1

RESEARCH CLUB – SCHOOL OF COMMERCE

PRESENTS

RESEARCH WEEK
26th April to 30th April 2024

ORGANIZED BY
B.K. SCHOOL OF MANAGEMENT
 2
Analysis vs. Analytics

application of logical and

refers to the process of segmenting computational reasoning to the
your problem into easily digestible component parts obtained in an
chunks that you can study analysis. And in doing that one is
individually and examine how they looking for patterns and often
relate to each other. exploring what she could do with
them in the future.
 3
Types of Data Analytics

 Business Analytics for Competitive Advantage -> Develops Data-Driven Approaches to Managerial Decisions
using these key Analytics capabilities.

 Descriptive Analytics: What happened?

 Diagnostic Analytics: Why did it happen?
 Predictive Analytics: What is likely to happen?
 Prescriptive Analytics: What should I do about it?
 Today, businesses whether big or small, apply a broad-based business analytics driven culture to achieve excellence
and growth, make informed and optimized decisions, improve outcomes and manage risk which sets them apart.
Types of Data Analytics: 4

Comprehensive Approach
• method to discover a pattern in large data sets using databases
Text Analytics or data mining tools.

• shows "What happened?" by using past data in the form of

Statistical Analytics dashboards.
• Descriptive Analysis and Inferential Analysis.

• analyses complete data or a sample of summarized

Descriptive Analytics numerical data.
• find different conclusions from the same data by selecting
Inferential Analytics different samples.

• shows "Why did it happen?" by finding the cause from the insight
Diagnostic Analytics found in Statistical Analysis.

• shows "What might happen in future?" predicting value of one

Predictive Analytics variable when we have value of another variable

• combines the insight from all previous Analysis to determine which

Prescriptive Analytics action to take in a current problem or decision.
 5
Techniques of Data Analysis

Data Analysis

Optimization
Univariate Bivariate Multivariate
Techniques

Descriptive Inferential Descriptive Inferential Descriptive Inferential Unconstrained Constrained

 6
Univariate Descriptive Statistics

Univariate
Descriptive
Analysis

Measures of
Measures of Measures of Measures of
Central
Dispersion Skewness Kurtosis
Tendency
 7
Univariate Analysis: Summary Measures

Describing Data Numerically

Central Tendency Variation Shape Kurtosis

Absolute Skewness
Arithmetic Mean
Median Quartiles Range Interquartile Range
Mode Deciles Mean Deviation
Percentiles Quartile Deviation
Geometric Mean Standard Deviation Variance

Harmonic Mean Relative Coefficients of these Measures

 Descriptive Analysis of Univariate
Data: Skewness

Shape of a Distribution: Symmetric or skewed

 Describes how data is distributed
 Measures of shape

Left-Skewed Symmetric Right-Skewed

Mean < Median < Mode Mean = Median =Mode Mode < Median < Mean

8
 9
Descriptive Analysis of Univariate Data:
KURTOSIS

 The height and sharpness of the peak relative to the rest of the data or the slope of the curve and the
frequency height is called Kurtosis. Balanda and Mac Gillivary say that increasing Kurtosis is associated with
the movement of the probability mass from the shoulders of a probability distribution into its center and
tails
 10
Descriptive Analysis of Univariate
Data: Kurtosis
 11
Kurtosis

Leptokurtic Mesokurtic Platykurtic

(high peak) (normal) (low peak)
(+ ve kurtosis) (zero kurtosis) (- ve kurtosis)
Mesokurtic distribution…kurtosis = 3
Platykurtic distribution…kurtosis < 3
Leptokurtic distribution…kurtosis > 3
 Statistical Tests for Different 12

Measurement Scales
Scale Descriptive Measures Inferential Measures
Nominal Percentage, Mode, Chi-Square, Binomial
Count test
Ordinal Quartiles, Percentiles, Spearman’s Rank
Deciles, Median Correlation, Friedman,
ANOVA
Interval Mean, Range, Product-moment
Standard Deviation correlation, t tests,
regression.
Ratio Geometric Mean, All Statistical tests can
Harmonic Mean, be performed.
Coefficient of
Variation
 13
Now we will run Descriptive Statistics in
SPSS

 Choose Analyze → Descriptive Statistics → Frequencies.

 Select variables of your interest from the left list box, and press the arrow button to drop it in
the Variable(s) list box. More than one variable can be selected from the list of variable in the
study using Shift key.

 Click on Statistics and select appropriate measures then click OK.

 Click on Charts and select appropriate chart then click OK.

 Click on OK.
 14
BIVARIATE ANALYSIS

 Bivariate data is used for little complex analysis than as compared with univariate data.
 Bivariate data is the data in which analysis are based on two variables per observation
simultaneously.
 Purpose: Determining empirical relationship between two variables
 Bivariate analysis is a simple (two variable) special case of multivariate analysis.
 Bivariate analysis can be helpful in testing simple hypotheses.
 It can help to determine at what extent it becomes easier to know and predict a value for one
variable (possibly a dependent variable) if we know the value of the other variable (possibly
the independent variable).
 Cross classification, correlation, analysis of variance, simple regression etc. are some applications
of bivariate analysis.
 15
Tools and Techniques for Bivariate Analysis

Bivariate
Analysis

Simple Simple Two Sample

Association of Two Sample
Correlation Regression Non
Attributes Parametric Test
Analysis Analysis Parametric Test
 16
Correlation

