A Practical Guide to Data Mining for Business and Industry

5 Analytics

Analytics

1. 5.1 Introduction
2. 5.2 Basis of Statistical Tests
   1. 5.2.1 Hypothesis Tests and P Values
   2. 5.2.2 Tolerance Intervals
   3. 5.2.3 Standard Errors and Confidence Intervals
3. 5.3 Sampling
   1. 5.3.1 Methods
   2. 5.3.2 Sample Sizes
   3. 5.3.3 Sample Quality and Stability
4. 5.4 Basic Statistics for Pre-analytics
   1. 5.4.1 Frequencies
   2. 5.4.2 Comparative Tests
   3. 5.4.3 Cross Tabulation and Contingency Tables
   4. 5.4.4 Correlations
   5. 5.4.5 Association Measures for Nominal Variables
   6. 5.4.6 Examples of Output from Comparative and Cross Tabulation Tests
5. 5.5 Feature Selection/Reduction of Variables
   1. 5.5.1 Feature Reduction Using Domain Knowledge
   2. 5.5.2 Feature Selection Using Chi-Square
   3. 5.5.3 Principal Components Analysis and Factor Analysis
   4. 5.5.4 Canonical Correlation, PLS and SEM
   5. 5.5.5 Decision Trees
   6. 5.5.6 Random Forests
6. 5.6 Time Series Analysis

5.1 Introduction

Data needs to be explored and analysed, and decisions need to be made. These activities are sometimes referred to as descriptive analytics and predictive analytics. Here, we include details of carrying out comparative tests and cross tabulations and consider how to detect correlations and patterns in the data that can be useful in selecting variables to build a model.

In data mining, there are special issues when testing features of the data because of the size of the datasets; statistical significance tests have to be interpreted differently. There are also issues when working with subsets sampled from the data, how the subsets are ...