Professional Documents
Culture Documents
Type of Measurement Differences between two independent groups Differences among three or more independent groups
One-way ANOVA
Type of Measurement
Ordinal
Kruskal-Wallis test
Type of Measurement
Nominal
Chi-square test
Type of Measurement
Nominal
Chi-square test
Chi-Square Test
(Oi Ei ) x = Ei
x = chi-square statistics Oi = observed frequency in the ith cell Ei = expected frequency on the ith cell
60
Null hypothesis- equal number of men and women are aware of the brand. Brand awareness is independent of the respondants gender.
Chi-Square Test
Eij =
Ri C j n
Ri = total observed frequency in the ith row Cj = total observed frequency in the jth column n = sample size
Expected frequency can be calculated as follows: E11 = (60)(65)/100= 39 E12 = (60)(35)/100= 21 E21 = (40)(65)/100= 26 E22 = (40)(35)/100= 14
Aware Unaware
d . f . = ( R 1)(C 1) d . f . = (2 1)(2 1) = 1
Critical value at the 0.05 probability level with 1 d.f. is 3.84. Thus null hypothesis is rejected, because 22.161 is much greater than 3.84. Brand awareness is dependent of the respondants gender.
Type of Measurement
t-test or Z-test
z-test
When groups are large
= 1 2
O R
=0 1 2
1 2 t= S X1 X 2
X1 = mean for Group 1 X2 = mean for Group 2 SX1-X 2 = the combined standard error of difference between means.
S X1 X 2
2 ( n1 1) S12 + (n2 1) S 2 ) 1 1 + = n n n1 + n2 2 2 1
S 2 = the variance of Group 1 S 2 = the variance of Group 2 n1 = the sample size of Group 1 n2 = the sample size of Group 2
1 2
A researchers wants to test the difference between sociology majors and business majors on scores on a scale measuring attitude towards business. Assume attitude scale is an interval scale. High score equals a favorable attitude toward business. The null hypothesis is that there is no difference in attitude toward business between the two groups.
Business Students
16.5 1 =
Sociology Students
= 2
12.2
S1 =2.1 n1= 21
S2 =2.6 n2= 14
S X1 X 2
1 1 + 21 14
= .797
Degrees of Freedom
d.f. = n - k
where:
The calculated t of 5.39 far exceeds the critical value of t for statistical significance. The null hypothesis is that there is no difference in attitude toward business between the two groups. FALSE Null hypothesis is rejected.
Type of Measurement
Nominal
Ho : 1 = 2
or
Ho : 1 2 = 0
( p1 p2 ) (1 2 ) Z=
S p1 p2
S p1 p2 =
1 1 pq n n 2 1
n1 p1 + n2 p2 p= n1 + n2
p1-=0.35
p2= 0.40
n1= 100
n2= 100
100 + 100
S p1 p2
( .35 .40) ( 0) Z=
0.068
Z = - 0.73 Here, Null hypothesis will be accepted as calculated Zvalue is less than the absolute critical Z- value of 1.96.
Type of Measurement
Interval or ratio
Analysis of Variance
Hypothesis when comparing three groups
SStotal = ( X ij X )
i = 1 j =1
SSwithin = ( X ij X j )
i = 1 j =1
SSbetween = n j ( X j X )
j =1
MSbetween
SSbetween = c 1
MS within
SS within = cn c
MSbetween F= MSwithin
Null Hypothesis- All the price treatment produces the same sales volume.
Degrees of freedom
c-1 where c=number of groups
Mean squared-MSbetween
SSbetween/c-1
Degrees of freedom
cn-c where c=number of groups, n= number of observations in a group
Mean squared-MSwithin
SSwithin/cn-c
Degrees of Freedom
MSBETWEEN F= MSWITHIN