Thanks for working with you

Running Head: EXPLORATORY DATA ANALYTICS

1

An Exploratory Data Analytics Approach for the Devices Lost in the Past six Days

Name

Institutional Affiliation

EXPLORATORY DATA ANALYTICS

2

Introduction
Exploratory Data Analytics (EDA) approach is a big topic incorporating a lot of
theoretical and practical content in the field of statistics. Many institutions/industries deploy
EDA for various purposes, such as checking assumptions and detecting mistakes in data from an
experiment/research. EDA knowledge is therefore, essential for industry because we do various
research and experiments. In our industry, for example, we collected data regarding the loss of
the company’s electric devices, and we shall use EDA to do the first analysis of the data. Despite
the availability of having many EDA approaches, multivariate graphical, univariate graphical,
multivariate non-graphical, and univariate non-graphical, the multivariate non-graphical
technique is the best to analyze the data we collected on the devices lost in our industry because
we have more than one parameter that we do not have to present in graphical forms.
Background Literature
EDA is a terminology that different people use different clauses to define. However,
according to 1.1.1. What is EDA? (n.d), EDA is a data analysis philosophy/approach employing
several techniques to test underlying assumptions, detect outliers and anomalies, extract
important variables, and uncover underlying structure. The definition mentioned above
incorporates what EDA does, thus implying its importance. Based on the type of data, there exist
several approaches that can be employed, as shown in the next paragraph.
Even though a person can do EDA in their way, there exist four standard techniques of
EDA. There are four standard techniques of EDA namely, multivariate graphical, univariate
graphical, multivariate non-graphical, and univariate non-graphical (Chapter 4, n.d., p.62).
Generally, univariate methods focus on one data colum...