## Monday, July 5, 2010

### Simple Linier Regression

A. Introduction
Regression is a measuring instrument which can also be used to measure whether there is any correlation. If we have two or more variables It is only fitting if we want to study how these variables are related or can be foreseen.

Regression analysis to investigate the relationship obtained is expressed in mathematical equations that express the functional relationship between the variables. The functional relationship between one predictor variable with a single criterion variable is called a simple regression analysis (single), while the functional relationship that is more than one variable is called multiple regression analysis.

The term regression (forecast / estimate) was first introduced by Sir Francis Galton in 1877 in connection with research on human height, namely the high child and high between her parents. In his research Galton found that children of parents high high tend to increase or decrease from the average population weight. Line showing the relationship is called the regression line.

Regression analysis was more accurate in analyzing the correlation, because the analysis was the difficulty in showing Slop (rate of change of a variable against another can be determined). Thus, through regression analysis, forecasting the value of the dependent variable in a more accurate value of the independent variables as well.

B. Linear Regression equation of Y on X
Linear regression equation of Y on X defined as follows:

Y = a + b X

Description:

Y = dependent variable
X = independent variable
a = intercept
b = regression coefficient / Slop

In the above equation, the value of a and b can be determined in the following manner:

Examples of simple regression exercise

Below are the data and work experience of eight sales turnover of marketing at Bang Toyib company
1. Determine the value of a and b!
2. Make a regression line equation!
3. What is the estimated sales turnover of a marketing that have 3.5 years work experience?

Completion:

1. value a = 3.25 and b = 1.25
2. The linear regression equation is
Y = a + bX
= 3.25 + 1.25 X
1. Predictive value of Y, if X = 3.5
Y = a + bX
= 3.25 + 1.25 X
= 3.25 + 1.25 (3.5)
= 7.625
Thus "Learning and Sharing" us this time .. Thanks