inferential statistics research methods Flashcards
what three things do you need to consider when choosing a statistical test?
research design
research aim
level of measurement
what are the two types of research design
related = produced by repeated measures and matched pairs
independent = produced from independent groups design
what are the two types of research aim?
is the aim to test a significant difference of a significant association/ correlation
what are the three levels of measurement/ data
nominal
ordinal
interval
what is nominal data ?
- most basic level of measurement
- frequency count that can be put into one category but not rank order
- e.g. a frequency count on the number of aggressive and non aggressive acts in an observation
what is ordinal data
- consists of a list of data than can be ranked in order, but not data that would fit into an interval scale
- do not have an objective scale
- e.g. the subjective rating of happiness (on a scale from 1 to 10) that participants may score themselves as on a questionnaire. A happiness rating of 10 is higher than 5, but it is not twice as happy as 5
what is interval data ?
- measured on a scale in which each interval is exactly the same size
- e.g. this is interval data because each second is the same duration, and 10 seconds are twice as long as 5 seconds.
what are the eight different statistical tests
- Spearman’s Rho
- Wilcoxon signed ranks test
- Mann Whitney U test
- Chi squared test
- Pearson’s r
- unrelated
- related
- sign test
what is Spearman’s Rho ?
- a test for significant association
- the levels of measurement must be ordinal
what is Wilcoxon signed ranks test ?
- a test for significant difference
- for related data ( repeated groups or matched pairs)
- level of measurement is ordinal
what is Mann- Whitney U test?
- a test of significant difference
- independent groups design
- level of measurement is ordinal
what is chi squared test ?
- test for difference or association
- nominal data
- if it’s for a test of difference than it is independent groups design
what is a sign test
- tests for a difference
- for related
- for nominal data
What is Pearson’s r test
- tests for an association
- interval data
what is unrelated t- test
- tests for a difference
- independent group design
- interval data
what is a related t test
- tests for a difference
- related
- interval data
Independent + nominal =
chi squared test
independent + ordinal =
Mann Witney u test
independent + interval
unrelated t test
related + nominal =
sign test
related + ordinal =
Wilcoxon matched pairs signed ranks test
related + interval
related t test
association + nominal =
chi squared
association + ordinal
Spearman’s Rho
association +’interval
Pearson’s r
When deciding whether to accept or reject a hypothesis what two things need to be considered ?
- how many participants are in each condition/ pairs of scores
- whether you have a directional or non directional hypothesis
a one tailed test is applied to …
directional hypothesis
a two tailed test is applied to…
a non directional hypothesis
the significance level for the result of any test is expresses as what ?
a probability value from 0-1
can be written at percentage or decimal
what does the significance level indicate ?
- the probability that the null hypothesis is true
- so it follows that a researcher would want a very small probability value in order to claim that the test result is statistically significant
what is the null hypothesis
results are down to chance
what is the minimum acceptable value for deciding whether a test result is statistically significant
5%
if the 5% level of significance is achieved this means the probability that the null hypothesis is true is…
1 in 20
what is a type 1 error
occurs when a null hypothesis is rejected when it should not have been
what is a type 2 error
occurs when a null hypothesis is retained when it should not have been