Scribd
Upload
57 views3 pages

Hypothesis Testing

This document outlines a study to analyze the relationship between gender and monthly expenditures. It proposes using ANOVA analysis with gender as the independent variable and expenditures as the dependent variable. It checks the assumptions of ANOVA, including normality of expenditures using the Kolmogorov-Smirnov test and homogeneity of variance. The ANOVA results show no significant difference between gender and expenditures, so the null hypothesis of no difference is accepted.

Uploaded by

AQUIF IBRAR
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
57 views3 pages

Hypothesis Testing

This document outlines a study to analyze the relationship between gender and monthly expenditures. It proposes using ANOVA analysis with gender as the independent variable and expenditures as the dependent variable. It checks the assumptions of ANOVA, including normality of expenditures using the Kolmogorov-Smirnov test and homogeneity of variance. The ANOVA results show no significant difference between gender and expenditures, so the null hypothesis of no difference is accepted.

Uploaded by

AQUIF IBRAR
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
You are on page 1/ 3

To check relation between Gender and their monthly expenditure

Iv= Gender(Non Metric)


DV= Expenses(Metric)

Hypothesis
Null Hypo: There is no significant difference between the mean score of their
expenditure in MBA first year for
various category of gender.
Alt. Hypo: There is significant difference between the mean score of their
expenditure in MBA first year for
various category of gender.
Test Rule: if P value is less than 0.05 (95%confidence interval) reject null
if P value is more than 0.05 (95%confidence interval) accept null

In order to test the above mentioned Hypo we will use ANNOVA method as IV=Gender is
categorical & DV=Eexpenditure (non metric)
In order to run annova we need to check following assumption
>>Test of variability, which can be check using plot diagram or statistical
measures like Standard deviation and variance.
How to check?
step 1 go to analyse then descriptives, then Descriptive Statistics

N Minimum Maximum Mean Std. Deviation Variance


Expenditure 47 450 32000 6328.72 6028.273 36340080.944
Valid N (listwise) 47

>> Test of Normality (1 sample KS test), we need to check normality of dependent


variable( expenditure) for various categories of IV which is gender
test rule: If significance value( p value is greater than 0.05 then data is
normally distributed)

OBSERVATION
One-Sample Kolmogorov-Smirnov Test
Expenditure
N 47
Normal Parametersa,b Mean 6328.72
Std. Deviation 6028.273
Most Extreme Differences Absolute .289
Positive .289
Negative -.194
Kolmogorov-Smirnov Z 1.984
Asymp. Sig. (2-tailed) .001

a Test distribution is Normal.


b Calculated from data.

STEPS
ANALYZE-DESCRIPTIVE STATISTICS-EXPLORE-PLOT-CHECKMARK NORMALITY PLOT WITH TESTS
NOTE: if distribution is not normal then you can go check the count of categories
if they are equal or close to equal you can proceed or else no ANNOVA test is
possible

>>Homogenity of Variance
STEP:Analyze-compare mean-One way Annova

Test of Homogeneity of Variances


Expenditure
Levene Statistic df1 df2 Sig.
4.002 1 39 .052
Test Rule: Significance value is greater than 0.05 hence data is homogenious

ANOVA
Expenditure
Sum of Squares df Mean Square F Sig.
Between Groups 14962703.833 1 14962703.833 2.910 .096
Within Groups 200554857.143 39 5142432.234
Total 215517560.976 40

p>0.05 accept the Null.

Chi Square test: king of non parametric tests(non metric, categorical


data[nominal,ordinal] data
Chi square test is a bi variante analysis, which checks the associations b/w 2 non
metric variables

Airlines.sav Data set


Purpose of study: is to check associations b/w professions of travellers and
airlines used by them
Var_1: proffession of travellers
Var_2: airlines used
Var_1 Professions
a)corporate
b)student
c)govt
Var_2 Airline
a)air india
b)spicejet
c)indigo
Null Hypo: There is no association (neither of them is dependent or indipendent)
b/w airlines preffered & profession of travellers
Alt. Hypo:
Test Rule if P value of chi Square analysis is less than 0.05 use will reject Null

Steps to do chi square analysis


step1: create cross tabulations for both the variables
Go to analyze
descriptives
-> crosstabs
It will ask you ROW(s) & COLUMN(s)
Click proff of traveler(Rows)
Airlines used(Columns)
Profession of traveler * Airlines used Crosstabulation
Count
Airlines used Total
Air India Spice Jet Indigo
Pro_T 35 45 38 118
Coprorate 26 21 13 60
Student 27 20 33 80
Total 88 86 84 258

Assumptions for Chi Sq test


>>Expected frequency of each of the 9 cell should be greater than 5(if less than 5
fisher test will apply)

Step 2
cell-check mark expected,observed value
Step 3
crosstabs-statistics-checkmark Chi-Square Test

Chi-Square Tests
Value df Asymp. Sig. (2-sided)
Pearson Chi-Square 8.764a 4 .067
Likelihood Ratio 8.948 4 .062
Linear-by-Linear Association .045 1 .832
N of Valid Cases 258
a 0 cells (0.0%) have expected count less than 5. The minimum expected count is
19.53.
Accept The Null(no association)

Objective2: No Association b/w Gender and airlines used


P vale of Chi-Square test= 0. 958
Accept the Null

Objective3:
Null:

You might also like