lecture 7 - comparing more than two groups: ANOVA Flashcards
(22 cards)
why not use several t-tests?
every time you conduct a t-test using a .05 level of significance, there is a 5% probability of falsely rejecting the null hypothesis (a Type 1 error)
(A Type 1 error is also known as a false positive and occurs when a researcher incorrectly rejects a true null hypothesis. This means that you report that your findings are significant when in fact they have occurred by chance.)
what is the experiment wise error rate?
p (type 1 error rate) = 1-0.95^n where n= no. of comparisons made
when should you use an ANOVA test?
with 2 groups both work but: t-test more efficient, ANOVA inefficient
with more than 2 groups: t-test not efficient, ANOVA more efficient
what is an ANOVA?
Analysis of Variance (ANOVA) is a parametric equivalent to t-tests that involves more than two groups
what are the assumptions of an ANOVA?
the data is interval or ratio
the data is normally distributed
the scores have equal variances (homogeneity)
for independent-samples the participants must be randomly sampled
what iS ANOVA and why do we need it?
true effect of the IV - variance between conditions
effect of individual differences - variance within condition
variance between>variance within
what three factors affect the variances?
- treatment effects
- individual differences
- random errors
what three factors affect the between groups variance?
- treatment effects
- individual differences
- random errors
what two factors affect the within-group variance?
individual differences
random errors
what is within-groups variance?
variation (difference) between people within the same group
what are treatment effects?
variance due to experimental manipulation
what are nuisance factors
individual differences
random errors
how do you calculate the f-ratio?
F statistic = MSbetween/MSwithin
F = average between group variation/average of within group variation
how do you determine whether the F-ratio is significant or not?
F > 1 effect of the IV is likely significant
F < 1 effect of the IV is not significant
what is the unadjusted p value multiples by?
the number of tests
what if the assumptions of the ANOVA are violated?
the Kruksal-wallis test
what is the Kruksal-wallis test?
“rank-based nonparametric test that can be used to determine if there are statistically significant differences between two or more groups of an independent variable on a continuous or ordinal dependent variable”
in ANOVA terminology - what are factors?
independent variable(s): nutritional intervention
in ANOVA terminology - what are levels of factors
conditions: three levels of the factor: water, beetroot juice, carnitine
what do you specify in ANOVAs?
factors
levels
design
what are the types of analysis of variance (ANOVA)
the number indicates the number of factors (IVs):
one-way ANOVA (one factor, e.g. nutritional interventions)
two-way ANOVA (two factors, e.g. nutritional interventions and gender)
three-way ANOVA (three factors, e.g. nutritional interventions, gender and age group)
what is meant when we describe an ANOVA as 2x4?
two factors (e.g. gender and facial expression)
gender has 2 levels
facial expression has 4 levels
