R Essential Training Part 2: Modeling Data

Course details

Trying to locate meaning and direction in big data is difficult. R can help you find your way. R is a statistical programming language to analyze and visualize the relationships between large amounts of data. It's one of the most important tools available for data analysis, machine learning, and data science. This training series provides a thorough introduction to R, with detailed instruction for working with R and RStudio and hands-on examples, from exploratory graphics to neural networks. In part two, Modeling Data, instructor Barton Poulson shows how to compute statistics, analyze data, predict outcomes, and group and classify cases. These are the fundamental techniques you need to generate meaningful insights for your organization.

Topics include:
Computing frequencies and correlations
Computing descriptive statistics
Conducting an item analysis
Comparing proportions
Comparing paired means
Comparing multiple means
Predicting outcomes with linear and logistic regression
Grouping cases with k-means clustering
Classifying cases with k-nearest neighbors
Creating ensemble models

Concepts

0. Introduction

01 - Model data with R
02 - Using the exercise files

1. R for Data Science

03 - Data science with R - A case study

2. Exploring Data

04 - Computing frequencies
05 - Computing descriptive statistics
06 - Computing correlations
07 - Creating contingency tables
08 - Conducting a principal component analysis
09 - Conducting an item analysis
10 - Conducting a confirmatory factor analysis

3. Analyzing Data

11 - Comparing proportions
12 - Comparing one mean to a population - One-sample t-test
13 - Comparing paired means - Paired samples t-test
14 - Comparing two means - Independent samples t-test
15 - Comparing multiple means - One-factor analysis of variance
16 - Comparing means with multiple categorical predictors - Factorial analysis of variance

4. Predicting Outcomes

17 - Predicting outcomes with linear regression
18 - Predicting outcomes with lasso regression
19 - Predicting outcomes with quantile regression
20 - Predicting outcomes with logistic regression
21 - Predicting outcomes with Poisson or log-linear regression
22 - Assessing predictions with blocked-entry models

5. Clustering and Classifying Cases

23 - Grouping cases with hierarchical clustering
24 - Grouping cases with k-means clustering
25 - Classifying cases with k-nearest neighbors
26 - Classifying cases with decision tree analysis
27 - Creating ensemble models with random forest classification

Conclusion

28 - Next steps