Question

A construction firm frequently estimates the amount of work accomplished on a construction site by a visual estimate of the amount of material used per day. The firm wanted to determine whether the accuracy of the estimates depended on the type of site. Two types of sites were considered: a high-rise building and a large one-story building. The firm employed hundreds of supervisors and randomly selected nine to participate in the study. Each supervisor approximated the number of bricks used in a given day at both sites. The difference (in thousands of bricks) between the approximation and the actual number of bricks used is recorded in the following table.

Supervisor        1          2          3          4          5          6          7          8          9

High-rise           0.9     1.1 0.7       0.3       1.3       1.6       -0.8       1.4      1.7

One-story       -1.6       2.5       1.1     -1.0 1.7   1.4       1.9       1.8       1.9

Answer 1

data

High-rise	One-story
0.9	-1.6
1.1	2.5
0.7	1.1
0.3	-1
1.3	1.7
1.6	1.4
-0.8	1.9
1.4	1.8
1.7	1.9

Using Excel

data -> data analysis -> t-Test: Paired Two Sample for Means

t-Test: Paired Two Sample for Means
	High-rise	One-story
Mean	0.911111	1.077778
Variance	0.608611	1.984444
Observations	9	9
Pearson Correlation	0.184515
Hypothesized Mean Difference	0
df	8
t Stat	-0.33806
P(T<=t) one-tail	0.372009
t Critical one-tail	1.859548
P(T<=t) two-tail	0.744017
t Critical two-tail	2.306004

TS = -0.33806

p-value for 2-tailed test is 0.744

since p-value > alpha

we fail to reject the null hypothesis

we conclude that the accuracy of the estimates does not depend on the type of site.