Biostats 3 & 4 Flashcards

1
Q

What are different testing methods for categorical data

A

Chi2

Fisher’s exact

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What are the rules and assumptions of categorical data

A

data are arranged into categories
data are independent; random sample from the population
must be a positive integer >0

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What are the types of studies for categorical data

A
cross sectional
prospective
retrospective
experimental
diagnostic test
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What is a cross sectional study

A

recruit study group and define two categories

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What is a prospective study

A

recruit group with some difference and follow them

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What is a retrospective study

A

start with a condition and look backwards at potential causes

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What is an experimental study

A

recruit a group, manipulate variables

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What is a diagnostic test

A

positive and negative results

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

When will a fisher’s exact test be used over chi2

A

when a sample group is <5

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What are the degrees of freedom

A

of variables in final calculation that are free to vary

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

How is DOF calculated

A

usually n-1

df=(rows-1) X (columns-1)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What is the use of Chi2

A

tests the goodness of fit; observed frequency compared to theoretical

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What does a student/paired t-test compare

A

means of 2 groups

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What are the requirements and assumptions of T-tests

A

n>30 for each population
data is continuous
data is a random sample and normally distributed
each population should have the same variance

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

WHat are the different types of t tests

A

one sample t test
independent t test
dependent t test

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What is a one sample t test

A

compare a group’s mean to a benchmark group

17
Q

What is an independent t test

A

compare 2 independent groups

18
Q

What is a dependent t test

A

compare 2 groups that are somehow related

19
Q

When do you use a 1-tailed t test

A

population is significantly greater than the other

20
Q

When do you use a 2-tailed t test

A

population is significantly different from the other population

21
Q

What is the use of ANOVA

A

to compare the means of 3 or more groups

22
Q

What are the rules and assumptions of ANOVA

A

compares all groups at once
tell you there is a difference between at least 2 groups
examines variance from mean scores
takes deviation for mean, square and sum= sum of squares

independent observations
normally distributed data
homogeneity of variance

23
Q

What is needed after ANOVA

A

post-hoc test

24
Q

WHat are the types of post hoc tests

A

Turkey test

Dunnett’s

25
Q

What is a Turkey post hoc test

A

compares each group to every other group

26
Q

What is a Dunnett’s post hoc test

A

compares all groups to a control group

27
Q

What are the nonparametric tests

A

Mann Whitney U test
Wilcoxon Signed ranks
Kruskal Wallis

28
Q

What does a Mann Whitney U test measure

A

RANKS instead of actual values

29
Q

What does a WIlcoxon Signed Rank test measure

A

absolute values of differences are sorted and ranked

30
Q

WHat is the alternative for independent t-test if there is skewed data

A

mann-whitney u test

31
Q

What is the alternative for dependent t-test if there is skewed data

A

wilcoxon signed ranks

32
Q

What is the alternative for ANOVA if there is skewed data

A

Kruskal Wallis

33
Q

Do you still need a post hoc test with a Kruskal Wallis

A

yes

34
Q

When is a box and whisker plot used

A

not a normal distribution