This test is used for testing the equality of variances of several populations that have normal distribution. This test is needed because one of the required conditions for many statistical methods is that the population variances be equal such as for the F-test of the analysis of variance (ANOVA). Beside Bartlett test, we can also use Levene test to see the equality of variances of several populations. The Levene test will be explained in another writing session. The hypotheses we test are
example: (using the apple juice example in one way ANOVA writting session)
Interpretation: There is not enough evidence to infer that the population variances differ, with the 95% level of confidence.
See you in other writing sessions, have enjoying statistics.
Any questions, send to the e-mail address: firstname.lastname@example.org
*) Writer is a lecturer in Institute of Statistics, Jakarta, Indonesia.
Bachelor of Statistics from Institute of Statistics, Jakarta, Indonesia.
Master of Science in Experimental Statistics from NMSU, USA.