Regression Model: Linear Relationships and Types of Regression Techniques

Name of the Student
Name of the professor
Institution Affiliation
City/State
Year/ Month/ Day

LITERATURE REVIEW
Introduction
Regression model
Regression analysis is among the common methods used for statistical analysis. It was
founded by Sir Francis Galton. Regression assists in studying how a response variable depends
on single or many predictors. Low dimensional sufficient summary plot is pursued in regression

graphics. These are the type of plots which do not require construction model but they have all
the information needed from the predictors. Regression analysis is also an extension of
correlation and it provides the evaluator with an opportunity to relationship outcome with an
interval-level variable. Dependent variable sometimes is known as Y- caused by other variables
and independent variables which is also referred to as X- and it is caused changes independent
variables [1]. The proper predictor when the correlation is zero is the mean
Numerous simulation procedures were developed in order to facilitate the performance. The
calibration procedure for programs assists in the formation of baseline models which were
developed in the 1990s. a graphical procedure is developed to allow visual based analysis of data
based on computer simulation. The calibrated approaches are used follow;
 Either the post-retrofit or base year data unreliable or unavailable
 The facility and the data can be modeled by well-documented simulation software
 An experienced simulation professional is available and is funded adequately by the
collecting appropriate input data and calibrating the simulation model [2].
Regression approach also allows modeling, examining and exploring spatial relationship
and explain the factors such as observing the spatial pattern. It can also be used for prediction
and it is also a starting point for all spatial regression analyses. Mapping is also done in
regression. It simply involves re-projecting the entire map in order to fit the other one. Mapping
regression is carried out by comparing the features individually and the process involves
resolving differences between the map scales [1].
The neural network helps in the provision of the attractive way to determine the data on
the dependent factors [3]. The neural network is appropriately viewed as a set of powerful non-

linear factors. The neural network can also be used as a pre-processor in order to replace the data
which are missing.
Scope of work
The regression model is a statistical procedure which enables a researcher to estimate the
linear, or straight line, a relationship that shows the relation between two or more variables. It is
this linear relationship that summarizes the amount of change in another variable(s). This model
may sometimes be used in testing the statistical importance, for instance, to test whether the
observed linear relationship could have emerged by chance or not. It is in this second course that
statistical methods, multivariate regression with relationships among several variables are
examined and discussed [4].
The two major variable regression model assigns one of the variables the status of an
independent variable while assigning the other variable the status of a dependent variable. The
independent variable is known to be the causative agent of changes in the dependent variable, or
the independent variable may occur prior in time to the independent variable. It can be noticed
that the researcher in our case cannot be certain of a causal relationship, even with the regression
model [5]. Moreover, if at all the researcher has a to make one of the variables an independent
variable, then the manner in which this independent variable is associated with changes in the
dependent variable can be estimated. When using the regression model, one needs to examine the
expression of the straight line first and this is given in the next section. It is by following this
procedure that we can arrive at the formula for determining the regression line from the observed
data [2].