Inferential statistics Flashcards
What do inderential statsictcs help researchers to do?
Inferential statistics help researchers to identify if their calculated value is a significant result at a level of P<0.005 by comparing it to the table of critical values
What two things are needed when determining whicn inferential statisicas test to use?
Design of the investigation
Level of data colleted
What are the statisical tests and their crtiteras?
Independent + nominal = Chi squared
Repeated + nominal = sign test
Correlation + nominal = No test but chi can be used
Independent + ordinal = Mann Whitney
Repeated + ordinal = Signed ranks
Correlation + ordinal = Spearmans Rho
Independent + Interval/ratio = Unrelated t-test
Repeated + Interval/ratio = Related t-test
Correlation + Interval/ratio = Pearsons
Why are parametric tests more powerful than non parametric tests?
What do parametric tests analyse? (3)
What level of data do non parametric tests use?
What are the tree criterion points for parametric tests?
Parametric tests are more powerful than non parametric tests because they analyse individual scores, their position, and the difference between one score and the other
Non parametric tests use only nominal or ordinal level data
Three criteria points for parametric test
- Interval or ratio level data
- Normal distribution of data
- Similar variances between results from the different conditions
