This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: Non-parametric Statistics Compare two categories of the independent variable = Mann-Whitney If more than 2 categories of the independent variable = Kruskal Wallis If independent variable measured repeatedly in same individuals over time = Friedman • Continuous o Linear association = Correlation (r) Is your sample size sufficient and data normally distributed (parametric)? = Pearson’s correlation Is your sample size small or data skewed (non-parametric)? = Spearman’s ranks o Predict how one variable determines the value of the other = Regression Analysis (r 2 ) Linear relationship = Regression equation (y=mx+b, m=slope) & significance test (slope differs from 0) Non-linear relationship = Polynomial equation Multiple variables = Multiple Regression...
View Full Document
- Spring '10
- Statistics, ndependent variable, ependent Variable, theoretical expected ratio, equation Mul tiple