Index
A
- accuracy / Customer satisfaction analysis with the multiple logistic regression
- action of regressing / Going back to the origin of regression
- Akaike Information Criterion (AIC) / Simple logistic regression
- apodixis / Going back to the origin of regression
- area under curve (AUC) / Model fitting
- artificial neural networks (ANN) / Regression with neural networks
B
- BAS package
- used, for creating Bayesian linear regression / Bayesian model using BAS package
- batch GD / Stochastic Gradient Descent
- Bayes' theorem / Bayes' theorem
- Bayesian Information Criterion (BIC) / Bayesian model using BAS package
- Bayesian linear regression
- about / Bayesian linear regression
- probability, basic concepts / Basic concepts of probability
- Bayes' theorem / Bayes' theorem
- creating, with BAS package / Bayesian model using BAS package
- binning
- using, for discretization / Data discretization by binning
- BLR package
- about / The BLR package
- BLR / The BLR package
- sets / The BLR package
- Boston dataset
- random forest regression / Random forest regression with the Boston dataset
- Box-Cox power transformation / The MASS package
- breast cancer
- classifying, with logistic regression / Classifying breast cancer using logistic regression
C
- caret package / The caret package
- caret package, functions
- train / The caret package
- trainControl / The caret package
- varImp / The caret package
- defaultSummary / The caret package
- knnreg / The caret package
- plotObsVsPred / The caret package
- predict.knnreg / The caret package
- car package
- ANOVA / The car package
- linear.hypothesis / The car package
- cookd / The car package
- outlier.test / The car package
- durbin.watson / The car package
- levene.test / The car package
- ncv.test / The car package
- categorical data
- multiple logistic regression / Multiple logistic regression with categorical data
- categorical variables
- about / Categorical variables
- nominal variables / Categorical variables
- dichotomous variables / Categorical variables
- ordinal variables / Categorical variables
- certain event / Basic concepts of probability
- Classification and Regression Tree (CART) / Regression trees
- classification tree / Regression trees
- Comprehensive R Archive Network (CRAN)
- URL / Installing R
- conditional probability / Basic concepts of probability
- Cook's distance / Diagnostic plots
- correlation
- versus regression / Regression versus correlation
- about / Association between variables – covariance and correlation
- count data model
- about / Count data model
- Poisson distributions / Poisson distributions
- Poisson regression model / Poisson regression model
- warp breaks per loom, modeling / Modeling the number of warp breaks per loom
- covariance / Association between variables – covariance and correlation
- cross-validation
- used, for overfitting detection / Overfitting detection – cross-validation
- k-fold / Overfitting detection – cross-validation
- Leave-one-out cross-validation (LOOCV) / Overfitting detection – cross-validation
- Cumulative Distribution / Multivariate Adaptive Regression Splines
- customer satisfaction analysis
- with multiple logistic regression / Customer satisfaction analysis with the multiple logistic regression
D
- data scaling / Scale of features
- data wrangling
- about / Data wrangling
- data, viewing / A first look at data
- datatype, modifying / Change datatype
- empty cells, removing / Removing empty cells
- incorrect value, replacing / Replace incorrect value
- missing values / Missing values
- NaN values / Treatment of NaN values
- decision trees / Regression trees
- deduction / Understanding regression concepts
- Department of Transportation (DOT) / Creating a linear regression model
- dependent / Regression versus correlation
- diagnostic plots / Diagnostic plots
- dimensionality reduction
- about / Dimensionality reduction
- principal component analysis / Principal Component Analysis
- discretization
- about / Discretization in R
- by binning / Data discretization by binning
- by histogram analysis / Data discretization by histogram analysis
- dummy coding / Discovering different types of regression
E
- Earth / Multivariate Adaptive Regression Splines
- ElasticNet regression / ElasticNet regression
- exponential family / Generalized Linear Model
F
- feature scaling
- about / Scale of features, Exploratory analysis
- min-max normalization / Min–max normalization
- z score standardization / z score standardization
- feature selection
- about / Feature selection
- stepwise regression / Stepwise regression
- regression subset selection / Regression subset selection
- Federal Highway Administration (FHWA) / Creating a linear regression model
- File Transfer Protocol (FTP) / Installing R
- Fitted values / Diagnostic plots
- Free Software Foundation's (FSF) / The R environment
- Froude number / Stepwise regression
G
- Galton universal regression law / Going back to the origin of regression
- Generalized Additive Model (GAM) / Generalized Additive Model
- Generalized Cross Validation (GCV) / Multivariate Adaptive Regression Splines
- generalized least squares (GLS) / The MASS package, Robust linear regression
