Ch 8 - Cost Estimation Flashcards
There are _____ steps of cost estimation. What are they?
Six
- Define the cost object for which the related costs are to be estimated
- Determine the cost drivers
- Collect consistent and accurate data on the cost object and the cost drivers
- Graph the data
- Select and employ an appropriate estimation method
- Evaluate the accuracy of the cost estimate.
What is the most important step in developing a cost estimate?
Identifying cost drivers
What are the two main estimation methods?
The high-low method and regression analysis
mean absolute percentage error (MAPE)
A measure of cost-estimation accuracy, calculated as the mean (average) absolute percentage prediction error.
Of the two estimation methods, which one is most accurate?
regression analysis
high-low method
A method using algebra to determine a unique cost estimation line between representative high and low points in a given data set.
regression analysis
A statistical method for obtaining the unique cost-estimating equation that best fits a set of data points.
least squares regression
A cost-estimation method in which the variable and fixed cost coefficients are found by minimizing the sum of the squares of the estimation errors.
dependent variable
In cost estimation, the cost to be estimated, aka the cost object
independent variable
A cost driver used to estimate the value of the dependent variable.
simple linear regression
Used to describe regression applications having a single independent variable.
multiple linear regression
Used to describe regression applications having two or more independent variables.
What is the principal advantage of the regression analysis method?
It is a unique estimate that produces the least estimation error. However, it can be strongly influenced by outlier data.
What is the goal when choosing independent variables in the regression analysis method?
The goal is to choose variables that (1) change when the dependent variable changes, that is, there is a predictive relationship (correlation) between the dependent and the independent variables and (2) do not duplicate other independent variables.
dummy variable
Used in a regression model to represent the presence or absence of a condition.