Regression analysis is a statistical procedure for developing a mathematical equation that describes how the dependent variable (y) is related to the independent variable(x).
Step-by-step explanation:
REGRESSION ANALYSIS
Regression analysis is a statistical method used to determine the relationship between two or more variables of interest way. It is a way of sorting out variables which have impact mathematically. It is a more sophisticated way of examining the relationship between two (or more) variables than is correlation. The major differences between correlation and regression are:
Regression can investigate the relationships between two or more variables.
It determines the direction of causality, from the explanatory variable (or variables) to the dependent variable.
The impact of each explanatory variable on the dependent variable is measured.
Regression analysis explains this causal relationship by fitting a straight line drawn through the data, which best summarises them. It is sometimes called ‘the line of best fit’ for this reason.
Regression analysis gives answers to such questions as:
Which factors matters most?
Which factors can be ignored?
How do these factors interact with each other?
Does the growth rate influence a country’s birth rate?
If the growth rate increases, by how much might a country’s birth rate be expected to fall?
Are other variables important in determining the birth rate?
In regression analysis, factors are called Variables. There are two (2) types of variables.
1. Dependent variables: This is the main factor you are trying to predict
2. Independent variables: This is the factor you suspect has an impact on the dependent variable.
The equation of the sample regression line may be written as
Zi = a + bXi
Where;
Zi is the predicted value of Y for observation
Xi is the value of the explanatory variable for observation
a is the bare fixed coefficients to be estimated. It measures the intercept of the regression line on the Y-axis
b measures its slope.
The regression analysis equation describes how the dependent variable (y) is related to the independent variable(x). It allows you to predict the outcome of a relatively small amount of error.
