Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
24 Cards in this Set
- Front
- Back
Why do you not use a t-test? |
Increases your risk of making a type 1 error |
|
What does the maths of an ANOVA examine? |
The variability between the means of each group compared with variability between the values within each group |
|
What does a larger F value mean? |
more likely to be a difference between at least 2 of your groups |
|
Equation for calculating F value? |
F = MSb/MSw (mean squares between/within) |
|
Equation for: MSb MSw |
MSb = SSb/dfb MSw = SSw/dfw |
|
Equation for df between groups? |
No. of groups - 1 |
|
Equation for degrees of freedom within groups? |
(n1 -1) + (n2 - 1) + (n3 -1)...(nn - 1) |
|
What does it mean if the F value is GREATER than Fcrit? |
SIGNIFICANT DIFFERENCE between at least 2 groups |
|
For which types of groups do you use a one- way ANOVA? |
independent |
|
For which types of groups do you use a repeasted-measures ANOVA for? |
Dependent groups |
|
Constraints for a one-way ANOVA? (2) |
a different treatment is applied to each group each subject produces a single measurement |
|
Constraints for repeated measures ANOVA? (2) |
all subjects are given the same treatment each subject provides 3 or more meaurements (taken at diff time points) |
|
3 underlying assumptions of parametric tests? |
data are continuous data are normally distributed variances of each group are statistically equal |
|
If data is not continuous or not normally distributed which test can be used? |
Mann-Whitney test
|
|
If there are 3 or more groups which test can you use? |
Kruskal-Wallis test
|
|
The ability to detect a difference between the data is the ?
Non-parametric test are what? |
Power of the test Less powerful |
|
What is a suitable measure of central tendency? |
most case = mean |
|
How accurate is my estimation of the mean? |
Calculate SEM |
|
How can you represent the spread of the data? |
calculate the standard deviation |
|
Is there a significant difference between 2 independent groups? |
UNPAIRED t test |
|
Is there a significant difference between 2 dependent groups? |
PAIRED t test |
|
If there a significant difference between 3 or more dependent groups which method do you use?
|
REPEATED MEASURES ANOVA, followed by post-hoc test
|
|
Is there a significant difference between 3 or more independent groups? |
ONE-WAY ANOVA, followed by post-hoc sig test |
|
If you try transformation of your data and this fails to normalise or minimise differences between variances what should you do? |
Use a NON-PARAMETRIC test |