TEST OF DIFFERENCE

BETWEEN MEANS
4TH QUARTER STATISTICS AND PROBABILITY
WEEK 2
 T-TEST
 the most common used
method to evaluate the
difference in means between
two groups.
 SIGNIFICANCE
-defined as the quality of being statistically significant.
 LEVEL OF SIGNIFICANCE
-denoted by alpha or refers to the degree of significance in which we accept or reject
the null hypothesis.
- 100% accuracy is not possible in accepting or rejecting a hypothesis.
- the significance level is also the probability of making the wrong decision when the null
hypothesis is true.
-In public health research alpha is usually 0.01 or 1%. In social science, alpha is usually
0.05 or 5% and 0.10 or 10% in other studies
- This implies that there is 1%, 5% or 10% probability of rejecting a true null hypothesis.

In symbol, it is written as:

=0.05
 TWO TYPES OF T-TEST:
1. T-test for one sample case
2. T-test of two sample case
 T-TEST FOR ONE SAMPLE CASE
 It is used in determining the significance difference between the sample mean form
and the standard mean/population mean.
FORMULA:

Where:
t-ratio = t-test
= standard mean/population mean
= sample mean
= standard error

sd = standard deviation
n = sample size
 DECISION RULE:
 If the computed t-valuet-critical value at and level of
significance; Accept Ho; and
 If the computed t-valuet-critical value at and level of
significance; Reject Ho
EXAMPLE:
Is there any significance difference in the sample mean of 10mg nicotine in blood stream
of 100 patients who are cigarettes smokers compared with that of the standard mean of 15mg
nicotine content in the blood stream of normal cigarettes error with 4.58 standard deviation? Use
alpha at 0.05.

Ho: mg nicotine

Ha: mg nicotine

SOLUTION:
SOLUTION FOR STANDARD ERROR SOLUTION FOR T-TEST

-10.92

Computed T-test Degree of Freedom T-critical Value at

Value alpha= 0.05 level of Interpretation Decision
significance
10.92 99 1.980 With significant Reject Ho
Difference
 EXAMPLE:
The average number of milligrams (mg) of cholesterol in a cup of a certain brand
of ice cream is 660 mg. A researcher randomly selected 10 cups of ice cream and determine an
average of 670 mg of cholesterol with standard deviation of 35mg. Is there any significant
difference between the population mean and the sample mean? Use alpha 0.05 level of
significance.

SOLUTION:
 SOLUTION FOR T-TEST
SOLUTION FOR STANDARD ERROR

Computed T-test Degree of Freedom T-critical Value at Interpretation Decision

Value alpha= 0.05 level of
significance

Without ACCEPT
0.903 9 2.262 Significant
Difference
 T-TEST OF TWO SAMPLE CASE
 It Is divided to two types
(a.)t-test of independent sample;
(b.) t-test for dependent sample.
FORMULA FOR T-TEST OF INDEPENDENT SAMPLE
(if the data is taken from two groups)

Where:
DECISION RULE:
 If the computed t-value<t-critical value at and level of
significance; ACCEPT Ho; and
 If the computed t-value>t-critical value at and level of
significance; REJECT Ho; and
EXAMPLE: Is there any significant difference in the Mathematics performance of the
students when grouped according to their gender profile? Use alpha at 0.05 (Data as
follows)

No Male Female
1 1.5 1.25
2 1.5 1.75
3 2 2.25
4 2.5 2
5 2.5 1.25
TOTAL:
MEAN
SOLUTION: COMPLETE THE TABLE
No Male Female
1 1.5 1.25 2.2500 1.5625
2 1.5 1.75 2.2500 3.0625
3 2 2.25 4.0000 5.0625
4 2.5 2 6.2500 4.0000
5 2.5 1.25 6.2500 1.5625
TOTAL: 10 8.5 21 15.25
MEAN:
2 1.7

NEEDED INFORMATION:
Computed T-test Degree of Freedom T-critical Value at alpha
Value =0.05 level of Interpretation Decision
significance
1.00 8 2.306 Without Significant Accept Ho
Difference
 FORMULA of T-Test of dependent Sample (If the data is taken from the same
group)

Where:
D = Difference between each data
n = sample population
DECISION RULE:
If the computed t-value < t-critical value at and level of significance; ACCEPT Ho;
If the computed t-value > t-critical value at and level of significance; REJECT Ho;
 EXAMPLE: Is there a significant difference in the learning process of the students based
from their pre-evaluation and post-evaluation conducted by their teacher? Use alpha at
0.05 (Data as followed).
Student No. Pre- Evaluation Post-Evaluation D
1 25 28
2 23 19
3 30 34
4 7 10
5 3 6
6 22 26
7 12 13
8 30 47
9 5 16
10 14 9
TOTAL:
MEAN:
SOLUTION: COMPLETE THE TABLE.
Student No. Pre- Evaluation Post-Evaluation D(pre-post)
1 25 28 -3 9
2 23 19 4 16
3 30 34 -4 16
4 7 10 -3 9
5 3 6 -3 9
6 22 26 -4 16
7 12 13 -1 1
8 30 47 -17 289
9 5 16 -11 121
10 14 9 5 25
TOTAL: -37 511
MEAN: -3.7
Needed information:
Computed T-Test Degree of Freedom T-critical Value at
Value alpha=0.05 level of Interpretation Decision
significance

With Significant
1.81 8 2.306 Difference ACCEPT Ho
 CHALLENGE YOURSELF:
1. Is there any significant difference in the sample mean of 35 average students per classroom for 90 students to
the standard mean of 38 average students for classroom with standard deviation of 2? Use alpha at 0.05
2. Is there any significant difference in the performance in Statistics and Probability of the students when grouped
according to their gender profile? Use alpha at 0.05 (Data as follows).
No. Male Female 
1 80 81
2 83 82
3 78 85
4 84 76
5 90 90
6 88 89
7 82 79
8 85 78
9 89 91
10 82 92

TOTAL:
MEAN:
THANK YOU!!
BREAK