Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 6

A taxi company is trying to determine whether the use of radial tires and belted tires

provide the same fuel consumption. Twelve cars were driven twice over a prescribed
test course; and for each test a car used a different type of tire (radial or belted) in
random order. The data obtained were recorded as follows:

Type o0f Tire x S


Radial 5.75 1.10
Belted 5.61 1.30

At 0.05 level of significance can we conclude that cars equipped with radial tires and
belted tires provide the same fuel consumption? Assume that the data are normally
distributed.
Solutions
Hypothesis Testing
1. State the null and the alternative hypotheses:
Ho: There is no significant difference on the fuel consumption of cars using radial
and belted tires
Ha: There is a significant difference on the fuel consumption of cars using radial
tires and belted tires

2. Specify the level of significance; determine the degrees of freedom and find the
Ttabular value at alpha = 0.05 using degrees of freedom of 22 based on df = n1 +n2 -2
= 12 + 12 – 2 = 22, we obtain the Ttabular value = 2.074 from the table.

3. Determine the test statistic to be used

t- test: two sample means

4. Compute the value of the Tcomputed

x1- x2
Tcomputed = _______________________________

S12 [(n1- 1)] +[{S22(n2 - 1)] 1 + 1


(n + n2) - 2 n n2
5.75 – 5.61
= [ (1.10) 2 ( 12 – 1) + [ (1.3)2 ( 12 – 1) 1 + 1
12 + 12 - 2 12 12

= 0.14 = 0.14
[ 13.31 + 18.59 ] 1 (1.45)_ (0.1667)
22 6

= 0.14 = 0.14
0.4916
0.2417

= 0.2848
ANALYSIS OF VARIANCE
Analysis of variance (ANOVA) is used to test hypothesis about the differences
between two or more means. The t – test based on the standard error of the
differences between two means can only be used to test differences between two
means. When there are more than two means, it is possible to compare each mean
with other using t – test. But, conducting multiple t – tests can lead to the increase of
the Type 1 error rate. Analysis of variance can be used to test differences among
several means for significance without increasing the Type 1 error rate.
The key statistics in ANOVA is the F – test of difference of group means, testing
if the means of the group formed by values of independent variables (or combinations of
values for multiples independent variables) are different enough to have occurred by
chance. If the group means do not differ significantly, then it is said that the
independent variables did not have an effect on the dependent variable. If F-test shows
that the overall independent variable(s) is(are) related to the dependent variable, then
multiple comparison tests of significance are used to explore just which groups of the
independent(s) have the most to do with the relationship.
ANOVA focuses on the F-test of significance of differences in group means. If
one has an enumeration rather than a sample, then any difference of means is “real”.
However, when ANOVA is used for comparing two or more different samples, the real
means are unknown. If the research wants to know if the difference in sample means is
enough to conclude that the real means do in fact differ among two or more groups, the
answer depends on:
1. the size of the difference between group means;
2. the sample sized in each group – larger sample sizes are
more reliable and
3. the variance (S2) of the variable
ONE-WAY ANOVA
One-way ANOVA tests differences in a single interval dependent variable among
two, three, or more groups formed by the categories of a single categorical independent
variable. Also known as univariate ANOVA, simple ANOVA, single classification
ANOVA, or one-factor ANOVA, this design deals with one independent variable and one
dependent variable. It tests whether the groups formed by the categories of the
independent variable seem similar. If the groups seem different, then it is concluded
that the independent variable has an effect on the dependent variable.
Analysis of variance assumes normal distributions and homogeneity of variance.
Therefore, in a one-factor/ one-way ANOVA, it is assumed that each of the populations
is normally distributed with the same variance, in between-subjects analysis. It is
assumed that each score is sampled randomly and independently.
THE F – TEST
F – test is the ratio of the variable estimates:
MSb
F = _____
MSw
Where:
MSb = mean square between
MSw = mean square within
To solve for F, we have to solve for the sum of squares (SS) using the:
a. Deviation method
b. Raw score method
EXAMPLE: The following are the IQs of random samples of students from 3 large
schools:
School 1 School 2 School 3
101 93 104
107 106 96
106 95 10 3
98 96 108
115 100 93

At 5% level of significance, test if there is a significant difference among the three


groups. Use the deviation method.
SOLUTIONS:
To perform the F – test, using the deviation method, the mean and the
variance of each group should be known.
School 1 School 2 School 3
101 93 104
107 106 96
106 95 10 3
98 96 108
115 100 93
X1 = 105.4 X2 = 98 X3 = 100.8
S12 = 54.3 S22 = 26.5 S32 = 37.7
n1 = 5 N2 = 5 n3 = 5

For the above example, the null hypothesis will be: there is no significant difference
among the means of the 3 schools.
Ho: µ1 = µ2 = µ3
And the alternative hypothesis will be: there is a significant difference among the
means of the 3 schools.
Ha: µ1 ≠ µ2 ≠ µ3

To solve for F, the means square (MS) should be computed.


For the mean square within (MSw), we use the equation:

S12 + S22 + S32 + …..Sn2


MSw = k
Where:
S2 = group variance
k = number of samples or groups
For this sample, S12 = 54.3; S22 = 26.5; S32 = 37.7 and k = 3
54.3 + 26.5 + 37.7
MSw = 3
= 39.5
For the mean square between (MSb) we used the equation:
∑(x – xG)2
MSb = m
K-1
Where:
m = number of observations in each sample / group
∑(x – xG)2 = summation of the squared deviation between the grand mean
and the mean of each group / sample
k = number of samples / groups
Hence, we have x1 = 105.4; x2 = 98; x3 = 100.8, the grand mean xG = 101.4; m = 5 and k
= 3.
(105.4 – 101.4)2 + (98 – 101.4)2 + (100.8 – 101.4)2
MSb = 5
3–1
= 5. (4) 2 + (-3.4)2 + (-0.6)2
2
= 5 (27.92)
2
= 69.8
Then, solve for F.
MSb 69.8
F = MS w 39.5
= 1.77
To determine if the computed F value is significant or not, the critical value should
be known. To find the critical value, compute for the degrees of freedom first. To
compute for the degrees of freedom use:
Dfb = k -1
Dfw = N – k
Since k = 3 and N = 15,
Dfb = 3 -1 = 2
Dfw = 15 – 3 = 12
Critical value at 5% level of significance with degrees of freedom at (2, 12) is 3.88
Since the computed F (1.77) is lesser than the critical value (3.88), then we
accept the null hypothesis and reject the alternative hypothesis. This means that there
is no significant difference among the IQs of the students from the 3 schools.

You might also like