You are on page 1of 11

Correlation and Regression

Narasimha murthy

CORRELATION
The degree of relationship between two variables is known as correlation coefficient It is denoted by r It is due to Pearson It varies between 1 to +1 including 0

If x & y are two variables then correlation r is given by 1/n [(xi x) (yi y)]

[(xi x)2] n

[(yi y)2] n

Positive Correlation
wt 90 80 70 60 50 40 30 20 10 0 0 50 100 150 200

Negative Correlation
80 70 60 50 40 30 20 10 0 0 20 40 60 80 100

Multiple Correlation : Relation between three or more variables. Partial Correlation : Study of two variables excluding some other variables

Correlation can be tested by using Students t-test. t = r (n-2) / (1- r2 ) Which follows t-distribution with (n-2) d.f.

Regression
Actual relation ship between variables Prediction one variable with other variable or variables In regression analysis, we have dependent variable and independent variable or variables.

If we have one dependent and one independent variable , then regression is called simple regression. One dependent and several independent variables, then it is multiple regression. When dependent variable takes two values viz. 0 and 1 ,independent can take any value, then it is Logistic regression.

The regression equation is Y = a+bX Where Y is dependent variable and X independent variable. a is intercept and b regression coefficient. For different values X , Y can be estimated.

Y intercept is the Y value of the line when X equals zero. It defines the elevation of the line.

Regression line

You might also like