Multivariate Analysis

An Introduction to Multivariate Analysis

Data analytics is all about looking at various factors to see how
they impact certain situations and outcomes.
 When dealing with data that contains more than two
variables, you’ll use multivariate analysis.
 Multivariate analysis isn’t just one specific method—rather, it
encompasses a whole range of statistical techniques.
 These techniques allow you to gain a deeper understanding of
your data in relation to specific business or real- world
scenarios.
 So, if you’re an aspiring data analyst or data scientist,
multivariate analysis is an important concept to get to grips
with.
1. What is multivariate analysis?
 In data analytics, we look at different variables (or factors) and how
they might impact certain situations or outcomes.
 For example, in marketing, you might look at how the variable “money
spent on advertising” impacts the variable “number of sales.”
 In the healthcare sector, you might want to explore whether there’s a
correlation between “weekly hours of exercise” and “cholesterol
level.”
1. What is multivariate analysis?
 This helps us to understand why certain outcomes occur, which in turn
allows us to make informed predictions and decisions for the future.
 There are three categories of analysis to be aware of:
 Univariate analysis, which looks at just one variable
 Bivariate analysis, which analyzes two variables
 Multivariate analysis, which looks at more than two variables
1. What is multivariate analysis?
As you can see, multivariate analysis encompasses all statistical
techniques that are used to analyze more than two variables at once.
 The aim is to find patterns and correlations between several variables
simultaneously—
Allowing for a much deeper, more complex understanding of a given
scenario than you’ll get with bivariate analysis.
An example of multivariate analysis
Let’s imagine you’re interested in the relationship between a person’s
social media habits and their self-esteem.
You could carry out a bivariate analysis, comparing the following two
variables:
1. How many hours a day a person spends on Instagram
2. Their self-esteem score (measured using a self-esteem scale)
An example of multivariate analysis
An example of multivariate analysis
You may or may not find a relationship between the two
variables;
However, you know that, in reality, self-esteem is a complex
concept.
It’s
likely impacted by many different factors—not just how
many hours a person spends on Instagram.
You might also want to consider factors such as age,
employment status, how often a person exercises, and
relationship status (for example).
An example of multivariate analysis
In order to deduce the extent to which each of these variables
correlates with self-esteem, and with each other, you’d need to
run a multivariate analysis.
So we know that multivariate analysis is used when you want to
explore more than two variables at once.
Now let’s consider some of the different techniques you might use to
do this.
Multivariate data analysis techniques and examples
There are many different techniques for multivariate analysis,
and they can be
divided into two categories:
1. Dependence techniques
2. Interdependence techniques
Multivariate analysis techniques: Dependence vs.
interdependence
When we use the terms “dependence” and “interdependence,”
we’re referring to different types of relationships within the
data.
Dependence methods

Dependence methods are used when one or some of the

variables are dependent on others.
Dependence looks at cause and effect;
In other words, can the values of two or more independent
variables be used to explain, describe, or predict the value of
another, dependent variable?
Dependence methods

To give a simple example, the dependent variable of “weight”

might be predicted by independent variables such as “height”
and “age.”
In machine learning, dependence techniques are used to build
predictive models.
The analyst enters input data into the model, specifying which
variables are independent and which ones are dependent
Dependence methods

—in other words, which variables they want the model to

predict, and which variables they want the model to use to
make those predictions
Interdependence methods

Interdependence methods are used to understand the

structural makeup and underlying patterns within a dataset.
In this case, no variables are dependent on others, so you’re
not looking for causal relationships.
Rather, interdependence methods seek to give meaning to a
set of variables or to group them together in meaningful ways.
Interdependence methods
So: One is about the effect of certain variables on others, while the
other is all about the structure of the dataset.
Some useful multivariate analysis techniques are
 Multiple linear regression
 Multiple logistic regression
 Multivariate analysis of variance (MANOVA)
 Factor analysis
 Cluster analysis
Multiple linear regression
Multiple linear regression is a dependence method which looks at the
relationship between one dependent variable and two or more
independent variables.
A multiple regression model will tell you the extent to which each
independent variable has a linear relationship with the dependent
variable.
This is useful as it helps you to understand which factors are likely to
influence a certain outcome, allowing you to estimate future outcomes.
Example of multiple regression:
As a data analyst, you could use multiple regression to predict crop
growth.
In this example, crop growth is your dependent variable and you want
to see how different factors affect it.
Your independent variables could be rainfall, temperature, amount of
sunlight, and amount of fertilizer added to the soil.
A multiple regression model would show you the proportion of
variance in crop growth that each independent variable accounts for.
Multiple logistic regression
Logistic regression analysis is used to calculate (and predict) the
probability of a binary event occurring.
A binary outcome is one where there are only two possible outcomes;
either the event occurs (1) or it doesn’t (0).
So, based on a set of independent variables, logistic regression can
predict how likely it is that a certain scenario will arise.
It is also used for classification.
Example of logistic regression:
Let’s imagine you work as an analyst within the insurance sector and
you need to predict how likely it is that each potential customer will
make a claim.
You might enter a range of independent variables into your model,
such as age, whether or not they have a serious health condition, their
occupation, and so on.
Using these variables, a logistic regression analysis will calculate the
probability of the event (making a claim) occurring.
 Another oft-cited example is the filters used to classify email as
“spam” or “not spam.”
Cluster analysis
Another interdependence technique, cluster analysis is used to group
similar items within a dataset into clusters.
When grouping data into clusters, the aim is for the variables in one
cluster to be more similar to each other than they are to variables in other
clusters.
This is measured in terms of intracluster and intercluster distance.
Intracluster distance looks at the distance between data points within one
cluster.
This should be small.
Cluster analysis
Intercluster distance looks at the distance between data points in
different clusters.
This should ideally be large.
Cluster analysis helps you to understand how data in your sample is
distributed, and to find patterns.
Cluster analysis example:
A prime example of cluster analysis is audience segmentation.
 If you were working in marketing, you might use cluster analysis to
define different customer groups which could benefit from more targeted
campaigns.
 As a healthcare analyst, you might use cluster analysis to explore
whether certain lifestyle factors or geographical locations are associated
with higher or lower cases of certain illnesses.
Because it’s an interdependence technique, cluster analysis is often
carried out in the early stages of data analysis.