COM 470 Lecture Notes - Lecture 20: Multivariate Analysis, Empirical Relationship, Dependent And Independent Variables
Document Summary
Description of subsets of cases, subjects or respondents. Bivariate analysis: the analysis of two variables simultaneously, for the purpose of determine the empirical relationship between them. Constructing a bivariate table: determine logical direction of relationship (independent variable and dependent variable), percentage down versus percentage across. Contingency table: a format for presenting the relationship among variables as percentage distributions. Guidelines for presentation of tables: a table should have a heading or title that describes what is contained in the table, original content should be clearly presented, the attributes of each variable should be clearly indicated. Welsh 3: the base on which percentage are computed should be indicated, missing data should be indicated in the table. Multivariate analysis: the analysis of the simultaneous relationships among several variables. Multivariate techniques allow the researcher to address issues with facts. For example, measuring multiple variables at the same time can be used to explain why women make less than men in the job market.