- Generalized Linear Model (GLM)
- about / The R stats package, Generalized Linear Model, Ridge regression, Modeling the number of warp breaks per loom
- simple logistic regression / Simple logistic regression
- Generalized Ridge Regression (GRR) / Generalized Additive Model
- General Public License (GPL) / The R environment
- glmnet package, function
- glmnet / The glmnet package
- glmnet.control / The glmnet package
- predict.glmnet / The glmnet package
- print.glmnet / The glmnet package
- plot.glmnet / The glmnet package
- deviance.glmnet / The glmnet package
- globally convergent version (GRPROP) / Neural network model
- Gradient Descent (GD) / Gradient Descent and linear regression, Gradient Descent
H
- histogram analysis
- using, for discretization / Data discretization by histogram analysis
I
- impossible event / Basic concepts of probability
- independent / Regression versus correlation
- indicator variables / Discovering different types of regression
- induction / Understanding regression concepts
- inference / Understanding regression concepts
- Integrated Development Environment (IDE) / RStudio
- interquartile range (IQR) / Finding outliers in data
- iteratively reweighted least squares (IRLS) / Robust linear regression
K
- K-Nearest Neighbor (KNN) regression / The caret package
L
- Lars package
- about / The Lars package
- lars / The Lars package
- summary.lars / The Lars package
- plot.lars / The Lars package
- predict.lars / The Lars package
- lasso regression / Lasso regression
- least absolute deviations / Lasso regression
- least absolute errors / Lasso regression
- least squares / Lasso regression
- least squares regression / Least squares regression
- Leverage / Diagnostic plots
- linear regression
- with SGD / Linear regression with SGD
- linear regression model
- creating / Creating a linear regression model
- statistical significance test / Statistical significance test
- model results, exploring / Exploring model results
- diagnostic plots / Diagnostic plots
- about / Gradient Descent and linear regression, Robust linear regression
- with SGD / Linear regression with SGD
- linear relationships
- searching / Searching linear relationships
- lobules / Classifying breast cancer using logistic regression
- log-Iteration / Linear regression with SGD
- log-linear model / Count data model
- log-odds / The logit model
- logistic regression
- about / Understanding logistic regression
- logit model / The logit model
- used, for classifying breast cancer / Classifying breast cancer using logistic regression
- exploratory analysis / Exploratory analysis
- model, fitting / Model fitting
- logit / The logit model
- Log Posterior Odds / Bayesian model using BAS package
- Lowess curve / Multivariate Adaptive Regression Splines
M
- marginal likelihood / Bayes' theorem
- MARS model equation / Multivariate Adaptive Regression Splines
- Mean Square Error (MSE) / Linear regression with SGD, Overfitting detection – cross-validation, Multivariate Adaptive Regression Splines, Multiple linear model fitting
- milk ducts / Classifying breast cancer using logistic regression
- min-max normalization / Min–max normalization
- model
- building / Building a model
- model results
- exploring / Exploring model results
- Model Selection / Multivariate Adaptive Regression Splines
- multicollinearity / Ridge regression
- multinomial logistic regression / Multinomial logistic regression
- multiple linear model
- fitting / Multiple linear model fitting
- Multiple Linear Regression (MLR) model
- concepts / Multiple linear regression concepts
- building / Building a multiple linear regression model
- with categorical predictor / Multiple linear regression with categorical predictor
- categorical variables / Categorical variables
- model, building / Building a model
- about / Bayesian linear regression
- multiple logistic regression
- about / Multiple logistic regression
- customer satisfaction analysis / Customer satisfaction analysis with the multiple logistic regression
- with customer satisfaction analysis / Customer satisfaction analysis with the multiple logistic regression
- with categorical data / Multiple logistic regression with categorical data
- Multivariate Adaptive Regression Splines (MARS) / Multivariate Adaptive Regression Splines
- multivariate models / Discovering different types of regression
- multivariate multiple regression / Discovering different types of regression
N
- National Weather Service (NWS) / Min–max normalization
- neural networks
- using, for regression / Regression with neural networks
- exploratory analysis / Exploratory analysis
- about / Neural network model
- nonlinear least squares / Nonlinear least squares
- nonlinear least squares, arguments
- about / Nonlinear least squares
- formula / Nonlinear least squares
- data / Nonlinear least squares
- start / Nonlinear least squares
- control / Nonlinear least squares
- algorithm / Nonlinear least squares
- trace / Nonlinear least squares
- subset / Nonlinear least squares
- weights / Nonlinear least squares
- na.action / Nonlinear least squares
- model / Nonlinear least squares
