October 30th 2018 Soci 217 The Logic of Multivariate Analysis and Social Statistics . Multivariate Analysis : The analysis of the simultaneous relationships among several variables. Examining simultaneously the effects of age, gender, and social class on religiosity would be an example of multivariate analysis. · Logic: Instead of one independent variable and one dependent variable, there is more than one independent variable. . We are looking at at least 3 variables . We seek an explanation through the use of more than one independent variable. . Example-> age, political affiliation and attitudes towards abortion Attitudes are dependant variables because we are saying political affiliation might affect you attitude to abortion o We can break our young and old down more " Young liberal · Young conservative · Old liberal · Old conservative o Attitudes to abortion · Favor · Oppose Logic of Multivariate Analysis Introduction . Focus: To delve into multivariate analysis a little more deeply by using the elaboration model to illustrate the fundamental logic of multivariate and causal analysis . The elaboration model is one method for doing multivariate analysis. It is a logical approach to data analysis-a systematic way to analyze cross-sectional data-equally applicable to a number of different alternative statistical methods. . Elaboration model definition: A logical approach to understanding the relationship between two variables through the simultaneous introduction of a third variable, usually referred to as a control or test variable. . The various outcomes of an elaboration analysis include replication, specification, explanation, and interpretation. The Origins of the Elaboration Model . The heart of the elaboration model and of multivariate analysis is to understand the nature of relationships by introducing other variables. · Having observed an empirical relationship between two variables (such as level of education and acceptance of induction), we seek to understand the nature of that relationship through the effects produced by introducing other variables. . The third variable is called the test or the control variable. . The relationship of this test or control variable to the other variables is called a partial relationship or a partial o Ex. In the last set of notes -> Black Male rates = Partial
October 30th 2018 Soci 217 . The partial relationships are then compared with the initial relationship discovered in the total sample, often referred to as the zero-order relationship to indicate that no test variables have been controlled for. · Terms defined: Test or control variable: A variable that is held constant in an attempt to clarify further the relationship between two other variables. Ex: Having discovered a relationship between education and prejudice, for example, we might hold gender constant by examining the relationship between education and prejudice among men only and then among women only. In this example, gender would be the test variable (also called the control variable). . Partial relationship: In the elaboration model, this is the relationship between two variables when examined in a subset of cases defined by a third (test) variable. Ex. In the