POLS 385 Study Guide - Quiz Guide: Microsoft Powerpoint, Statistical Model, Linear Regression
20 Oct 2016
School
Department
Course
Professor
Document Summary
Bivariate hypothesis tests and causality: establishes co-variation between 2 variables, but not controlling for cofounding variables. Alternative hypothesis: what we expect to see if our theory is true (relationship exists) Null hypothesis: what we expect to see if our theory is false (relationship does not exist) P-value: measures the lack of fit between our null hypothesis and data. Probability of observing our results in the event that the null hypothesis is true (if p-value is low, reject the null hypothesis) Eg. result is statistically significant if p-value is less than a predetermined or critical p-value (. 05) Procedure: 1) state hypotheses 2) select critical value 3) compute the p-value 4) interpret results. N1, n2 = sample sizes (# of observations); s1, s2 = standard deviation; s21, s22 = sample variances. The t-statistic (3. 44) falls outside the non-rejection region (1. 98), so reject null hypothesis: correlation coefficient (iv: continuous + dv: continuous): scatter plot is the best representation for this.
