This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Two variables: Which test? Explanatory variable Categorical Numerical Categorical Contingency analysis Logistic regression Survival analysis Response variable Numerical ttest Analysis of variance Regression Correlation Correlation: r • ! Describes the relationship between two numerical variables • ! Parameter: ! (rho) Estimate: r Max. lifespan of females (days) 12.5 15.0 17.5 20.0 22.5 25.01 1 2 3 4 Number of males per female C. elegans data r 2 = 0.93 %adults who smoke 15 20 25 30 10 20 30 40 50 60 70 80 90 Excise tax (c/pack) Smoking/taxes data r 2 = 0.12 r =  0.98 r =  0.35 Correlation assumes... • ! Random sample • ! X is normally distributed with equal variance for all values of Y • ! Y is normally distributed with equal variance for all values of X Correlation coefficient facts • !1 < ! < 1 • ! Coefficient of determination: r 2 : Describes the proportion of variation in one variable that can be predicted from the other Estimating the correlation coefficient r =...
View
Full Document
 Spring '10
 Driscoll
 Statistics, Correlation, Normal Distribution, Variance, Pearson productmoment correlation coefficient, Spearman's rank correlation coefficient, Statistical dependence

Click to edit the document details