stat tests Flashcards
unrelated, nominal
chi-squared
- calculated value of X^2 equal to or more than critical value
related, nominal
sign
- s equal to or less
correlation, nominal
chi-squared
- calculated value of X^2 equal to or more than critical value
unrelated ordinal
mann-whitney
- calculated value of U must be equal or less than
related ordinal
wilcoxon
- calculated value of T is sum of less frequent signs
- must be equal to or less than critical value
unrelated correlation
spearman’s rho
- rho must be equal to or more than
unrelated interval
unrelated t-test
- calculated value of t must be equal to or more than the critical value
related interval
related t-test
- calculated value of t must be equal to or more than the critical value
correlation interval
pearson’s r
- equal to or more than
three things for stat tests
difference or correlation
experimental design
level of measurement
levels of measurement
quantitative data can be classified into types or levels of measurement - nominal, ordinal or interval
parametric tests
pearson’s r
related t-test and unrelated t-test
- relies upon the assumption that the data you want to test is (or approximately is) normally distributed
measures of central tendency and dispersion
nominal
central tendency - mode
dispersion - n/a
ordinal
- median
- range
interval
- mean
-standard deviation
how to tell types of study
if has two groups then looking at a difference
if theres different people involved then its unrelated - eg just doesnt mention matching
degrees of freedom
pearson’s r = N-2
related t-test = N-1
ulrelated t-test = NA + NB - 2
correlation coefficient strengths
Very weak or negligible correlation: 0 to 0.1 or -0.1 to 0
Weak correlation: 0.1 to 0.3 or -0.1 to -0.3
Moderate correlation: 0.3 to 0.5 or -0.3 to -0.5
Strong correlation: 0.5 to 1 or -0.5 to -1
degrees of freedom calculation - fun - pearsons
Pearson’s correlation:
Mnemonic: “Partners in Crime”
Explanation:
Count the number of paired observations.
Subtract 2 from the total number of pairs to calculate the degrees of freedom.
degrees of freedom calculation - fun - related t-test
Related t-test:
Mnemonic: “Time to Compare”
Explanation:
Count the number of pairs or matched observations.
Subtract 1 from the total number of pairs to calculate the degrees of freedom.
degrees of freedom calculation - fun - unrelated t-test
Unrelated t-test:
Mnemonic: “Two Worlds Collide”
Explanation:
Count the number of participants in each group.
Add up the number of participants from both groups.
Subtract 2 from the total number of participants to calculate the degrees of freedom.
degrees of freedom calculation - fun - chi-sequared
Mnemonic: “Row-Column Dance”
Explanation:
Count the number of rows and columns in the contingency table.
Subtract 1 from the number of rows (R) and 1 from the number of columns (C).
Multiply the results: df = (R - 1) x (C - 1).