CHAPTER-1

INTRODUCTION:
Multiple linear regression

The simple linear regression model that is a model with a

single regression x that has a relationship with a response y that
is a straight line. This simple linear regression model is
y = β0 + β1 x + ε

Where the intercept β0 and the slope β1 are unknown constants

and ε is a random error component. The errors are assumed to
have mean zero and unknown variance σ². Additionally we
usually assume that the errors are uncorrected . This means that
the value of one error does not depend on the value of any other
error.
The mean of this distribution is
E(y/x) = β0 + β1x
and the variance is
Var (y/x) = Var(β0 + β1 x + ε) =σ²
Thus the mean of y is a linear function of x although the
variance of y does not depend on the value of x . Because the
errors are uncorrelated the response are also uncorrelated.
The parameters β0and β1 are usually called regression
coefficients have a simple and after useful interpretation. The
slope β1 is the change in the mean of the distribution of y
produced by a unit change in the mean of the distribution of y
produced by a unit change in x. If the range of data on x
includes x=0 then the intercept β0 is the mean of the distribution
of the response y when x=0. If the range of x does not include
zero then β0 has no practical interpretation.
The parameters β0 and β1 are unknown and must be estimated
using sample data.
1. The method of least squares is used to estimate β0 and β1.
That is we will estimate β0 and β1 so that the sum of the
squares of differences between the observations yi and the
straight line is minimum.

Yi=β0 + β1 xi + εi , i= 1,2,3,……….,n

Simple linear regression can only be used when one has two
continuous variables an independent variable and a dependent
variable. The independent variable is the parameter that is used
to calculate the dependent variable or outcome.
A multiple linear regression analysis is carried out to predict the
values of a dependent variable y given a set of p explanatory
variables (x1, x2,……,xp). The necessary theory for multiple
linear regression.
Multiple linear regression is used to estimate the relationship
between two or more independent variables one dependent
variable
A multiple linear regression model with two regressor variables
is
Y= β0 + β1 X1 + β2 X2 + ε

A multiple linear regression model with more regressor

variables is

Yi = β0 + β1 x1 + β2 x2 +……+βk xk + ε

Where i=n observation

Yi = dependent variables[
Β0 = y – interest
Β1 x1 = the regression coefficient of the first
Independent variables
 Βn xn = the regression coefficient of the last
independent variables
ε = model error
Here we assumed that the expected value of the error term ε is
zero the parameter β0 is the intercept of the regression plane . If
x1 x2 = 0 then β0 is the mean of y . Otherwise β0 has no
physical interpretation . The parameter β1 indicates the
expected changes in response y per unit change in x1 when x2
are held constant
In general the response y may be related to k regressor or
predictor variables

The model
Y = β0 + β1 x1 + β2 x2 + …….+ βk xk + ε
Is called multiple linear regression model with k regressor . The
parameters βj , j = 0,1,2,…k are called regression coefficients .
The parameter βj represents the expected change in the response
y per unit change in xj when all the remaining regression
variables xj (i≠j)are held constant . For the parameter
βj (j =1,2,….k)are called partial coefficient .
A hypothesis is an assumption about a population parameters .
It is a statement about the population that may or may not be
true . The hypothesis conclusion about accepting or not
accepting hypotheses .
A statistical hypothesis is an assertion or conjecture concerning
one or more population. Hypothesis testing is formulated in
term of two hypothesis
 H0 : The null hypothesis
 H1 : The alternate hypothesis
The null hypothesis represents the status of H0 . The hypothesis
that states there is no statistical significance between two
variables in the hypothesis .
The alternative hypothesis is against of the null hypothesis .
states that there is statistical significance between two variables .
holds true if the null hypothesis is rejected . Usually what the
researcher thinks is true and is testing .
A conjecture about the distribution of some random variables .
A hypothesis can be simple or composite does . A simple
hypothesis completely specifics the distribution . A composite
does not specify .

A three category variables can be included in a models as one

covariate , coded with values 0,1 and 2 corresponding to the
three categories .
This is generally incorrect , because it imposes an ordering on
the categories that may not exist in reality sometimes it’s ok to
do this for education categories . the correct approach to
incorporating three anordered categories is to define two
different indicator variables .
The hypothesis actually to be tested is usually given the symbol
H0 and is commonly referred to as the null hypothesis . it is the
hypothesis of no difference . it can be defined as the hypothesis
which is under our consideration and may have possible chances
of rejection under the assumption which are true . it is statistical
hypothesis that status that there no difference between a
parameter and specific value , or that there is no difference
between two parameters .
The other hypothesis which is assumed to be true when the null
hypothesis is false, is referred to as the alternative hypothesis ,
and is often symbolized H1 it is statistical hypothesis that states
that there is difference between two parameters .

Both the null and alternative hypothesis should of significance

before any statistical test of significance is conducted

For example
H0 : µ = 100
H1 : µ > 100