MBA804: QUANTITATIVE ANALYSIS

Introduction

What is Quantitative Analysis?

Quantitative analysis is the use of systematic scientific approach with the help of Mathematical
models, theories and assumptions in the analysis and interpretation of data in order to make
effective and efficient decisions.

We can also define Quantitative methods as a science of making rational decisions in the presence
of uncertainty using mathematical models derived from probability theory.

Importance of Quantitative methods

1. Enables one use Mathematical models and theories for future planning and forecasts.
2. Understand the application and use of mathematical models to obtain solutions and make
informed decisions
3. Make quick and precise decisions
4. Organize and present data in a logical form
5. Evaluate the reliability of the actions made
6. The various statistical measures of “average’, “dispersion, “skewness”, “correlation’, etc.
are generally useful for enabling comparison between different time periods or
geographical areas.
7. ‘Regression’ analysis enables establishment of relationship between various economic
factors, e.g input and output, production and sales, demand and per capita income.
‘Regression equation of a dependent variable upon one or several independent variables
also helps in assessing the impact of each of the several factors, and may be used for
forecasting.

Attributes, variables and Data

A variable is a characteristic that changes or varies over time and/or for different individuals or
objects under consideration. For example, body temperature is a variable that changes over time
within a single individual. Religious affiliations, income, height, age, weight, parity, are all
variables.
Data is a set of measurements that result when a variable is measured on a set of experimental
units. An experimental unit is the individual/ or object on which a variable is measured. One or
more variables can be measured on the same experimental unit. Univariate data results when a
single variable is measured on a single experimental unit. Bivariate data result when two variables
are measured on a single experimental unit. Multivariate data result when more than two variables
are measured on the same experimental unit. Data is indeed the raw material of statistics.

The character of statistical information collected from a group of individuals or objects, is of two
types – quantitative and qualitative.
Qualitative Variables – Measure a quality or characteristic on each experimental unit. Qualitative
variables produce data that can be categorized according to similarities or differences in kind. The
data is often referred to as categorical data. Technically, the qualitative character is an attribute.
An attribute cannot be measured but can be classified under different heads or categories.
Examples of attributes that will produce categorical data include; Color, Taste ranking, Political
affiliation etc.
N/B: In the case of qualitative variables, measurement in the usual sense of the word is not
achievable. Thus we make counts/frequencies that belong to the various categories. It is this that
we manipulate when our analysis involves qualitative variables.

Quantitative Variables – These measure a numerical quantity or amount on each experimental

unit. These variables produce numerical data. Examples of these variables include; Weight of
preschool children, Temperature, time, Blood pressure, Serum Cholesterol level, age of patients
seen in a dental clinic etc. The quantitative character is technically called a variable. A variable
takes different values and can be measured numerically in suitable units.

Sources of data.
Are classified in two groups namely:-
1. Primary Sources
2. Secondary sources.

Primary Sources/data
Are defined as those items that are original to the problem under study and this can be in two
categories.
a) Remains of a given period e.g. skeletons, weapons, tools, utensils, fossils etc.
b) Those items that have had a direct physical relationship with the events being re-constructed
(oral or written testimony) provided by actual participants or withers of an event or participants
themselves. Documents considered as primary themselves. Documents considered as primary
sources include manuscripts, files, publication, and research reports.

Secondary Sources of data

Are those that do not bear direct physical relationship to the event being studied. Some of these
are quote materials, textbooks, encyclopedia, prints or paintings.

Descriptive Statistics

What is Statistics?
It is the subject of scientific study, which deals with
i. The theories and methods of collection, organization, summarization and analysis of data.
ii. The drawing of inferences about a body of data when only a part of the data is observed.
Thus the purpose of statistics is to investigate and evaluate the nature and meaning of information inherent in data.

Descriptive statistics
Descriptive statistics are a means of organizing and summarizing observations. They provide us with an overview of
the general features of a set of data. Descriptive statistics can assume a number of different forms; among these are
tables, graphs and numerical summary measures. We present the various methods of displaying a set of data, determine
what kind of data we have and lastly we discus which technique is the most appropriate in a given circumstance.

Inferential Statistics
One of the most basic concepts in statistics is sampling. In most statistical problems, a specified number of
measurements/data (referred to as a sample) is drawn from a much larger set of measurements (called the population).
Often it is difficult to study the population and thus we try to describe or predict the behavior of the population on the
basis of information obtained from a representative sample from the population. Inferential statistics is the branch of
statistics that provides the procedures used to make inference about population characteristics from information
contained in the sample drawn from the population.

Ways to summarize data or present data

Tables
– Frequency tables (frequency distributions)
– Relative frequencies (percent of total)

Graphs
– Bar charts
– Frequency polygons
– Scatter plots

Histogram
It is a diagrammatic representation used for quantitative data consisting of continuously joined vertical bars meeting
at class boundaries, the areas contained by the bars being drawn proportional to the frequencies of the classes they
represent.
From histograms, frequency polygons can be generated. This makes it much easier to compare two or more histograms
generated from different groups of data. The frequency polygons are obtained by joining the midpoint tops of the
Histogram.

Ogive (Cumulative frequency Polygon)

This is obtained by plotting the cumulative frequencies or cumulative relative frequencies (vertical axis) against the
upper class boundaries. The ogives are useful in;
 Determining some of the summary measures (ie. Median, quartiles, deciles or percentiles)
 Determining cumulative frequency corresponding to a given measure of the variable under consideration
 Determining the number (or proportion) of observations expected to lie between two values of the variable
under consideration

Bar Charts
A bar chart comprises a number of spaced rectangles, which generally have their major axes vertical. They can be
used to represent a large variety of statistical data e.g. simple, component and multiple bar graphs.

Pie Charts
These are extensively used means of presenting data where actual numerical quantities are not so important. It is made
up of sectors showing the contribution of the components that make up a whole.
Example: Suppose we posses the following information concerning the central heating installations in Kenya:

Type of central heating Number of Households (millions)

Gas-fired 18.00
Electric 9.00
Oil – fired 11.25
Solid fuel 6.75

This information can be represented by a pie chart as follows:

 Central Heating Installations

Gas-fired

15% Electric
40%
25%
Oil – fired

20%
Solid fuel

Stem and leaf plots

This plot represents a graphical display of the data using actual numerical values of each data point. It is constructed
as follows;
 Divide each measurement into two parts: the steam and the leaf.
 List the stems in the column, with a vertical line to their right.
 For each measurement, record the leaf portion in the same row as its corresponding stem.
 Order the leaves from lowest to the highest in each stem.
 Provide a key to your stem and leaf coding so that the reader can recreate the actual measurements if
necessary.
Example: The following data deal with the aflatoxin levels of raw peanut. Approximately

30 26 26 36 48 50
16 31 22 27 23 35
52 28 37
Use the information to construct a stem and leaf plot to display the distribution of the data.

Stem Leaf
(tens) (Units)
1 6
2 662738
3 06157
4 8
5 02

In this case the number of 10s forms the “stem” and the unit digits represent the leaves.