Regression Analysis in R: Linear Regression and Logistic Regression

This first chapter of the series of statistical data analysis using R, which the authors provides in this second part (PART II) of the book, introduces and practically illustrates to the users how to run a linear and logistic regression analysis in R. This statistical technique (regression) helps to estimate the association or dependency of relationship between two variables. Technically, there are two main points to consider when conducting regression analysis. First is to check whether a predictor variable (often called the independent variable—see Chap. 5 ) is good enough (measured through significant levels, e.g., p-values ≤ 0.05) in predicting the effect (outcome) or response of the targeted variable (the dependent variable). Second, the regression analysis can be used to determine what variable(s), in particular, are the significant predictors of the outcome (dependent variable) in the case of multiple independent variables. Linear regressionLinear Regression, as the name implies, assumes that the relationships between the independent and dependent variables are linear. Thus, a constant unit of change in one of the variables implies a constant unit of change in the other. On the other hand, unlike the linear regression that uses continuous variablesContinuous variables in its tests, the Logistic regressionLogistic Regression (an alternative or non-parametricNon-parametric equivalent of the linear regression) is used when the dependent variable is a categoricalCategorical or dichotomousDichotomous (binary) data, i.e., fits into one of two clear-cut categories.