Test the difference between the two means

There are many researches in which the comparison between two different population means using
Independent samples t-test.
The null hypothesis
H 0 : μ1=μ2
Where μ1 is the mean of the first sample and μ2 is the average of the second sample
While the alternative hypothesis
H 1 : μ 1< μ 2 H 1 : μ 1 ≠ μ2 H 1 : μ 1> μ 2
1) An experiment was conducted on two types of fruit (apples and oranges) to see if there is a difference
between the amount of sodium in the apple and the oranges? The data were as follows:
5.6
apples 4.86 5.11 5.23 5.19 5.32 5.2 4.95 4.98
1
orange 5.5
4.72 4.81 5.22 5.67 4.96 5.35 5.34  
s 2
Solution
Null Hypothesis: Average amount of sodium in apples = average amount of sodium in oranges
Alternate Hypothesis: Average amount of sodium in apples ≠ average amount of sodium in oranges
Data entry
First column: You must type two different
numbers to represent each type.
(1) can be used to represent the first type (apple)
and (2) can be used to represent the second type
(orange)
Second Column: The data collected should be
written in each case.

Data analysis
From the Analyze menu, choose compare means and then independent samples T-test

1
The following box appears

Move values in the test variables list

Groups are moved in the grouping variable

Definition of groups
Click the define groups button. To find out what the numbers are Type I (1) and Type II (2).
We used 1 to represent our first type and used 2 to represent the second type. Click the continue button when
you're finished.

2
Click the OK button when you're finished.
The OUTPUT window

Sig (2-Tailed) value

This value indicates if there is a statistically significant difference between the average of the two means.
 If the value is greater than 0.05 then there is no statistically significant difference (we accept null
hypothesis).
• If the value is less than 0.05 then there are statistically significant differences (we reject null
hypothesis).
P−value=0.789>0.05
Decision: we can accept H 0
Then there isn’t a statistically significant difference between the amount of sodium in the apple and the
oranges
2) A study was designed to test the difference in diastolic blood pressure readings between men and
women. Run a suitable stoical test.
Males 76 76 74 70 80 68 90 76 80 68 72 96 80
Females 76 70 82 90 68 60 62 60 62 72
Solution
H 0 : μmales =μfemales
H 1 : μ males ≠ μ females

Independent Samples Test

Levene's Test for t-test for Equality of Means
Equality of Variances

3
 95% Confidence
Interval of the
Sig. (2- Mean Std. Error Difference
F Sig. t df tailed) Difference Difference Lower Upper
pressure Equal variances .626 .438 1.888 21 .073 7.18462 3.80522 -.72877 15.09800
assumed
Equal variances 1.836 17.124 .084 7.18462 3.91424 -1.06914 15.43837
not assumed
P−value=0.073>0.05
Decision: we can accept H 0
Then there isn’t a statistically significant difference in diastolic blood pressure readings between men
and women
3) “Is the length of a steel bar affected by the heat treatment technique used?” This was the question
being tested when the following data were collected. Do you support this claim?
tech1 156 159 151 153 157 159 155 155 151 152
tech2 154 156 150 151 156 155 153 154 149 150
Solution
H 0 : μtech1=μtech 2
H 1 : μ tech 1 ≠ μtech 2

Independent Samples Test

Levene's Test for
Equality of Variances t-test for Equality of Means
95% Confidence
Interval of the
Sig. (2- Mean Std. Error Difference
F Sig. t df tailed) Difference Difference Lower Upper
technique Equal variances .108 .747 1.586 18 .130 2.00000 1.26139 -.65009 4.65009
assumed
Equal variances 1.586 17.656 .131 2.00000 1.26139 -.65380 4.65380
not assumed
P−value=0.130>0.05
Decision: we can accept H 0 (there isn’t a statistically significant difference between mean of tech1 and
tech1)
the length of a steel bar i s n ’ t affected by the heat treatment technique used
ANOVA Test Using SPSS

4
If the comparison is between two different population means using Independent samples t-test., then the
comparison between means of 3 groups or more, we use the ANOVA test and the hypotheses are as follows:
H0: μ1=μ 2=μ3=…=μn
The means of all the groups are equal
H 1 : at least two are different
doesn’t say how or which ones differ
Example: 25 patients with Blood Disease Treatments: Treatment A, Treatment B, Treatment C
Data Means
numbers of days until A: 5,6,6,7,7,8,9,10 7.25
recover B: 7,7,8,9,9,10,10,11 8.875
C: 7,9,9,10,10,10,11,12,13 10.11
overall mean 8.8
Are there differences significant? Test whether the Treatment has an effect on the mean of days
4) To study the effect of temperature on yield in a chemical process, five batches were produced at each
of three temperature levels. Test whether the temperature level has an effect on the mean yield of the
process.
32 39 36 24 34 C 50°
27 23 34 31 30 C 60°
31 30 28 28 23 C 70°
Solution
Data Entry
First column: You must type two different numbers
to represent each type.
(1) can be used to represent the first type (50° C)
(2) can be used to represent the second type (60° C)
(3) can be used to represent the third type (70° C)
Second Column : The data collected should be
written in each case.

Data analysis

5
 From the Analyze menu, choose compare
means and then One-Way ANOVA

Move values in the Dependent List and Groups

are moved in the Factor
Click the OK button when you're finished.

The OUTPUT window

P−value=0.210>0.05
We can accept H0 (no statistically significant difference), Then the temperature level did not affect the
average yield of the crop
5) Auditors must make judgments about various aspects of an audit on the basis of their own direct
experience, indirect experience, or a combination of the two. In a study, auditors were asked to make
judgments about the frequency of errors to be found in an audit. The judgments by the auditors were
then compared to the actual results. Suppose the following data were obtained from a similar study;

6
 lower scores indicate better judgments. Test to see whether the basis for the judgment affects the quality
of the judgment.

Direct 18.5 15.8 17.0 18.2 20.2 16 13.3

Indirect 22.2 20.5 16.6 18.3 24.2 19.8 21.2
Combination 24.0 21.5 25.2 26.8 27.5 25.8 24.2
Solution
H 0 : μD ir ec t =μI n d i r e ct =μC o m b i n a t i o n
H 1 : at least two are different

ANOVA
Sum of Squares df Mean Square F Sig.
Between Groups 151.204 2 75.602 6.895 .006
Within Groups 197.374 18 10.965
Total 348.578 20
P−value=0.006<0.05
Decision: reject H 0
6) Four different paints are advertised as having the same drying time. To check the manufacturer’s claims, five
samples were tested for each of the paints. The time in minutes until the paint was dry enough for a second
coat to be applied was recorded. Test to see whether the mean drying time is the same for each type of paint.

Paint 1 128 137 135 124 141

Paint 2 144 133 142 146 130
Paint 3 133 143 137 136 131
Paint 4 150 142 135 140 153
Solution
H 0 : μP ai nt 1 =μ P a i nt 2=μ P a i nt 3=μ P a i nt 4
H 1 : at least two are different

ANOVA
drying
Sum of Squares df Mean Square F Sig.
Between Groups 330.000 3 110.000 2.543 .093
Within Groups 692.000 16 43.250
Total 1022.000 19
P−value=0.093>0.05
Decision: We can’t reject H 0