Session 4a Flashcards
When H0 is rejected in ANOVA, we infer that at least one pair of means is different.
But, we may not know which pairs of means are different
what can we do to figure this out
post hoc tests
The F ratio or F test gives what
a global effect of the independent variable on the dependent variable (omnibus or overall test)
what is the issue with omnibus or overall test (F ratio or F tests)
It does not tell us which pairs of means are different
what are Post hoc (a posteriori/unplanned) comparisons
Decided upon after the experiment
In the case of ANOVA, used if three or more means were compared
what are the main 2 post hoc tests
Sheffé
Tukey’s Honestly Significant Difference (HSD) test
Sheffé’s Test Can be used when
if groups have different sample sizes
Sheffé’s Test is less sensitive to what
departures from the assumption of normality and equal variances in the population
what post hoc test is the most conservative
Sheffé’s Test
is the most conservative test (very unlikely to reject H0)
But, this means a good choice if you wish to avoid what
Type I errors
Tukey’s HSD test is used when
if groups have equal sample sizes and all comparisons represent simple differences between two means
Tukey’s HSD test uses when
studentized range statistic, , Q
what is the ‘minimum absolute difference between two means required for a statistically significant difference’
HSD
