![SPSS Test Primer(doesn’t include all required test)
Parametric Technique-Normally distributed
data
Nonparametric Technique-Not Normally
distributed data
One sample t-test H0: Average x = constant value One sample median test H0: Median x = constant value
Independent-samples t-test (2 groups only) H0: Average x for Group1 = Average x for
Group2
Mann-Whitney U Test(2 groups only) H0: Median x for Group1 = Median x
for Group2
Paired-samples t-test
(2 time periods or 2 dependent variables)
(dependent samples t test)
H0: Average x before = Average x after
H0: Average x at Time1 = Average x at Time2
Wilcoxon Signed Rank Test
(2 time periods or 2 dependent variables)
H0: Median x before = Median x after
H0: Median x = Median y
One-way between-groups ANOVA(3 or more groups) H0: Average x is equal among group1, group2,
group3 ……
Kruskal-Wallis Test(3 or more groups) H0: Median x is equal among
group1,group2,group3 ……
One-way repeated-measures ANOVA
(3 time periods or 3 dependent variables)
H0: Average x, y, z is equal(3 time periods) Friedman Test
(3 time periods or 3 dependent variables)
H0: Median x,y,z is equal
These has no nonParametric
alternatives
These has no Parametric
alternatives
Two-way analysis of variance (between groups) H0: effect of age on optimism is not
different for males and females?
Chi-square for goodness of fit H0: Proportions of var A for (x
=0.3), (y=0.25),(z=0.45)
Mixed between-within groups ANOVA Which intervention (maths skills/confidence
building) is more effective in reducing
participants’ fear of statistics, measured
across three periods (pre-intervention, post-
intervention, three-month follow-up)?
Chi-square for independence
Same as Fisher’s exact test
(one var have 5 or less as expected frequency)
H0: x is independent of y
H0:There is no association between x
and y
Multivariate analysis of variance (MANOVA) Are males better adjusted than females in
terms of their general physical and
psychological health (in terms of anxiety and
depression levels and perceived stress)?
McNemar Test H0: no significant change in
proportion of yes/no for x,y
H0:Proportion of yes/no at time1 =
proportion of yes/no at time2
Analysis of covariance Is there a significant difference in the Fear
of Statistics Test scores for participants in
the maths skills group and the confidence-
building group, while controlling for their
pre-test scores on this test?
Cochran’s Q Test
three or more time points[categorical var],
each with 2 values [yes,no]
H0: no significant change in
proportion of yes/no for x,y,z
H0:Proportion of yes/no at time1 =
proportion of yes/no at time2=
proportion of yes/no at time3
Kappa Measure of Agreement H0: no significant change in
proportion of yes/no/maybe for x,y
Other tests](https://image.slidesharecdn.com/1mainspssalltestsummarya3-200131194134/85/1-main-spss-all-test-summary-a3-1-320.jpg)
1 main spss all test summary (a3)
- 1. SPSS Test Primer(doesn’t include all required test) Parametric Technique-Normally distributed data Nonparametric Technique-Not Normally distributed data One sample t-test H0: Average x = constant value One sample median test H0: Median x = constant value Independent-samples t-test (2 groups only) H0: Average x for Group1 = Average x for Group2 Mann-Whitney U Test(2 groups only) H0: Median x for Group1 = Median x for Group2 Paired-samples t-test (2 time periods or 2 dependent variables) (dependent samples t test) H0: Average x before = Average x after H0: Average x at Time1 = Average x at Time2 Wilcoxon Signed Rank Test (2 time periods or 2 dependent variables) H0: Median x before = Median x after H0: Median x = Median y One-way between-groups ANOVA(3 or more groups) H0: Average x is equal among group1, group2, group3 …… Kruskal-Wallis Test(3 or more groups) H0: Median x is equal among group1,group2,group3 …… One-way repeated-measures ANOVA (3 time periods or 3 dependent variables) H0: Average x, y, z is equal(3 time periods) Friedman Test (3 time periods or 3 dependent variables) H0: Median x,y,z is equal These has no nonParametric alternatives These has no Parametric alternatives Two-way analysis of variance (between groups) H0: effect of age on optimism is not different for males and females? Chi-square for goodness of fit H0: Proportions of var A for (x =0.3), (y=0.25),(z=0.45) Mixed between-within groups ANOVA Which intervention (maths skills/confidence building) is more effective in reducing participants’ fear of statistics, measured across three periods (pre-intervention, post- intervention, three-month follow-up)? Chi-square for independence Same as Fisher’s exact test (one var have 5 or less as expected frequency) H0: x is independent of y H0:There is no association between x and y Multivariate analysis of variance (MANOVA) Are males better adjusted than females in terms of their general physical and psychological health (in terms of anxiety and depression levels and perceived stress)? McNemar Test H0: no significant change in proportion of yes/no for x,y H0:Proportion of yes/no at time1 = proportion of yes/no at time2 Analysis of covariance Is there a significant difference in the Fear of Statistics Test scores for participants in the maths skills group and the confidence- building group, while controlling for their pre-test scores on this test? Cochran’s Q Test three or more time points[categorical var], each with 2 values [yes,no] H0: no significant change in proportion of yes/no for x,y,z H0:Proportion of yes/no at time1 = proportion of yes/no at time2= proportion of yes/no at time3 Kappa Measure of Agreement H0: no significant change in proportion of yes/no/maybe for x,y Other tests