 Correlation coefficient—number used to describe the strength and direction of association between
variables
▪ Very strong = .80 through 1
▪ Moderately strong = .60 through .79
▪ Moderate = .50 through .59
▪ Moderately weak = .30 through .49
▪ Very weak to no relationship 0 to .29

-1.00 0.00 1.00

Perfect Negative No Perfect Positive
Correlation relationship Correlation
 17
Correlation: Pearson’s r

 Interval and/or ratio variables

 Pearson product moment coefficient (r)
 two interval variables, normally distributed
 assumes a linear relationship
 Can be any number from 0 to -1 : 0 to 1 (+1)
 Sign (+ or -) shows direction
 Number shows strength
 Linearity cannot be determined from the coefficient
e.g.: r = .8913
 The population correlation coefficient ρ (rho) measures the strength of the association between the
variables
 The sample correlation coefficient r is an estimate of ρ and is used to measure the strength of the linear
relationship in the sample observations
 18
Statistical Relationship : Rank Correlation

 Spearman’s rho Commonly used distribution-free (nonparametric) measure of correlation between

two ordinal variables.
 For all of the cases, the values of each of the variables are ranked from smallest to largest, and the
Pearson correlation coefficient is computed on the ranks.
 Spearman’s rank correlation coefficient is

 The rank correlation coefficient takes a value between –1 and +1.

 19
Introduction to Regression Analysis

 Regression analysis is used to:

◦ Predict the value of a dependent variable based on the value of at least one independent variable
◦ Explain the impact of changes in an independent variable on the dependent variable
Dependent variable: the variable we wish to explain
Independent variable: the variable used to explain the dependent variable
 20
Regression Analysis

Regression analysis examines associative relationships between a metric dependent variable and one or
more independent variables in the following ways:
 Determine whether the independent variables explain a significant variation in the dependent variable:
whether a relationship exists.
 Determine how much of the variation in the dependent variable can be explained by the independent
variables: strength of the relationship.
 Determine the structure or form of the relationship: the mathematical equation relating the independent
and dependent variables.
 Predict the values of the dependent variable.
 Control for other independent variables when evaluating the contributions of a specific variable or set of
variables.
 Regression analysis is concerned with the nature and degree of association between variables and does
not imply or assume any causality.
 21
Simple Linear Regression Model

 Only one independent variable, x

 Relationship between x and y is described by a linear function
 Changes in y are assumed to be caused by changes in x
 22
Types of Regression Models

Positive Linear Relationship Relationship NOT Linear

Negative Linear Relationship No Relationship

 23
Population Linear Regression

The population regression model:

Population Random Error

Population Independent term, or
Slope
y intercept Variable residual
Coefficient
Dependent
Variable

y = β0 + β1x + ε
Linear component Random Error
component
 24
Population Linear Regression

y y = β0 + β1x + ε
Observed
Value of y for
xi
εi Slope =
Predicted β
Random Error 1
Value of y for
xi for this x value

Intercept =
β0
xi x
 25
Estimated Regression Model

The sample regression line provides an estimate of the

population regression line

Estimated Estimate of Estimate of the

(or the regression
predicted) y regression slope
value intercept
Independe

ŷi = b0 + b1x nt variable

The individual random error terms ei have a mean of zero

 26
Least Squares Criterion

b0 and b1 are obtained by finding the values of b0 and b1 that minimize the sum of the squared residuals

e 2
=  (y −ŷ) 2

=  (y − (b 0 + b1x)) 2
 The Least Squares Equation

The formulas for b1 and b0 are:

b1 =
 ( x − x )( y − y )
sy
 (x − x) 2
b1 = r
algebraic equivalent:
sx

 xy − n x y and

b1 = b0 = y − b1 x
 x 2
−
(  x ) 2

n
Chap 13-27
 28
Interpretation of the Slope and the Intercept

 b0 is the estimated average value of y when the value of x is zero

 b1 is the estimated change in the average value of y as a result of a one-unit

change in x
 29
Coefficient of Determination
R2

 The coefficient of determination is the portion of the total variation in the dependent variable that is
explained by variation in the independent variable

 The coefficient of determination is also called R-squared and is denoted as R2

SSR
R = 2

SST where 0 R 1 2
 30
Coefficient of Determination
(continued)
R2

Coefficient of determination

SSR sum of squares explained by regression

R =
2
=
SST total sum of squares
Note: In the single independent variable case, the
coefficient of determination is

R =r 2 2

where:
R2 = Coefficient of determination
r = Simple correlation coefficient
 31
Examples of Approximate R2 Values
y
R2 = 1
Perfect linear relationship
between x and y:
x
R2 = 1
y 100% of the variation in y
is explained by variation in
x

x
R2 = +1
 32
Examples of Approximate R2 Values

y
0 < R2 < 1

Weaker linear relationship

between x and y:
x
y Some but not all of the
variation in y is explained
by variation in x

x
 33
Examples of Approximate R2 Values

y R2 = 0
No linear relationship
between x and y:

The value of Y does not

x depend on x. (None of the
R2 = 0
variation in y is explained
by variation in x)
 34
Now we will run Regression in SPSS

 Choose Analyze → Regression → Linear.

 Move your continuous dependent variable into the Dependent box.

 Move your independent variables into the Independent box.

 For Method make sure Enter is selected.

 Click on the Statistics button and select: Estimates, Confidence Intervals, Model fit, Descriptives, Part and
Partial correlations and Collinearity diagnostics.

 Click on Continue and then OK.

Thank You