1
MULTIVARIATE ANALYSIS
TECHNIQUES
2
FACTORS INFLUENCING THE
SELECTION OF A DATA
ANALYSIS STRATEGY
• Previous steps of the marketing research
project—Problem definition, development
of an approach, and research design. Data
analysis is geared toward providing
information that will help answer the
problem at hand.
3
FACTORS INFLUENCING THE
SELECTION OF A DATA
ANALYSIS STRATEGY
• Known characteristics of the data—For
example, scale of measurement (nominal,
ordinal, interval, or ratio). Certain
techniques are only appropriate for certain
types of data.
4
FACTORS INFLUENCING THE
SELECTION OF A DATA
ANALYSIS STRATEGY
• Properties of the statistical techniques—
Different statistical techniques serve
different purposes and have different
underlying assumptions with varying
degrees of robustness to their violations.
Statistical techniques vary in their purpose
and involve different assumptions.
5
FACTORS INFLUENCING THE
SELECTION OF A DATA
ANALYSIS STRATEGY
• Background and philosophy of the
researcher—Researchers vary in degree of
sophistication and philosophies (in making
assumptions about the variables and their
underlying populations).
6
CLASSIFICATION OF
STATISTICAL TECHNIQUES
• Statistical techniques can be classified as
univariate and multivariate.
• Univariate techniques are appropriate for
analyzing data when there is a single
measurement of each element in the sample,
or if there are several measurements on each
element, each variable is analyzed in
isolation.
Independent Related
Independent Related
* Two- Group
t test
* Z test
* One-Way
ANOVA
* Paired
t test
* Chi-Square
* Mann-Whitney
* Median
* K-S
* K-W ANOVA
* Sign
* Wilcoxon
* McNemar
* Chi-Square
Metric Data Non-metric Data
Univariate Techniques
One Sample Two or More
Samples
One Sample Two or More
Samples
* t test
* Z test
* Frequency
* Chi-Square
* K-S
* Runs
* Binomial
8
• Multivariate techniques are suitable for
analyzing data when there are two or more
measurements on each element and the
variables are analyzed simultaneously.
• They differ from univariate (single
phenomenon) techniques in that they shift the
focus away from the levels (averages) and
distributions (variances) of phenomena,
concentrating instead upon the degree of
relationships (correlations or covariances)
among these phenomena.
9
• Multivariate statistical techniques can be
classified as dependence techniques or inter­
dependence techniques.
• Dependence techniques are appropriate when
one or more variables can be identified as
dependent variables and the remaining as
independent variables.
• In interdependence techniques, the variables
are not classified as dependent or independent;
rather, the whole set of interdependent
relationships is examined.
10
More Than One
Dependent
Variable
* Multivariate
Analysis of
Variance and
Covariance
* Canonical
Correlation
* Multiple
Discriminant
Analysis
* Cross-
Tabulation
* Analysis of
Variance and
Covariance
* Multiple
Regression
* Conjoint
Analysis
* Factor
Analysis
One Dependent
Variable
Variable
Interdependence
Inter-object
Similarity
* Cluster Analysis
* Multidimensional
Scaling
Dependence
Technique
Interdependence
Technique
Multivariate Techniques

Multivariate Analysis Techniques

  • 1.
  • 2.
    2 FACTORS INFLUENCING THE SELECTIONOF A DATA ANALYSIS STRATEGY • Previous steps of the marketing research project—Problem definition, development of an approach, and research design. Data analysis is geared toward providing information that will help answer the problem at hand.
  • 3.
    3 FACTORS INFLUENCING THE SELECTIONOF A DATA ANALYSIS STRATEGY • Known characteristics of the data—For example, scale of measurement (nominal, ordinal, interval, or ratio). Certain techniques are only appropriate for certain types of data.
  • 4.
    4 FACTORS INFLUENCING THE SELECTIONOF A DATA ANALYSIS STRATEGY • Properties of the statistical techniques— Different statistical techniques serve different purposes and have different underlying assumptions with varying degrees of robustness to their violations. Statistical techniques vary in their purpose and involve different assumptions.
  • 5.
    5 FACTORS INFLUENCING THE SELECTIONOF A DATA ANALYSIS STRATEGY • Background and philosophy of the researcher—Researchers vary in degree of sophistication and philosophies (in making assumptions about the variables and their underlying populations).
  • 6.
    6 CLASSIFICATION OF STATISTICAL TECHNIQUES •Statistical techniques can be classified as univariate and multivariate. • Univariate techniques are appropriate for analyzing data when there is a single measurement of each element in the sample, or if there are several measurements on each element, each variable is analyzed in isolation.
  • 7.
    Independent Related Independent Related *Two- Group t test * Z test * One-Way ANOVA * Paired t test * Chi-Square * Mann-Whitney * Median * K-S * K-W ANOVA * Sign * Wilcoxon * McNemar * Chi-Square Metric Data Non-metric Data Univariate Techniques One Sample Two or More Samples One Sample Two or More Samples * t test * Z test * Frequency * Chi-Square * K-S * Runs * Binomial
  • 8.
    8 • Multivariate techniquesare suitable for analyzing data when there are two or more measurements on each element and the variables are analyzed simultaneously. • They differ from univariate (single phenomenon) techniques in that they shift the focus away from the levels (averages) and distributions (variances) of phenomena, concentrating instead upon the degree of relationships (correlations or covariances) among these phenomena.
  • 9.
    9 • Multivariate statisticaltechniques can be classified as dependence techniques or inter­ dependence techniques. • Dependence techniques are appropriate when one or more variables can be identified as dependent variables and the remaining as independent variables. • In interdependence techniques, the variables are not classified as dependent or independent; rather, the whole set of interdependent relationships is examined.
  • 10.
    10 More Than One Dependent Variable *Multivariate Analysis of Variance and Covariance * Canonical Correlation * Multiple Discriminant Analysis * Cross- Tabulation * Analysis of Variance and Covariance * Multiple Regression * Conjoint Analysis * Factor Analysis One Dependent Variable Variable Interdependence Inter-object Similarity * Cluster Analysis * Multidimensional Scaling Dependence Technique Interdependence Technique Multivariate Techniques