Bivariate statistical measures regression and correlation

Bivariate statistical measures regression and correlation

1. Regression

   • It is used to derive an equation that relates a criterion variable to a or more of prediction; if one is used variable is called regression analysis simple and if you use more it is called multiple regression analysis
     • Simple Linear regression
       • The relationship is explained exists between the variable answer "Y" and a single explanatory variable "X"
     • Multiple regression
       • Work with a variable interval or ratio level. It is possible to analyze the same way the relationship between two or more through equations
     • Logistic regression
       • It is used to predict the result of a categorical variable, in function of the variables independent or predictive
   • Regression analysis
     • Statistical: Allows incorporate a component random in the relationship
     • Standardized: The slope "β1" tells us if there is a relationship between two variables
     • Deterministic: Under ideal conditions, the independent variable can be a mathematical function of the independent variables.
   • Regression problems
     • Inhomogeneous variance
     • Non linear relationship
     • correlated errors

2. Correlation

   • It is used to measure the closeness of the linear relationship between two or more variables on an interval scale.
     • Bivariate measures
       • Coefficient of determination R1
         • Simple linear correlation
           • Positive correlation and negative correlation
             • Scatter plots
               • Regression
                 • Simple regression
                   • Multiple regression