Paired samples t-tests Flashcards Preview

Psychology 3rd Year > Paired samples t-tests > Flashcards

Flashcards in Paired samples t-tests Deck (40)
Loading flashcards...
1
Q

What does a t-test tell us?

A

The t test tells us how likely it is that we will observe a difference - is this by chance?

2
Q

why would we use a t test?

A

when one of our variables has more than one condition.

3
Q

what kind of data design must we have to do a t-test?

A

repeated design

4
Q

how many conditions must our IV have to do a t test?

A

2

5
Q

How many participants do you need to do a t-test?

A

10

6
Q

What scale should our data be on to use a t-test?

A

interval/ratio

7
Q

The difference scores (change scores) for t tests must be…

A

Normally distributed :)

8
Q

T tests are interested in the __________ between participant’s T1 and their T2 scores.

A

differences

9
Q

When will the t value get bigger?

A
  1. when the difference scores are larger, assuming they are also consistently in the same direction.
  2. when there is less variation in difference scores.
10
Q

___ variation is more likely to be significant as there is a much smaller distribution, this score is an extreme.

A

less

11
Q

t (951) = -12.39, p< .001 (two tailed)

Anything missing?

A

Yes effect size!

12
Q

If you use a 1 tailed hypothesis what do you have to do to the p value?

A

We have to half it!

13
Q

what is a small effect size?

A

0.1

14
Q

What is a medium effect size?

A

0.3

15
Q

What is a large effect size?

A

> 0.5

16
Q

What is the formula for r (effect size)?

A

√ t2/ (t2 + df)

17
Q
t = -12.39
df= 951

Calculate the effect size.

A

√ t2/ (t2 + df)

√-12.39 squared/ (-12.39 squared + 951)

r = 0.37

18
Q

Larger T value =…

A

larger difference and smaller variation

19
Q

What do t-tests evaluate?

A

The difference in participants’ scores from one condition to the other.

20
Q

What 2 non-parametric tests would you use?

A

2 conditions: Wilcoxon Signed ranks

3 or more conditions: Friedman Test

21
Q

if you have 2 conditions what non-parametric test do you use?

A

Wilcoxon Signed Ranks

22
Q

If you have 3 conditions or more, what non-parametric test do you use?

A

Friedman Test

23
Q

What is the non-parametric equivalent to the t-test?

A

Wilcoxon signed Ranks

24
Q

what conditions does non-parametric data reflect?

A

Less than 10 participants
Ordinal data
Data skewed

25
Q

What does Wilcoxon Signed Ranks test?

A

whether data in 1 condition is consistently ranked more highly than in the other condition.

26
Q

How does ranking work if people have the same score?

A

If we have 3 score 1’s.
1 + 2 + 3 = 6

6/3 = 2

27
Q

The ___ value is always the smaller number of the 2 sums of ranks.

A

the T value :)

28
Q

How is a Wilcoxon signed ranks reported?

A

T = 2, N= 8, p= .023 (two tailed).

29
Q

What is the effect size in Wilcoxon Signed Ranks?

A

r = z / square-root-of-N

30
Q

What are Cohen’s guidelines for effect sizes

A

r = .10 (small), .30 (medium), .50 (large

31
Q

T = 2, N = 8, p = .023 (two-tailed), r = .80.

When would you not report effect size?

A

If p wasn’t significant.

32
Q

What is an extension of the Wilcoxon?

A

Friedman- for 3 or more conditions :)

33
Q

What is the standard form to report Friedmans?

A

χ2 (2) = 12.25, p = .002

34
Q

After we get our Freidman’s what do we have to do?

A

We have to conduct follow up Wilcoxon’s to find out where the sig differences lie!

35
Q

If we have 4 conditions, how many Wilcoxon follow up tests do we have to do?

A
A v B
A v C
A v D
B v C
B v D
C v D

6 tests!!!

36
Q

What do Wilcoxon follow up tests inflate?

A

They inflate the chances of making a type I errors.

37
Q

How do we resolve the increased chance of makimg a type I error in a follow up Wilcoxon test?

A

We do a bonferromi Correction!

38
Q

What is a Bonferroni Correction?

A

Divide the level of significance (0.05) by the number of tests you are conducting.

39
Q

I you have 3 Wilcoxon follow up tests- what is the significance value?

A

0.05/3 = 0.017

40
Q

What is the appropriate effect size to use for paired sample t-tests?

A

Cohen’s d