This book shows how a linear algebra equation can be fit to a data set using the R programming language. The first part of the book covers the basic theory of statistical linear modeling, and the second part works through some example data sets, covering different combinations of predictor and response types.
Part 1 - TheoryTheory of Linear ModelingLinear Models in PracticeDiscovering the Unknown Coefficients, Part 1Discovering the Unknown Coefficients, Part 2Predicting New ResponsesProperties of Variables16 Types of VariablesPredictor Variable TypeResponse Variable Type Part 2 - Examples Response Categorical Unordered 2 GroupCat Uno 2 → Cat Uno 2Cat Uno >2 → Cat Uno 2Cat Ord >2 → Cat Uno 2Num Dis BI–INF → Cat Uno 2Num Con BI–INF → Cat Uno 2 Response Numerical DiscreteCat Uno 2 → Num Dis BI–INFCat Uno >2 → Num Dis BI–INFCat Ord >2 → Num Dis BI–INFNum Dis BI–INF → Num Dis BI–INFNum Con BI–BI → Num Dis BI–INF Numerical Continuous Cat Uno 2 → Num Con INF–INFCat Uno >2 → Num Con BI–BICat Ord >2 → Num Con BI–INFNum Dis BI–INF → Num Con BE–INFNum Con BI–BI → Num Con BE–INF Two Predictor VariablesCat Uno 2 + Cat Uno 2 → Num Con INF–INFCat Uno 2 + Num Con INF-INF → Num Con INF–INFNum Con INF-INF + Num Con INF-INF → Num Con INF-INF Three Predictor VariablesCat Uno 2 + Cat Uno 2 + Cat Uno 2 → Num Con INF–INFCat Uno 2 + Cat Uno 2 + Num Con → Num Con INF–INFCat Uno 2 + Num Con + Num Con → Num Con INF–INFNum Con + Num Con + Num Con → Num Con INF–INF