FCS 200 Lecture Notes - Lecture 11: Descriptive Statistics, Regression Analysis, Alternative Hypothesis
Document Summary
A few types of statistical tests: research question: Statistical tests for mean differences: t-test for independent samples, t- statistic, anova, f-statistic. Statistical significance and p value: a result is statistically significant if we conclude that it is not very likely to have occurred by chance, use p-values to determine the significance, the smaller the p-value the better. Chi-squared test: written as x^2 test, used to determine whether sample data show an association, or a difference in a pattern/ distribution of data by group. It is a probability distribution test: used on categorical data. Regression: multiple regression can assess simultaneous effects or associations of multiple predictor/independent variables on a single outcome/ dependent variable, linear relationship to the data, like a correlation. Types of inferential errors (inference is not exact: any time we make a decision using inferential statistics, there are 4 possible outcomes, researchers decision. Practical significance: what statistical significance means, the results were not likely due to chance.