In: Statistics and Probability
Ten randomly selected people took an IQ test A. The next day they took a very similar IQ test B. Their scores are shown in the table below.
Person | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 |
Test A | 106 | 99 | 95 | 92 | 87 | 127 | 115 | 100 | 77 | 108 |
Test B | 112 | 101 | 99 | 96 | 90 | 130 | 112 | 99 | 80 | 112 |
1. Use a 0.05 significance level to test the claim that, on
average, people do better on the second test than they do on the
first.
(a) State the null and alternative hypotheses. (Type
muD for the mean of the differences in test A -
test B.)
H0 :
H1 :
(b) Find the rejection region.
Reject H0 if t<
(c) Find the test statistic. (If necessary, round the sample mean
and sample standard deviation to 2 decimal places. Also round your
final answer to 2 decimal places.)
t =
(d) Do these samples provide significant evidence that, on average,
people do better on the second test than they do on the first?
(Type: Yes or No )
2. Construct a 95% confidence interval for the mean of the
differences in test A - test B. (Round your final answer to 2
decimal places.)
( , )
(a)
= mean of the differences in test A - test B
claim on average, people do better on the second test than they do on the first. : Test B > Test A i.e Test A -Test B < 0
< 0
Ho : = 0
Ha : < 0
Left tail test
(b) Find the rejection region.
Number of persons = Sample size : n=10
Degrees of freedom : n-1 = 10-1 =9
Significance level = 0.05
Critical value of left tailed test : -t0.05
For 9 degrees of freedom t0.05 = 1.833
Critical value of left tailed test : -t0.05 = -1.833
Reject H0 if t < -1.860
c) Find the test statistic. (If necessary, round the sample mean
and sample standard deviation to 2 decimal places. Also round your
final answer to 2 decimal places.)
di : Sample differnce in test score of student i (Test A - Test B)
Sample mean difference :
Sample standard deviation of difference
Person | Test A | Test B | d | (d-) | (d-)2 |
1 | 106 | 112 | -6 | -3.5 | 12.25 |
2 | 99 | 101 | -2 | 0.5 | 0.25 |
3 | 95 | 99 | -4 | -1.5 | 2.25 |
4 | 92 | 96 | -4 | -1.5 | 2.25 |
5 | 87 | 90 | -3 | -0.5 | 0.25 |
6 | 127 | 130 | -3 | -0.5 | 0.25 |
7 | 115 | 112 | 3 | 5.5 | 30.25 |
8 | 100 | 99 | 1 | 3.5 | 12.25 |
9 | 77 | 80 | -3 | -0.5 | 0.25 |
10 | 108 | 112 | -4 | -1.5 | 2.25 |
Total | -25 | 62.5 | |||
Mean: | -25/10-=-2.5 | (d-)2 = 62.5 |
Test Statistic t = -3.00
(d) Do these samples provide significant evidence that, on average, people do better on the second test than they do on the first? (Type: Yes or No )
Answer : Yes
As Calculated Value of t is less than Critical Value i.e. ( -3.0<-1.833 ); Reject Null Hypothesis. There is sufficient evidence to conclude that the difference < 0 i.e people do better on the second test than they do on the first
2. Construct a 95% confidence interval for the mean of the
differences in test A - test B. (Round your final answer to 2
decimal places.)
( , )
Formula for confidence interval for the mean of the differences
for 95% confidence interval = (100-95)/100 =0.05
/2 = 0.05/2 =0.025
t/2,n-1 = t0.025,9 = 2.2622
95% confidence interval for the mean of the differences in test A - test B.
95% confidence interval for the mean of the differences in test A - test B (-4.39,-0.62)
Answer
(-4.39,-0.62)