Learning curve analysis is used in planning, budgeting, and forecasting and also to determine estimated labor costs when bidding on a contract. It is based on the idea that efficiency increases the more experience a person has with a given task. As a result, the time required for performing the task decreases as increases occur in the number of times the task has been performed. Learning curve analysis is useful in forecasting costs for the purpose of developing a bid or other pricing. However, it is not useful for measuring the average change in the manufacturing costs associated with a change in a cost driver.
Regression analysis is useful for forecasting future manufacturing costs by measuring the historical average change in the manufacturing costs associated with a change in a cost driver. Total costs begin at the fixed cost level and rise by the amount of variable cost per unit for each unit of increase in activity. In theory at least, total costs graph as a straight line that begins at the fixed cost level on the Y intercept and rises at the rate of the variable cost per unit for each unit of increase in activity. The cost function for total manufacturing costs is Y = F + VX Where: Y = Total costs F = Fixed costs V = Variable costs X = Total production The equation of the cost function can be found by the use of regression analysis. Once the equation of the cost function has been found, forecasting of future costs can be accomplished.
Time series analysis is used for forecasting values where time is the independent variable. Here, the independent variable is the value of the cost driver.
Exponential smoothing is a time series forecasting technique using the most recent period's actual value and the most recent period's forecasted value. Time series analysis is used for forecasting values where time is the independent variable. Here, the independent variable is the value of the cost driver.
|
