PSYC 60 Lecture Notes - Lecture 14: Repeated Measures Design, Variance, Null Hypothesis
Document Summary
Psyc 60 lecture wednesday, november 2nd: the t test for two independent samples. Overview: until now: used one sample to draw inferences about a population. Each design has different strengths and weaknesses considered in this chapter; repeated-measures (withinsubjects) designs will be reserved for discussion in chapter 11. But, with more than 2 groups we use a different statistical technique (anova). Iv. t statistic for independent-measures design: notation for two samples: subscripts 1 and 2. So we will only cover the t-test: to evaluate hypotheses we will use a version of the t statistic. Previously (one sample): single-sample t statistic now (two separate samples): independent- measures t statistic : what is s(m1-m2), measure of standard or average distance between sample statistic (m1- M2 approximates 2 with some error: for each: sm=sqrt(s^2/n)=s/sqrt(n, combined standard error: when n1 = n2! But this only works: but, there is a problem: the formula is limited for n1 = n2.