwh
77.5 45 77.5 55 68 50 75 41
80 73 79 57 66.5 37 75.5 51
78 43 80 68 69 43 71.5 34
78.5 61 79 73 70.5 42 63 19
77.5 52 76 57 63 25 60 19
83 56 76 51 64 31 64 30
83.5 70 75.5 55 64.5 31 62.5 23
81.5 69 79.5 56 65 32 63.5 35
75.5 53 78.5 72 66.5 35 73.5 29
69.5 51 82 73 67 32 68 55
70 39 71.5 69 66.5 34 77.5 56
73.5 55 70 38 67.5 35
(a) Give and interpret a 98% confidence interval for ?.
(b) Give and interpret a 90% confidence interval for ?1.
(c) Give and interpret a 90% interval for the average electrify consumption for days that are 79 degrees Fahrenheit.
(d) Tomorrow it is supposed to be an average of 67 degrees Fahrenheit in College Station, TX. Predict tomorrow's electricity consumption using a 90% interval.
(e) Run an appropriate hypothesis test to determine if there is statistically significant evidence that the average electricity consumption changes with the mean daily temperature.
Regression
Regression Equation
Kwh = -97.92 + 2 * tavg
Y = α + β1 X
a)
At alpha = 0.02,
df = 47-1 = 46
tCritical = 2.404
Hence, 98% CI for α = -97.22 +/- 2.404 * 13.86 = {-131.25, -64.6}
Interpretation
There is 98% Probability that the true mean value of α lies in the interval {-131.25, -64.6}
b)
At alpha = 0.1,
df = 47-1 = 46
tCritical = 1.676
Hence, 90% CI for β1 = 2 +/- 1.676 * 0.19 = {1.68, 2.32}
Interpretation
There is 90% Probability that the true mean value of β1 lies in the interval {1.68, 2.32}
c)
When, tavg = 79,
Using the Regression Equation
Kwh = -97.92 + 2 * 79 = 60.16
At alpha = 0.1,
df = 47-1 = 46
tCritical = 1.676
Hence, 90% CI for Kwh = 60.16 +/- 1.676 * 8.39 = {46.1, 74.21}
Interpretation
There is 90% Probability that the true mean value of Kwh lies in the interval {46.1, 74.21}
d)
When, tavg = 67,
Using the Regression Equation
Kwh = -97.92 + 2 * 67 = 36.14
At alpha = 0.1,
df = 47-1 = 46
tCritical = 1.676
Hence, 90% CI for Kwh = 36.14 +/- 1.676 * 8.39 = {22.09, 50.20}
e)
From the Regression Output, r = 0.8426
alpha = 0.05
Null and Alternate Hypothesis
H0: Sigma = 0
Ha: Sigma <> 0
Test Statistic
t = r * (n-1)1/2 / (1-r2)1/2 = 10.61
P-value = TDIST(10.61,46,2) = 0.00000000000006
Since, the p-value is less than 0.05, we reject the null hypothesis ie there is significant correlation between the two variables ie electricity consumption changes with the mean daily temperature.