Professional Documents
Culture Documents
Linear Regression: Quantitative Techniques
Linear Regression: Quantitative Techniques
Linear regression
Linear regression is a method that studies the relationship between continuous variables. The
variables are plotted on a straight line. The linear regression can be calculated using the following
formula:
Y= a + bx
Where:
Y is the dependent variable
X is the independent variable
b is the slope of the regression line
a is the intercept of the regression line
The equation is usually used to compute for Total Cost. The formula is
TC = FC + VC/UxQ
Where
TC is total cost
FC is fixed cost
VC/U is variable cost per unit
Q is quantity
This method assumes linear relationship of costs and quantity, or the Relevant Range. The
method assumes that variable cost is a fixed charge per unit and total fixed costs is constant in any
production level. It is then possible to determine the fixed and variable costs by using a series of
equations
To compute for fixed cost, you have the option of using either the highest or lowest quantity. The
equation presented below assumes the highest activity cost
Then compute for the total cost using the regression equation.
The high-low method does not consider small details such as variation in costs. It assumes that fixed and unit
variable costs are constant, which is not always the case in real life. There are also other cost estimation tools
that can provide more accurate results. The leastsquares regression method takes into consideration all data
points and creates an optimized cost estimate. It can be easily and quickly used to yield significantly better
estimates than the high-low method.
The Method of Least Squares and Linear Programming
The least squares method is a statistical procedure to find the best fit for a set of data points by minimizing the
sum of the offsets or residuals of points from the plotted curve. Least squares regression is used to predict the
behavior of dependent variables. Of the cost estimation methods, this is the most accurate. It uses the
following equations to compute for the constant and variable coefficient: