Question

write an article with regression model

Answer 1

Regression model is a type of quantitative forecasting model as it calculates the relationship between two or more variables to predict the sales or demand forecasts etc. This model assumes that the one variable is associated with another variable and it tries to find out the relationship among them. For example there could be a relationship between time, budget of a product and expected sales. It is based on the historical data and it is used to forecast future sales/trend on the basis of past data and growth trends.

The regression model analyzes linear equation with two variables; dependent variable y and independent variable x. Generally least-squares linear regression technique is used to estimate the value based on past cost data. The term least-squares regression implies that the ideal fitting of the regression line is achieved by minimizing the sum of squares of the distances between the straight line and all the points on the graph.

The linear trend line Regression Equation is represented by the following equation

y = a + bx

Where a is the y-intercept of the line and b is the slope of the line.

Formula to calculate the a and b are following

Slope b = (n * Σxy – Σx * Σy) / {n * Σ(x^2) - (Σx)^2}

Intercept a = (Σy – b * Σx) / n

Where,

n is number of period

Σy is the sum of total dependent variables

Σx is the sum of independent variable

Σxy is the sum of the products of dependent and independent variables

Σx^2 is the sum of squares of independent variable

There are multiple regression tools also that help to determine the relationship between many independent variables and a dependent variable. This process finds out that how multiple independent variables are related to a dependent variable.

The multiple linear regression equation can be written in following manner –

y = b0 + b1 *x1 + b2 *x2 +………. + bn * xn

Where,

y is dependent variable

x1, x2,… xn are independent variables

b0 is the y-intercept of the line when all of the independent variables are zero

And b1, b2….bn are the estimated regression coefficients where each regression coefficient denotes the change in y relative to one unit change in the respective independent variable.