choosing a statistical test Flashcards
three main factors
whether the researcher is looking for a difference or correlation
in the case of a difference what experimental design is being used
the level of measurement
decision 1 - difference or correlation
relates to the aim or purpose of the investigation - is the researcher looking for a difference or a correlation
should be obvious from the wording of the hypothesis
decision 2 - experimental design
when the research is looking for a difference experimental design is needed
three types of- independent groups, repeated measures and matched pairs
in repeated measures the same participants are used in all conditions
in matched pairs participants in each conditions are not the same but have been matched on some variable that is important
the two above are related designs
independent group designs means partial tons in each contains are different
choosing statistical test
test of difference
unrelated design:
nominal - Chi-squared
ordinal- Mann-Whitney
interval - Unrelated t-test
related design:
nominal - sign test
ordinal - Wilcoxon
Interval - related t-test
test of association or correlation:
nominal - Chi-squared
ordinal- Spearman’s rho
interval - Pearsosns r
decision 3 - levels of measurement
quantitative dara can be divided into different levels of measurement
three level - nominal ordinal and interval
nominal data
data is represented in the form of categories
discrete data
only one item can appear in one of the cateoegies
ordinal data
data is ordered in some way
rate how much they like something
does not have equal intervals
lacks precision because it is based on subjective opinion rather than objective measures
interva, data
based on numerical scales
equal intervals
most precise
