Hypothesis tests Flashcards

(20 cards)

1
Q

Test used for finding population mean (mu)

1-variable, 1-sample, numerical…

A

1-sample z/t-test

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

Assumptions for 1-sample z/t-test

A

z-test: sample mean is from normal distribution (if sample size is large enough, CLT applies)
t-test: sample is from normal distribution (or sample size is large enough to be robust)

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

What is a 1-sample z/t-test used for?

A

Finding the population mean (mu)

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

Test used for finding the average distance between pairs

2-variables, numerical, 1-sample (e.g. over time)…

A

Paired t-test

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

Assumptions for paired t-test

A

The differences between pairs are drawn from a normal population.

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

What is a paired t-test used for?

A

Finding the average distance between pairs

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

Test used for hypothesising a linear relationship between 2 numerical variables

A

t-test for population slope (beta)

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

Assumptions for t-test for population slope

A
  1. Linear model is appropriate (scatterplot)
  2. Residuals are from a normal distribution (histogram)
  3. Residuals have constant standard deviation (residuals vs. fit) => an even scatter along x axis
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Test used for finding the difference between averages

2 independent samples, numerical

A

2-sample t-test for difference between 2 population means

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

Assumptions for a 2-sample t-test

A
  1. Both samples drawn from normal distribution

2. Both samples have same standard deviation

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

What is a 2-sample t-test used for?

A

Finding the difference between that averages of 2 independent samples

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

Test used for hypothesising about a single proportion

Categorical, 1-variable

A

z-test for population proportion (pi)

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

Assumptions for z-test for population proportion

A

n(pi) >5

n(pi-1)>5

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

Test used for hypothesising about any number of proportions

A

Chi-squared goodness-of-fit test

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

Assumptions for chi-squared goodness-of-fit test

A

All expected values >/= 5

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

What is a chi-squared goodness-of-fit test used for?

A

Hypothesising about any number of proportions

17
Q

Test used for hypothesising about associations between 2 categorical variables

A

Chi-squared test of independence

18
Q

Assumptions for chi-squared test of independence

A

All expected values >/= 5

19
Q

What is a chi-squared test of independence used for?

A

Hypothesising about associations between 2 categorical variables.

20
Q

Name all the hypothesis tests

A

1-sample z/t-test for population mean
Paired t-test for population mean difference
T-test for population slope (beta)
2-sample t-test for differences between population means
z-test for population proportion (pi)
Chi-squared goodness-of-fit test
Chi-squared test of independence