Stat 121 Choosing the right method Flashcards

1
Q

Testing a claim or checking to see if groups are different?

A

Hypothesis test

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

Estimating the value of a parameter?

A

Confidence interval

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

One group with quantitative response (working with means)?

A

1-sample t-test for means
β€”ORβ€”
1-sample t-interval for means

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

One group with categorical response (working with proportions)?

A

1-sample z-test for proportions
1-sample z-interval for proportions

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

PAIRED DATA / Matched pairs with quantitative response (working with means)?

A

Matched pairs t-test for means
Matched pairs t-interval for means

(Note: use the 1 sample t
formulas but with 𝑑̅ in place of
π‘₯Μ… and sd in place of s)

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

2 GROUPS quantitative response (working with means)?

A

2-sample t-test for means
2-sample t-interval for means

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

2 GROUPS categorical response (working with proportions)?

A

2-sample z-test for proportions
2-sample z-interval for proportions

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

2 GROUPS categorical response with more than 2 options (working with proportions)?

A

Chi-squared Test for independence

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

3+ groups quantitative response (working with means)?

A

Anova (f-test)

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

3+ groups categorical response (working with proportions)?

A

Chi-squared Test for independence

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

Using Quantitative X to predict Y quantitative response (working with means)?

A

T-test for slope of regression line

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