Data Analysis and Forecasting for AutoMobile Inc. Expansion

This report presents a data analysis and forecasting study conducted for AutoMobile Inc., a car distributor considering market expansion. The analysis focuses on identifying factors influencing vehicle ownership in various Asian countries using 2019 data. The report employs scatter graphs to visualize the correlation between vehicles per thousand population and various factors like income, population, population density, and urban population percentage. Regression analysis is performed to determine the relationship between closely associated variables. The report further explores the correlation between total vehicle ownership and factors like income, population, population density, and urban population. Regression equations are calculated and interpreted for the most relevant variables, providing insights into market expansion opportunities. The report also includes an analysis specific to Cyprus, comparing actual and predicted figures and suggesting areas for improvement. The study aims to help AutoMobile Inc. make informed decisions about its expansion strategy by understanding the key drivers of vehicle ownership and market potential.

Data Analysis
and
Forecasting

Abstract
Forecasting and data analysis for most important factors being used in
order to identify future prospects of the company. In this regard, use of
correlation and regression are being adopted by the Auto mobile
incorporation in order to identify its respective requirement of market
expansion from future prospects. It involves regression equation, correlation
methods and use of scatter graph in respect of analysing historic data of
Auto mobile incorporation.

Table of Contents
Abstract...........................................................................................................2
Introduction.....................................................................................................4
Main Body........................................................................................................4
a) Scatter graphs of historical data as given ...............................................4
b) Preparation of regression line equation and interpretation of results in
reference to closely associated variables....................................................8
....................................................................................................................8
c) Scatter graph of given data ....................................................................9
d) Linear Regression line and its interpretation ........................................11
e) Suggestion for most suitable regression equation in respect of
usefulness of the company........................................................................12
f) Analysis of data in respect of Cyprus......................................................13
Conclusion.....................................................................................................13
References.....................................................................................................15

Introduction
Data analysis and forecasting is a significant term which are used to
analyse available inputs to reach at a quantitative conclusion. In
statistics, forecasting implies the usage of historical inputs in order o
make certain predictions which will be helpful in analysis of trends in
current time. The data collected needs to be appropriate in order to carry
forecasting from business prospective. In this reference, report includes
implementation on regression analysis which useful term of statistics. It
is used in order to identify relationship between dependent variable and
other independent variables. There are also various forms of regression
presentation which will be discussed later in the report in reference to
Auto mobile Inc. which is a car distributor and thinking of expanding its
operations.
Main Body
a) Scatter graphs of historical data as given
Correlation is a term which is used to examine relationship between
two or more quantitative terms or variables. It is very useful in practical life,
as it suggests connection between variables as to understand their future
relevance in terms of behaviour (Wei and et. al., 2021). It is important to
analyse future in order to draw maximum of benefits and profits from an
activity. In order to identify relationship between two variables, correlation
coefficient is calculated. It reflects value between -1 to 1. If there is 0
correlation coefficient, it becomes that there is no relationship between
units. If it comes to -1 there is perfect negative correlation and 1 suggests
perfect positive correlation between variables. It is significantly valuable in
practical sense, as it helps to understand how to variables are correlated in a
specific manner as may be provided.
In this regard, sales historical data of Auto Mobile incorporation is
evaluated in order to identify correlation between various variables as
suggested by the organisation (Wang and et. al., 2020). Analysis has been
made in order to suggest organisation which factors are optimum in order to
expand its market further. Therefore, in this reference, various historical data
such as income, population, population density, population in urban areas

and their respective correlation with vehicles per 1000 population is
interpreted with the help of scatter graph in the following manner.
Scatter graph showing vehicles per thousand populations against income
By interpreting above graph it is concluded that vehicles per thousand
populations against income per capita reflects high positive correlation with
each other (Karabiber and Xydis, 2020). The correlation between both of the
variables is 0.724069 which is near to 1. As it is believed that resulting
correlation between two variables is perfect when outcome is 1. If it goes in
minus, then it reflects negative correlation between two variables. But in the
given scatter graph, given variables are moving in the upward trend in right
direction which means that the given variable have positive correlation with
each other in respect of Auto mobile incorporation.
Scatter graph showing vehicles per thousand populations against
population

In above graph, resulting correlation between given variables is
0.161741925 which is considered as weak positive correlation as it is
nowhere close to 1. Therefore, vehicles per thousand population and
population are two variables which are said to be unlikely correlated with
each other. Due to vast difference between vehicle per thousand head and
population it is said to be weaker connection between given variables.
Scatter graph showing vehicles per thousand populations against
population density
As shown from above graph, it is interpreted that correlation between
population density and vehicles per thousand populations is very weak

