Equality of medians (non-parametric) Flashcards

1
Q

T-tests rely on the variables being….

A

Symmetrical/normally distributed

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

What is the non-parametric analogue of the one sample t-test?

A

The Wilcoxon Signed Rank Test

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

When should you used the Wilcoxon Signed Rank Test?

A

▪️Compare median to a pre-specified value
▪️Skewed continuous data
▪️Ordinal (interval) or discrete data

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

What is the null hypothesis of a Wilcoxon Signed Rank Test?

A

The MEDIAN equals a certain predefined value

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

What assumptions are needed for the Wilcoxon Signed Rank Test?

A

▪️Observations are randomly and independently drawn
▪️At least interval data (more than 5 categories unless you can assume distances are equidistant)

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

What statistics do your report for the Wilcoxon Signed Rank Test?

A

The standardised test statistic (Z) and the p value

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

What is the non-parametric analogue of the independent sample t-test?

A

Mann-Whitney U test

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

When would you use the Mann-Whitney U test?

A

▪️Compare distributions of two different samples
▪️Skewed continuous data
▪️Ordinal (interval) or discrete data

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

What is the null hypothesis of a Mann-Whitney U test?

A

The two DISTRIBUTIONS are equal

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

What assumptions are needed for the Mann-Whitney U test?

A

▪️Observations are randomly and independently drawn
▪️At least interval data (more than 5 categories unless you can assume distances are equidistant)

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

What statistics do you report for the Mann-Whitney U test?

A

The Mann-Whitney U number and the p-value

(and describe how they differ)

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

What is the non-parametric analogue of the paired sample t-test?

A

Wilcoxon Matched-Pair Signed Rank Test

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

When would you use the Wilcoxon Matched-Pair Signed Rank Test?

A

▪️Compare medians of two paired or matched groups
▪️Skewed continuous data
▪️Ordinal (interval) or discrete data

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

What assumptions are needed for the Wilcoxon Matched Pair Signed Rank Test?

A

▪️Observations are randomly and independently drawn
▪️At least interval data (more than 5 categories unless you can assume distances are equidistant)
▪️Two samples need to be dependent observations of the cases (paired or matched)

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

What statistics do you report for your Wilcoxon Matched Pair Signed Rank Test?

A

The standardised test statistic (Wilcoxon rank sum Z) and the p-value

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

What category of tests are better suited for small samples sizes (less than 30)

A

Non-parametric

17
Q

What category of tests are most powerful for numerical comparison?

A

Parametric tests