Inferential Testing Flashcards Preview

Psychology2- Further Research Methods > Inferential Testing > Flashcards

Flashcards in Inferential Testing Deck (17):
1

What are the parametric tests?

Pearsons r
Related T test
Unrelated T test

2

What are the Non-parametric tests?

Chi squared
Spearmans rho
Mann Whitney U
Wilcoxon

3

Why are parametric tests favoured to Non-parametric tests?

They are more likely to detect an effect of the IV compared to non-parametric tests

4

What at the assumptions/criteria that needs to be met to use Parametric tests?

Data type
-Must use equal interval or ratio data
Normal disruption
-Data will be normally disrupted
Homogeneity of variance
-The samples of data will have roughly equal variance (the range/dispersion of data)

5

What do you need to consider when looking at the homogeneity of variance?

The experimental design
-whether the groups are independent or repeated
>this will affect the standard deviation of results as the results will vary depending on the groups of independent measures.

6

What is the difference between a parametric test and a Non-parametric tests?

a parametric statistical test is one that makes assumptions about the parameters (defining properties) of the population distribution(s) from which one's data are drawn, while a non-parametric test is one that makes no such assumptions.

7

What are the 3 D’s

Difference - what type of study (experiment = difference) (non-experiment = correlational)

Design -what experimental design was used

Data - what level of measurement what used?

8

How do you work out if you can use a parametric test?

Look at what level of measurement is being used
(Nominal and ordinal cannot be used in parametric testing)

9

If you can use a parametric test and the data is correlation, what test should you use?

Pearsons r

10

If you can use a parametric test, the results are non-correlational and you use independent groups, what test should you use?

Unrelated T test

11

If you can use a parametric test, the data’s non-correlational and you do not use independent groups then what test should you use?

Related T test

12

If you cannot use a parametric test, the data is nominal and you use a independent groups design, what test should you use?

Chi-squared

13

If you cannot use a parametric test, the data is nominal and you do not use a independent groups design, what test should you use?

Sign test

14

If you cannot use a parametric test, the data is not nominal and the data is correlational, what test should you use?

Spearmans rho

15

If you cannot use a parametric test, the data is not nominal, the data is not correlational and you use an independent group design, what test should you use?

Mann-Whitney

16

If you cannot use a parametric test, the data is not nominal, the data is not correlational and you do not use an independent group design, what test should you use?

Wilcoxon

17

What does a large standard deviation imply?

The iv effected the participants in a large variety of ways.