PSYC 2030 Chapter Notes - Chapter 9: Null Hypothesis, Scatter Plot, Regression Analysis
Document Summary
0. 00 (no relation): pearson"s r : calculated for data measured on either an interval or ratio scale. Descriptive stat: the inferential analysis for orrelations involves determining if a particular correlation is significantly greater or less than zero, that is, the null hypothesis is that the true value of r is 0. Spearman"s rho: calculated for ordinal (ranking) data: scatterplots, provides a visual representation of the relationship shown by a correlation, perfect correlations yield a straight line, whereas a correlation of zero yields a scatterplot, assuming linearity. Some relations are not linear and applying pearson"s r to them will fail to identify the relationship. Some experiments produce data on a scatter that have parabolic tendencies; curvilinear: restricting the range, restricting the range of one (or both) of the measured variables weakens the correlation. Found by squaring pearson"s r so that the coefficient will always be positive.