Homogeneity of variance and independent samples t-test
Assess homogeneity of variance when comparing two independent groups on a continuous outcome
The assumption of homogeneity of variance is the second statistical assumption that needs to be tested when comparing two independent groups on a continuous outcome. Homogeneity of variance is assessed using Levene's Test for Equality of Variances. In order to meet the statistical assumption of homogeneity of variance, the p-value for Levene's Test should above .05. If Levene's Test yields a p-value below .05, then the statistical assumption of homogeneity of variance has been violated.
Homogeneity of variance essentially makes sure that the distributions of the outcomes in each group are comparable and similar. If independent groups are not similar in this regard, superfluous findings can be yielded. Independent samples t-tests should not be conducted on continuous variables that violate the assumption of homogeneity of variance. Independent samples t-tests should only be conducted on continuous outcomes between groups that have "equal" or "similar" variances.
Homogeneity of variance essentially makes sure that the distributions of the outcomes in each group are comparable and similar. If independent groups are not similar in this regard, superfluous findings can be yielded. Independent samples t-tests should not be conducted on continuous variables that violate the assumption of homogeneity of variance. Independent samples t-tests should only be conducted on continuous outcomes between groups that have "equal" or "similar" variances.
The steps for assessing the assumption of homogeneity of variance in SPSS
1. Click Analyze.
2. Drag the cursor over the Compare Means drop-down menu.
3. Click on Independent-Samples T Test.
4. Click on the continuous outcome variable to highlight it.
5. Click on the arrow to move the outcome variable into the Test Variable(s): box.
6. Click on the "grouping" variable to highlight it.
7. Click on the arrow to move the "grouping" variable into the Grouping Variable: box.
8. Click on the Define Groups button.
9. Enter the categorical value for the first independent group into the Group 1: box. Example: "0"
10. Enter the categorical value for the second independent group into the Group 2: box. Example: "1"
12. Click Continue.
13. Click OK.
2. Drag the cursor over the Compare Means drop-down menu.
3. Click on Independent-Samples T Test.
4. Click on the continuous outcome variable to highlight it.
5. Click on the arrow to move the outcome variable into the Test Variable(s): box.
6. Click on the "grouping" variable to highlight it.
7. Click on the arrow to move the "grouping" variable into the Grouping Variable: box.
8. Click on the Define Groups button.
9. Enter the categorical value for the first independent group into the Group 1: box. Example: "0"
10. Enter the categorical value for the second independent group into the Group 2: box. Example: "1"
12. Click Continue.
13. Click OK.
The steps for interpreting the SPSS output for homogeneity of variance
1. In the Group Statistics table, there are several important pieces of information about each independent group in the "grouping" variable including the size of each group (N) and their respective means (Mean) and standard deviations (Std. Deviation). Disregard the Std. Error Mean values for practical purposes.
2. In the Independent Samples Test table, look under the Levene's Test for Equality of Variance column heading. Look at the p-value in the Sig. column.
If it is MORE THAN .05, then researchers have met the assumption of homogeneity of variance and can interpret the independent samples t-test along with its means and standard deviations from the first table.
If the p-value is LESS THAN .05, then researchers have violated the assumption of homogeneity of variance and will use a non-parametric Mann-Whitney U to conduct their analysis.
2. In the Independent Samples Test table, look under the Levene's Test for Equality of Variance column heading. Look at the p-value in the Sig. column.
If it is MORE THAN .05, then researchers have met the assumption of homogeneity of variance and can interpret the independent samples t-test along with its means and standard deviations from the first table.
If the p-value is LESS THAN .05, then researchers have violated the assumption of homogeneity of variance and will use a non-parametric Mann-Whitney U to conduct their analysis.
Was the assumption of homogeneity of variance met for independent samples t-test?
Hire A Statistician - Statistical Consulting for Students
DO YOU NEED TO HIRE A STATISTICIAN?
Eric Heidel, Ph.D. will provide the following statistical consulting services for undergraduate and graduate students at $75/hour. Secure checkout is available with Stripe, Venmo, Zelle, or PayPal.
- Statistical Analysis
- Research Design
- Sample Size Calculations
- Diagnostic Testing and Epidemiological Calculations
- Survey Design and Psychometrics