T-test
If you have two variables (numerical) You want to compare if the two means of the two variables is statistical different For between subjects experiment Use Independent samples t-test For within subjects experiment Use Paired-samples t-test
Paired-samples t-test
A paired-samples t-test was conducted to compare variable 1 in condition 1 and condition 2. There was no significant difference in the score of variable 1 for condition 1 (M=52.2, SD=10.25) and condition 2 (M=52.8, SD=9.48); t(199)=-.87, p=0.387.
There are two Sig. Check out the Sig. of Levenes Test first If Sig. of Levenes Test < 0.05 If Sig. of Levenes Test > 0.05
Use the Sig. of Equal variance not assumed Use the Sig. of Equal variance assumed
An independent samples t-test was conducted to compare variable 1 in condition 1 and condition 2. There was a significant difference in the score of variable 1 for condition 1 (M=52.2, SD=10.25) and condition 2 (M=52.8, SD=9.48); t(169.71)=-3.656, p=0.000.
ANOVA
If you have more than two variables (numerical) You want to compare if the means of the variables is statistical different Use ANOVA!
A one-way between subjects ANOVA was conducted to compare variable 1 in condition 1, condition 2 and condition 3. There was a significant difference of variable 1 on variable 2 at the p<.05 level for the N conditions [F(2,12)=4.94, p=0.027].
Post hoc comparisons using Tukey HSD test indicated that the mean score for condition 1 (M=4.20, SD=1.30) was significantly different than condition 3. However, condition 2 (M=3.60, SD=0.89) did not significantly differ from condition 1 and condition 3.
A one-way within subject ANOVA was conducted to compare the effect of DV on IV in condition 1, condition 2 and condition 3. There was a significant effect of the IV, Wilks Lambda=0.10, F(2,3)=13.42, p=.032.
Binomial Test
For binary variables (Yes, No) E.g. Prospect Theory You have 2 identical choice You want to show a bias in making choice i.e. people tend to make one choice than the other, even though the choices are identical H0: No bias in choice 50/50 in the two conditions H1: Bias in choice not 50/50 in the two conditions
Chi-Square Test
Two categorical variables [Yes, No] [Male, Female] See if there is a relation between the two variables Use Chi-Square Test H0: No relation between the two variables H1: There exists a relation between the two variables Reject H0 is p<.05 i.e. there exist a significant effect between the two variables
SPSS Chi-Square Test Sig. > .05 Reject H1 i.e. There is no bias in choice between male and female.
The percentage of participants that were republican or democrat did not differ by gender, 2(1, N=12)=0.00, p=1.00.