The conditional independence tests depend on the nature of the variables involved. For categorical variables, the mutual information test is used, and for continuous ones the correlation coefficient is used. Conceptually, the mutual information measures how much information is shared between two random variables. On the other hand the correlation test evaluates if the correlation coefficient is statistically different from 0.
- Title Page
- Copyright and Credits
- About Packt
- Contributors
- Preface
- Getting Started with R and Statistics
- Introduction
- Technical requirements
- Maximum likelihood estimation
- Calculating densities, quantiles, and CDFs
- Creating barplots using ggplot
- Generating random numbers from multiple distributions
- Complex data processing with dplyr
- 3D visualization with the plot3d package
- Formatting tabular data with the formattable package
- Simple random sampling
- Creating diagrams via the DiagrammeR package
- C++ in R via the Rcpp package
- Interactive plots with the ggplot GUI package
- Animations with the gganimate package
- Using R6 classes
- Modeling sequences with the TraMineR package
- Clustering sequences with the TraMineR package
- Displaying geographical data with the leaflet package
- Univariate and Multivariate Tests for Equality of Means
- Linear Regression
- Introduction
- Computing ordinary least squares estimates 
- Reporting results with the sjPlot package 
- Finding correlation between the features 
- Testing hypothesis 
- Testing homoscedasticity 
- Implementing sandwich estimators 
- Variable selection 
- Ridge regression 
- Working with LASSO 
- Leverage, residuals, and influence 
- Bayesian Regression
- Nonparametric Methods
- Robust Methods
- Time Series Analysis
- Introduction
- The general ARIMA model 
- Seasonality and SARIMAX models 
- Choosing the best model with the forecast package 
- Vector autoregressions (VARs)  
- Facebook's automatic Prophet forecasting  
- Modeling count temporal data 
- Imputing missing values in time series  
- Anomaly detection 
- Spectral decomposition of time series 
- Mixed Effects Models
- Predictive Models Using the Caret Package
- Bayesian Networks and Hidden Markov Models
- Other Books You May Enjoy
How it works...
-
No Comment
..................Content has been hidden....................
You can't read the all page of ebook, please click here login for view all page.