Experiment 4 (Linear and Nonlinear regression)

THEORY:
Regression analysis mathematically describes the relationship between a set of independent
variables and a dependent variable. In statistics, linear regression is a linear approach to
modelling the relationship between a dependent variable and one or more independent
variables. In linear regression, the relationships are modelled using linear predictor
functions whose unknown model parameters are estimated from the data. Such models are
called linear models. Linear regression has many practical uses. Most applications fall into
one of the following two broad categories: predicting responses and estimating variation in
response. Linear regression models are often fitted using the least squares approach.
There are several types of linear regression analyses available to researchers.
Simple linear regression:one dependent variable, one independent variable
Multiple linear regression: one dependent variable (interval or ratio), two independent
variables (interval or ratio or dichotomous)
NONLINEAR REGRESSION
In statistics, non-linear regression is a form of regression analysis in which observational data
are modelled by a function which is a nonlinear combination of the model parameters and
depends on one or more independent variables. The data are fitted by a method of successive
approximations. In this part we will discuss how to fit any set of functions of more than 2
parameters either appearing linearly (multiple linear regression), or nonlinearly (multiple
non-linear regression).
MULTIPLE REGRESSION USING EXCEL
The form of the equation is

The goal is to find the best M values of ai, given the M functions fi (x) and data yi = y
(xi), i =1, . . ., N
In Excel, you put the x values in a column and create additional columns, with each column
being a function, evaluated for the x value in that row. The example used here is to find the
constants in a reaction rate formula.
The expected expression is
and the goal is to find the values of k, n, and m that give the best fit of the rate for various
partial pressures of substances A and B. This form is not linear, which is a requirement of
multiple regression, but a transformation can make it linear. Take the logarithm of both sides
of the equation

This equation has the following form:

where the dependence upon two or more variables is clear.

PROCEDURE:
The data is entered into the libre office calc, and the various terms are transformed as shown
in next table. Columns A and B are the partial pressures of the two chemicals for which the
rate is measured, as indicated in column C.
Pa Pb

0.1044 0.1036

0.1049 0.2871

0.103 0.5051

0.2582 0.1507

0.2608 0.31

0.2407 0.4669

0.3501 0.0922

0.3437 0.1944

0.3494 0.5389

0.4778 0.1017

0.488 0.258

0.5014 0.5037
CALCULATIONS IN LIBRE OFFICE:

RESULT:

Rate equation by Linear regression is – rate = 7.10 Pa 0.98 Pb 1.9893

Rate equation by nonlinear regression is – rate = 6.97 Pa 0.956 Pb 0.195