Bonina, Janessa BSA-3A

Exercise 10

t-TEST

2. A social psychologist was interested in sex differences in the sociability of teenagers. Using
the number of good friends as a measure, he compared the sociability of eight female and
seven male teenagers. Test the null hypothesis of no difference with respect to sociability
between females and males.

Females Males
8 1
3 5
1 8
7 3
7 2
6 1
8 2
5

t-Test: Two-Sample Assuming Equal Variances

Variable 1 Variable 2
Mean 5.625 3.142857143
Variance 6.267857143 6.476190476
Observations 8 7
Pooled Variance 6.364010989
Hypothesized Mean Difference 0
df 13
t Stat 1.901120727
P(T<=t) one-tail 0.03984186
t Critical one-tail 1.770933396
P(T<=t) two-tail 0.079683719
t Critical two-tail 2.160368656

Decision Rule: Do not reject the null hypothesis because the computed value (1.90) is less
than the critical t-ratio (2.16) with 5% level of significance.
 3. Test for the significance of the before and after difference in mean typing speed (word/min) in
this random sample of students in a typing class. Use 5% level of significance.

Student Before After

A 18 39
B 15 30
C 10 21
D 12 10
E 9 20
Total 64 120

t-Test: Paired Two Sample for Means

Variable 1 Variable 2
Mean 12.8 24
Variance 13.7 120.5
Observations 5 5
Pearson Correlation 0.775276726
Hypothesized Mean Difference 0
df 4
t Stat -2.967994064
P(T<=t) one-tail 0.020613092
t Critical one-tail 2.131846786
P(T<=t) two-tail 0.041226185
t Critical two-tail 2.776445105

Decision Rule: Do not reject the null hypothesis because the computed value (-2.97) is less
than the critical t-ratio (2.78) with 5% level of significance.

4. A researcher believes that alcohol intoxication even half the legal limit, that is, 0.05 blood
alcohol instead of 0.10, might severely impair driving ability. To test this he subjects 10
volunteers to a drinking simulation test first while sober and then after drinking sufficient to
raise the blood alcohol level to 0.05. The researcher measures performance as the number of
simulated obstacles with which the driver collides. Thus the higher the number the poorer the
driving. The obtained results are as follows:

Driver Before After

A 1 4
B 2 2
C 0 1
D 0 2
E 2 5
F 1 3
G 4 3
H 0 2
I 1 4
J 2 3
 t-Test: Paired Two Sample for Means

Variable 1 Variable 2
Mean 1.3 2.9
Variance 1.566666667 1.433333333
Observations 10 10
Pearson Correlation 0.392980914
Hypothesized Mean Difference 0
df 9
t Stat -3.748170285
P(T<=t) one-tail 0.002283775
t Critical one-tail 1.833112933
P(T<=t) two-tail 0.00456755
t Critical two-tail 2.262157163

Decision Rule: Do not reject the null hypothesis because the computed value (-3.75) is less
than the critical t-ratio (1.75) with 5% level of significance.