Least-Squares Regression Method
A mixed cost can be split into variable and mixed components by a statistical technique called simple linear regression analysis. This technique methematically calculates the y-intercept and the slope of a striaght line that ideally fits through a set of points on a graph. In least-squares method, the ideal fitting of the regression line is achieved by minimizing the sum of squares of the distances between the line and all the points on the graph.
In cost behavoir analysis, the cost volume formula "y = a + bx", is equivalent to regression line. Its y-intercept (a) and slope (b) represent the total fixed cost and variable cost per unit respectively, can be calculated by solved following simulataneos linear equations of least-squares regression analysis:
By solving the above equations for total fixed cost (a) and variable cost per unit (b), we obtain: