Book Image

Hands-On Exploratory Data Analysis with R

By : Radhika Datar, Harish Garg
Book Image

Hands-On Exploratory Data Analysis with R

By: Radhika Datar, Harish Garg

Overview of this book

Hands-On Exploratory Data Analysis with R will help you build a strong foundation in data analysis and get well-versed with elementary ways to analyze data. You will learn how to understand your data and summarize its characteristics. You'll also study the structure of your data, and you'll explore graphical and numerical techniques using the R language. This book covers the entire exploratory data analysis (EDA) process—data collection, generating statistics, distribution, and invalidating the hypothesis. As you progress through the book, you will set up a data analysis environment with tools such as ggplot2, knitr, and R Markdown, using DOE Scatter Plot and SML2010 for multifactor, optimization, and regression data problems. By the end of this book, you will be able to successfully carry out a preliminary investigation on any dataset, uncover hidden insights, and present your results in a business context.
Table of Contents (17 chapters)
Free Chapter
1
Section 1: Setting Up Data Analysis Environment
7
Section 2: Univariate, Time Series, and Multivariate Data
11
Section 3: Multifactor, Optimization, and Regression Data Problems
14
Section 4: Conclusions

Grubbs' test and checking outliers

In statistics, or particularly in R programming, an outlier is defined as an observation that is far removed from most of the other observations. Often an outlier is present due to a measurement error.

The following script is used to detect the particular outliers for each and every attribute:

> outlierKD <- function(dt, var) {
+
var_name <- eval(substitute(var),eval(dt))

+
na1 <- sum(is.na(var_name))

+
m1 <- mean(var_name, na.rm = T)

+
par(mfrow=c(2, 2), oma=c(0,0,3,0))

+
boxplot(var_name, main="With outliers")

+
hist(var_name, main="With outliers", xlab=NA, ylab=NA)

+
outlier <- boxplot.stats(var_name)$out

+
...