Scribd
Upload
52 views23 pages

Multivariate Analysis

This document discusses various types of multivariate analysis techniques including multiple regression analysis, multiple discriminant analysis, multivariate analysis of variance, and canonical correlation analysis. It describes the characteristics, assumptions, purposes, and examples of these statistical methods for analyzing multiple variables.

Uploaded by

Dev Kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
52 views23 pages

Multivariate Analysis

This document discusses various types of multivariate analysis techniques including multiple regression analysis, multiple discriminant analysis, multivariate analysis of variance, and canonical correlation analysis. It describes the characteristics, assumptions, purposes, and examples of these statistical methods for analyzing multiple variables.

Uploaded by

Dev Kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 23

MULTIVARI

ATE
ANALYSIS
TAKSHIKA GOYAL
MBA(FINANCE)
200101040025
UNIVARIATE

BIVARIATE

MULTIVARIATE
MULTIVARIATE
ANALYSIS
 This is a collection of methods for analyzing data in which a
number of observation are available for each object .

 Means this is a statistical technique which simulteneously


analyse more than two variables on a sample of observations
can be categorised.
DEFINITION
 A collectionof procedure
for analyzing the
association between two
or more sets of
measurement that were
made of each object in
one or more sample of
objects.
CHARACTERISTICS

 This deal with reality , possess the ability to analysis


complex data.

 This gives realistic result.

 Helps in decision making.

 Arrange a large number of complex information


involved in real data into simplified visible form.
Measurement scale

No. of variables

Dependence or
Interdependence
Metric Non-Metric

• Interval • Nominal
• Ratio • Ordinal
Types of
variable

Explanatory Criterion
DIFFERENT COMBINATIONS
Measurement of
Scale

Dependent Independent
Variable Variable

Metric Scale

Regression Analysis
SIMPLE
1 DV 1 IDV REGRESSION
ANALYSIS

MULTI
1 DV >1 IDV REGRESSION
ANLYSIS

CANONICAL
>1 DV >1 IDV ANALYSIS
CORELLATION
MULTIPLE REGRESSION ANALYSIS

A statisticalmeasure
that attempts to
determine the strength
of relationship between
one dependent variable
and a series of other
changing variable.
Measurement of
Scale

Dependent
Variable Independent
Variable
(>2)

Non-Metric Form Metric Form

Multiple Discriminant Analysis


MUTLTIPLE
DISCRIMINANT
ANALYSIS
 It is a classification problem , where two or more group
of population are known as a priori.

 Example :
If we want to predict the use of the net banking
customers based on years of education and age of a person.
 There are two possiblities :

Use of net banking is qualitative


YES OR NO

Age and Year are quantitative variable

(yes or no ) is function of age and year


= a+b1 age + b2 year of education
PURPOSE
 When we want to create the distinction
in the dependent variables in more
than two groups then it will be called
as MDA.

 To investigate difference among


groups.

 To classify cases into group.

 To test theory by observing whether


cases are classified as predicted.
ASSUMPTIONS
 Group of dependent variable are mutually exclusive and
the group sizes are not grossly different that means we
cant have one group of very large number and other with
very small number.
 Variables are independent of each other.
 The number of independent variables is not more than 2
less dependent variables and the sample size is n then
k<= n-2.
MULTIVARIATE ANALYSIS OF
VARIANCE
This is appropriate when several
metric dependent variable are
involved in research study along with
many non-metric explanatory
variable.
ASSUMPTIONS
 The independent variable are categorical.
 There are multiple dependent variable.

 There is relationship between dependent variable.

 The number of observation for each combination of the


factor are same.

PURPOSE
 To determine if individual categorical independent
variable have an effect on a group or related set of
individual dependent variable.
 EXAMPLE:
A call centre manager wants to know if the operator or method of
answering calls makes a difference on average hndle time, wait time
and customer satisfaction.
INDEPENDENT VARIABLE : CALL OPERATOR AND
METHOD OF ANSWER
DEPENDENT VARIABLE : AVERAGE HANDLE TIME , WAIT
TIME , CUSTOMER SATISFACTION

 H0 : the means of AHT,WT,CS are the same for Operator 1&2.


 Ha : the mean of AHT, WT,& CS are not the same for operator 1 & 2

 H0 : the means of AHT,WT,CS are same for method of answer 1&2


 Ha : the means of AHT,WT,CS are not same for the method of
answer 1&2
CANONICAL CORRELATION
ANALYSIS
 It is suitable where there are many dependent variables
and various independent variables.

DVs IDVs

Sales Engine size

Resale Horsepower

Price Length

MPG Fuel capacity

You might also like