Scribd
Upload
4 views

estimated annual cost=^β year of initial operation+^β ε y=1.8705 x−3675.4833

Uploaded by

Jacob Sheridan
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
4 views

estimated annual cost=^β year of initial operation+^β ε y=1.8705 x−3675.4833

Uploaded by

Jacob Sheridan
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 1

Question 1

a) estimated annual cost= ^β 1∗year of initial operation+ ^β 0+ ε


b) y=1.8705 x−3675.4833
c) Mean zero, constant variance, normally distributed, independent
d) 2309.1
e) 230.9
f) 15.2
g) s is the standard error in the least squared regression line.
h) The 95% confidence interval goes from 1.05853 to 2.682401. This means that I can be 95%
confident that the true value for the slope is between 1.05853 and 2.682401.
i) Since p=0.000442 which is less than α =0.05 which means that it is statistically useful for
predicting the annual cost using the year of initial operation.
j) r 2=0.7249 This means that 72.49% of the error can be explained using this model.
k) The desired interval is a 95% confidence interval. This interval is from 17.0869 to 38.98911.
l) This interval means that you can 95% confident that the true value of the average annual cost of
all the military aircraft with the year of initial operation in 1980 is within that interval.

Question 2
a) SSE=1.0169 , s 2=0.046224 , s=0.215
b) σ 2 can be estimated by s2 which is equal to 0.046224
c) σ can be estimated by s which is equal to 0.215
d) It’s hard to give a practical explanation to s 2 because it’s hard to explain a squared unit.
e) s is the standard amount of error in the linear progression to predict sweetness.
f) The 90% confidence interval for the slope of the line is -0.003864436 to -0.0007568157. This
means that we can be 90% confident that the true slope of the line is in that interval.
g) The p-value is 0.0181 which is less than α . This indicates that ^β 1 is significantly different than
zero.
h) r 2=0.2286, r =0.4781. The coefficient of determination, r 2 describes how much of the error is
explained by the linear regression. In this case, it would be 22.86%
i) The 95% confidence interval for mean sweetness at x=300 is 5.437193 to 5.680568. This
indicates that there is a 95% confidence that the true mean value for sweetness at that value of
pectin is in that interval.
j) The 95% prediction interval for sweetness at x=300 is 5.096694 to 6.021066. This indicates
that there is a 95% confidence that the true value for sweetness at that value of pectin is in that
interval.

You might also like