3. Parametric test
A statistical test, in which specific assumptions are
made about the population parameter is known as
parametric test.
4. when to use parametric test?
To use parametric test; the following Four conditions
have to be satisfied:
-Data must be in Interval scale.
-Data must be in ratio scale.
-Subjects should be randomly selected.
_Data should be normally distributed.
5. Determination of parametric test
Interval scale: interval between observation in terms
of fixed unit of measurement. Eg. Measures of
temperature.
Ratio scale: The scale has a fundamental zero point.
Eg. Age, income.
(IN CASE OF NOMINAL AND ORDINAL SCALE NON-
PARAMETRIC TEST IS USED)
6. Parametric VS Non Parametric test
.
PARAMETRIC •NON-PARAMETRIC
Specific assumptions are made
regarding the population
•No specific assumptions are made
regarding the population
Parametric test is powerful if it is exists •Not powerful like parametric test
Test statistics based on distribution •Test statistics is arbitrary
•No parametric test exists for nominal
scale data
•Central measure - mean
•Can draw more conclusions
•Non parametric test exists for nominal
scale data
•Central measure - median
•Simplicity , not affected by outliers
7. Contd.
Two sampled t-test Mann-whitney test
Paired t test Wilcoxon signed rank test
Anova Kruskal _wallis test
8. TYPES of parametric tests
1.Large samplel tests.
Z test
2. Small sample test
t-test
Independent /unpaired – t test
Paired t-test
ANOVA(analysis of variance)
one way analysis of variance
Two way analysis of variance.