PSYC 2020 Lecture Notes - Lecture 19: Statistical Hypothesis Testing, Effect Size
10 Apr 2018
School
Department
Course
Professor
Document Summary
Parametrict - all the tests we have done so far, z-test, t-test, hypothesis test. Make assumptions about the population (e. g. , or 1 - 2) Homegentity of variance - desn"t apply to a one condition experiment - are the means significantly different fron to another. Require data to be measured with an interval or ratio scale. Test hypothesis about proportions or relationships wihtin populations - not specific parameters. Make no assumptions about the population"s underlying distribtuion - so it doesn"t matter if it is normally distributed in the population or not. Can be used with nominal or ordinal data. Nonparametric equivalent of the single sample t test. Hypothesis test that uses proportions from a sample to make inference about proportions in the population. Degrees of freedom shows us the number of choices we had. Nonparametrict equivalenet of rh independant measures of t and anova. Identical to goodness of fit test, except we are now looking at the relatiosnhip between 2 variables.
