STAT 5: Introduction to Multiple Testing Flashcards
1
Q
What is a two sample t-test?
A
- when you compare two samples with each other
2
Q
What is a one sample t-test?
A
- when you compare a group to a specific mean
- i.e. the mean of a population or a specific group
3
Q
Give example codes for a two sample t-test and a one sample t-test
A
4
Q
Give an example of a for a one-tailed two sample t-test
A
5
Q
What is a paired t-test?
A
- sometimes called a dependent sample t-test
- applied when two samples are closed related to each other
- e.g. measuring the same sample or patient twice, before or after a certain treatment
6
Q
How do you perform a paired t-test in R?
A
7
Q
What could happen when data do not fit under the assumptions of a statistical test?
A
- the probability calculations underlying the test are likely to be incorrect
- this could increase the chance of false positive or false negative results
8
Q
What are the three assumptions of the t-test?
A
9
Q
What is the Family Wise Error Rate?
A
- the FWER is the probability of getting a false positive if the null hypothesis is true across a group of tests
- with the increase in the number of tests, the alpha is no longer the type 1 error rate
10
Q
How do you calculate the FWER?
A
11
Q
What is ANOVA?
A
- analysis of variance, or F-test
- compares the variance within samples with the variance between the samples
- shows you whether all the values that have been measured in our samples actually come from the same population or whether the observation of at least one group comes from a different population
12
Q
What is SSW and how do I calculate it?
A
- sum of squared differences within the group
13
Q
What is SSB and how do I calculate it?
A
- the sum of squared differences between the groups
14
Q
A
15
Q
How do we calculate the degrees of freedom between groups
A
K - 1
- K= number of groups/samples
17
Q
How do you calculate the variance between and within groups and the F statistic?
A
