#8 Multiple Linear Regression & Multicollinearity in R

Week-8 R & data file: https://github.com/bkrai/Statistical-Modeling-and-Graphs-with-R Strategy for fitting multiple regression models; Problems with many explanatory variables; Multicollinearity TIMESTAMPS 00:00 Introduction 00:46 Categorical or factor explanatory variables, example - salary of professors 02:10 Multiple linear regression, dummy variables 06:31 Multiple linear regression (MLR) with significant variables 08:11 Markdown file in R, turning off messages related to libraries 11:10 Professor salary example in R 11:30 data partition 16:00 MLR with training data 16:50 OLS with all possible steps 18:04 stepAIC function, forward, backward & both directions 20:25 Prediction and model performance 22:50 Interactions in multiple linear regression 26:30 Plot for interactions 32:48 Polynomials in multiple linear regression 34:44 Selecting important variables in multiple linear regression 37:18 Forward selection, backward elimination and mixed selection 40:06 Full Vs reduced model, data - allbacks, partial F-test 43:19 Multicollinearity 44:47 Multicollinearity example, data on pizza sales 45:42 Three models with contradictions 47:22 Reason for contradictions 48:53 Which variable is really explaining variation? 50:00 Problem with Multicollinearity 53:42 Variance inflation factors (vif) 56:52 Why it is called variance inflation factor? 58:45 Mineral composition example 59:43 Coxite data in R 01:01:00 chart.Correlation function from PerformanceAnalytics library in R 01:03:10 vif in R 01:06:34 Correlations and VIFs 01:13:36 Read a CSV file in R, example with vehicle.csv file R is a free software environment for statistical computing and graphics, and is widely used by both academia and industry. R software works on both Windows and Mac-OS. It was ranked no. 1 in a KDnuggets poll on top languages for analytics, data mining, and data science. RStudio is a user friendly environment for R that has become popular. #LinearRegression #Multicollinearity