(Yu, Zhang and Qin, 2018). The respective correlation between these
variables are 0.015426099 which is considered as very weak as per
correlation theory. The above mentioned variables have same impact
with each other but they are not much closely interconnected variables.
It means that increase in population density will also increase vehicles
per thousands of populations but such rise will not be of much
importance.
Scatter graph showing vehicles per thousand populations against
percentage of population in urban areas
In this given evaluation, these two variables have positive
correlation of fairly moderate range. As calculated correlation between
these variables is 0.391982381 which is identified as moderate
correlation of units. It means that increase in one variable will not affect
other variable in much proportion. This situation occurs when given

historicl data have unidentified increasing right upward trend which can
be seen in the above scatter data.
b) Preparation of regression line equation and interpretation of results in
reference to closely associated variables
In the above scatter graph, the most closely correlated variables are
said to be per capita income and vehicles per thousand population. As their
correlation was identified nearer to 1 which tells that these variables impact
each other in optimistic manner. In above graph, these variables are used to
identify regression line equation in order to understand given factors in
future prospective (Zhang and et. al., 2018). Regression analysis plays key
role in respect of decision making by the superiors. Regression line is
equated as y = mx + b where Y= dependent variable, m= intercept and b= slope
of the line. Therefore, as per this analysis, it is interpreted that above graph
shows moderate correlation between two above mentioned variables. Liner
regression line is best fit when the result is more than or equal to 0.9, but in this
graph the result is 0.5 which means that the above data has moderate level of
correlation with each other. In reference to Auto mobile incorporation, it has been
determined that given historical data of 2019 which includes various elements,
suggests that per capita income and vehicles per thousand population has close
correlation with each other which means that change in one factor will modify

other factors as well. Therefore, increase in per capita income will give rise to
increased vehicles per thousand populations.
c) Scatter graph of given data
Scatter graph showing total vehicle ownership against per capita income
In this data, it is analysed that given variables have weak negative
correlation which is identified through application of correlation formula.
Negative correlation arises when outcome is expressed in negative terms
(Bahrami and et. al., 2018). The negative correlation is 0.16142801 which is
considered as weak negative correlation.
Scatter graph showing total vehicle ownership against population

In the above scatter graph, it is identified that total vehicle ownership
and population has high positive correlation with each other. Their respective
correlation outcome is 0.987115489 which is classified as positive
correlation. In this graph, total vehicle ownership and population has been
analyzed and it is identified that they have optimum level of correlation with
each other.
Scatter graph showing total vehicle ownership against population density
In above visual graph, it is identified that given two variables have
weak positive correlation with each other. It means that change in one

variable will hardly affect other variables. Their respective correlation is
0.281222701 which is classified under category of weak positive correlation.
Scatter graph showing total vehicle ownership against population in urban
areas
Here it is determined that total vehicle ownership and population in
urban areas have very weak positive correlation with each other. It is
identified that these variables have reflected 0.117480069 correlation which
is very low yet positive.
d) Linear Regression line and its interpretation

In above analysis, it is identified that total vehicle ownership is closely
associated with population as compared to other variables (Woo and Owen,
2019). They produce high positive correlation with each other which is said
to be good for organizational development in the long term. It becomes
easier to identify chances of deviations as organization knows that which
variable is affected with which variable. From above analysis, it is interpreted
that total vehicle owned has better correlation with population as compared
to other factors. Also they tend to have positive right upward movement
which suggests that these variables present best fitted linear regression line
as compared to others. In respect of Auto mobile incorporation, they need to
focus on population factor in regard to increase their respective market
segment (Desai and Ouarda, 2021).
e) Suggestion for most suitable regression equation in respect of usefulness
of the company
Regression equation is an important tool in statistics which is used to
determine relationship between given set of data, if exists (Ginker and
Lieberman, 2021). Various data given in a table form or other form can be
represented with the use of regression equation in more appropriate
manner. It helps in prediction of future events with the help of visual graph
or through an equation. Regression line is said to best fit for a data. It is
helpful in sorting the data in more presentable manner which is easy to
understand.
In this report, data of 2019 in reference to Auto mobiles incorporation
has been evaluated in order to identify future prospects of the company in
order to expand its relative operations in further market. From above
analysis, two most suitable regression equations are vehicles per thousand
populations to per capita income and total vehicles ownership to population.
As these two produces best positive correlation with respective variables.
The organization must focus over variables such as per capita income and
populations in reference to expansion of its operations in new segment. As
these regress equations reflect most appropriate results in reference to the
said organisation so that these are considered as best suitable regression
equations from organization's point of view. As regression equation helps in