- upper bounds / Nonlinear least squares
- lower bounds / Nonlinear least squares
- Normal Q-Q plot / Building a multiple linear regression model
- Not a Number (NaN) / A first look at data
- null hypothesis / Statistical significance test
O
- Ordinary Least Squares (OLS) / Ridge regression, Robust linear regression, Nonlinear least squares
- outliers
- searching, in data / Finding outliers in data
- about / Robust linear regression
- overfitting
- about / Understanding overfitting
- detection, with cross-validation / Overfitting detection – cross-validation
P
- partial / Multiple logistic regression
- penalized quasi-likelihood (PQL) / The MASS package
- perfect linear association
- modeling / Modeling a perfect linear association
- Poisson distributions / Poisson distributions
- Poisson regression model / Poisson regression model
- polynomial regression / Polynomial regression
- Posterior Inclusion Probabilities (pip) / Bayesian model using BAS package
- posterior probability / Bayes' theorem
- precision / Customer satisfaction analysis with the multiple logistic regression
- Principal Component Analysis (PCA) / Principal Component Analysis
- principal components / Principal Component Analysis
- prior probability / Bayes' theorem
- probability
- basic concepts / Basic concepts of probability
R
- R
- installing / Installing R
- precompiled binary distribution, using / Using precompiled binary distribution
- installing, on Windows / Installing on Windows
- installing, on macOS / Installing on macOS
- installing, on Linux / Installing on Linux
- source code, installation / Installation from source code
- random forest regression
- with Boston dataset / Random forest regression with the Boston dataset
- exploratory analysis / Exploratory analysis
- multiple linear model, fitting / Multiple linear model fitting
- about / Random forest regression model
- Receiver Operator Characteristic (ROC) / Model fitting
- regression
- origin / Going back to the origin of regression
- applications / Regression in the real world
- about / Understanding regression concepts
- versus correlation / Regression versus correlation
- types / Discovering different types of regression
- R packages, using / R packages for regression
- with neural networks / Regression with neural networks
- regression subset selection / Regression subset selection
- regression towards mediocrity / Going back to the origin of regression
- regression tree
- about / Regression trees
- splitting / Regression trees
- pruning / Regression trees
- tree selection / Regression trees
- regularization
- about / Regularization
- ridge regression / Ridge regression
- lasso regression / Lasso regression
- ElasticNet regression / ElasticNet regression
- R environment / The R environment
- resampling
- bootstrap resampling / Overfitting detection – cross-validation
- Residual QQ / Multivariate Adaptive Regression Splines
- Residuals / Diagnostic plots
- Residual Sum of Squares (RSS) / Ridge regression, Multivariate Adaptive Regression Splines
- Residuals vs Fitted values / Multivariate Adaptive Regression Splines
- resilient backpropagation (RPROP) / Neural network model
- ridge regression / Ridge regression
- Road Casualties Great Britain (RCGB) / Ridge regression
- Road Traffic Accidents (RTA) / Ridge regression
- robust linear regression / Robust linear regression
- Robust Regression Model / Robust linear regression
- R packages
- using, for regression / R packages for regression
- R stats package / The R stats package
- car package / The car package
- caret package / The caret package
- glmnet package / The glmnet package
- sgd package / The sgd package
- BLR package / The BLR package
- Lars package / The Lars package
- RStudio
S
- sensitivity / Model fitting
- sgd package / The sgd package
- sgd package, functions
- sgd / The sgd package
- print.sgd / The sgd package
- predict.sgd / The sgd package
- plot.sgd / The sgd package
- simple logistic regression / Simple logistic regression
- smallest absolute gradient (sag) / Neural network model
- smallest learning rate (slr) / Neural network model
- specificity / Customer satisfaction analysis with the multiple logistic regression, Model fitting
- Standardized residuals / Diagnostic plots
- standard score / z score standardization, Neural network model
- statistical significance test / Statistical significance test
- stepwise regression
- about / Stepwise regression
- forward method / Stepwise regression
- backward method / Stepwise regression
- stepwise method / Stepwise regression
- stochastic / Stochastic Gradient Descent
- Stochastic Gradient Descent (SGD) / The sgd package, Stochastic Gradient Descent
- Support Vector Machine (SVM) / Support Vector Regression
T
- Theoretical Quantiles / Diagnostic plots
- TIOBE
- URL / The R environment
- True Negative Rate (TNR) / Customer satisfaction analysis with the multiple logistic regression, Model fitting
- true positive rate (TPR) / Model fitting
U
- UCI Machine Learning Repository
V
- variables
- relationships / Association between variables – covariance and correlation
Z
- z score standardization / z score standardization, Neural network model