Suppose we want to find out if a relationship exists between the

height and weight of 20 SKSU MAT English Students. Test at

level of significance.

Student x y
Height (cm) Weight ( kg)
1 170 72
2 172 70
3 158 60
4 165 73
5 180 85
6 195 98
7 183 78
8 175 76
9 182 82
10 190 90
11 165 75
12 184 80
13 194 90
14 176 78
15 182 84
16 178 80
17 180 82
18 168 76
19 157 64
20 185 85
 APA REPORTING STYLE

t df p r interpretation
Height x 10.76 19 2.8E-09 0.93 Significant /Very
Weight strong or high
correlation

If , reject the null hypothesis.

If , accept the null hypothesis.

Or

F df p r interpretation
Height x 115.84 19 2.8E-09 0.93 Significant /Very
Weight strong or high
correlation

r-computed value Adjectival Equivalent

± 1.00 Perfect correlation/relationship
± 0.91 to ± 0.99 Very strong or high correlation/relationship
± 0.71 to ± 0.90 Strong or high correlation/relationship
± 0.41 to ± 0.70 Moderate or substantial correlation/relationship

± 0.21 to ± 0.40 Slight correlation/relationship

± 0.01 to ± 0.20 Very low or very weak correlation/relationship
0.00 No correlation/relationship
EXAMPLE 2

It is very observable that people living below poverty line have less
access to good food and thus, it is very possible that their meat
protein intake are significantly less than those living above the
poverty level . but no one has actually made a research on this. So ,
one day a group of nutrition students conducted a survey and
collected the following data in grams.

Below Poverty Level Above Poverty Level

62.1 90
69.1 90
66.6 75.5
73.3 59.1
72.9 83.7
65.5 70.2
67 64.1
67.2 66.5
65.9 89
64.3 83.8
72.9 82.9
61.3 88.6
68.5
64.6
71.2

At 5% significance level , do the data provide sufficient evidence to

conclude that the mean protein intake of all people with incomes
below poverty level is less than the mean protein intake of all people
with incomes above poverty level?
 ̅̅̅ ̅̅̅

Group n mean sd df t p interpretation

Below 15 67.5 3.81 13 -3.32 0.002781372 Significant
Poverty
Level
Above 12 78.6 11.11
Poverty
Level

Note: When the sample size are small and the variances of the
populations where the samples come from cannot be ascertained to
be statistically equal, then the variances will not be pooled and the
degrees of freedom is computed by following formula:

( )

( ) ( )

Note the validity of the t-statistic depend on the normality of the

populations where the samples come from. To test the normality,
two tests are commonly used by the statisticians and these are
Kolomogorv –Smirmov Test and Shapiro Wilk Test.
EXAMPLE 3

A comparison on costs when one is confined in private hospitals in

Region A and Region B revealed the following data:

Region A Region B
6808 6334
7044 5922
7106 6007
7016 5899
7028 6090
7189 5927
7061 5903
7045 5803
7448 6291
7187 5920
6694 6109
6875 6181
7302 5761
6706 6094
6766 5999
7247 5795
6155
6287
6048
6064

Do the data provide a sufficient evidence to conclude that there is

difference between the mean cost when confined in private per
patient per day in region A and B? Perform the appropriate test at
the 0.05 significance level?
Group n mean sd df t p interpretation
Region 18 7049.78 218.15 36 16.38 2.91399E- Significant
A 18
Region 20 6029.45 166.81
B

EXAMPLE 3
It is widely known that dieting and following an exercise
program can reduce weight . Suppose than an experiment is
run in the following manner to a group of overweight women
aged 30 to 40 years old
Group A- diets without enrolling into an exercise program
Group B- enrolls in an exercise program but does not observe
diet management
Group C- does diet and enroll in an exercise program
Group D- neither diets nor enrolls exercise program
Let us assume there are 20 gorgeous overweight women in
each of these groups aged 30 to 40 years old . On day 1 their
body weights were measured and after 30 days into the
program , their body weights were again measured and the
difference of the previous weight minus recent weight was
recorded in kilograms (kg). The Table below summarizes the
results of the experiment. Perform an analysis at 0.05 level of
significance.
Group A Group B Group C Group D
-5.1 -1.8 -8.2 2.7
-4 -0.6 -7.2 3.8
-12.6 -9.6 -14.6 -4.8
-8.2 -5.1 -10.9 -0.4
-5.3 -2 -8.4 2.5
-3.5 -0.1 -6.8 4.3
1.3 5 -2.7 9.1
-13.1 -10.2 -15.1 -5.3
-5.4 -2.2 -8.5 2.4
-3.7 -0.3 -7 4.1
-10.3 -7.3 -12.7 -2.5
-5.2 -1.9 -8.2 2.6
-6.9 -3.7 -9.8 0.9
-13.3 -10.5 -15.3 -5.5
-8.1 -4.9 -10.8 -0.3
-3.9 -0.5 -7.1 3.9
-6.2 -2.9 -9.1 1.6
-5.8 -2.5 -8.8 2
-9.1 -6 -11.7 -1.3
-7.9 -4.7 -10.6 -0.1
 df ss ms F p Interpretation
Treatment 3 1255.10 418.36 32.78 1.06025E- significant
13
Error 76 970.07 12.76
Total 79 2225.1

* level of significance

According to NSCB statistics the life expectancy of Filipino women is

70.1 years. Suppose that a random sample of 30 women in town
Town B, yield the following data below. Would you say that the life
expectancy of the women in Town B is greater than the national
average? Use level of significance.

77.6 68.2 63 66.7 68.1 78.4 66.9 72.1 65.5 70

67.8 74.3 75.6 76.1 66.9 81.1 66.8 74.8 80 75.5
76.1 75.6 69.8 69.7 77 75.7 77 74 71.9 72.9