Chapter 8 - Cost Estimation

the relevant range

High low predictions are only valid for activity that falls within what?

difference in cost for high and low activity points divided by the difference for the value of the cost driver for the high and low activity

How do you calculate b in the high low equation?

minimizing the sum of the squares of the estimation erro

How does regression analysis fit the data?

t-value

In a multiple regression, a variable with a low _____ should be removed to simplify the model and lead to more accurate cost estimates.

target costing and pricing

Managers commonly use cost estimation to assess the cost impact of different product designs or product enhancements in ________

approximately +/- one standard error distance around the regression line

The 67% confidence interval is measured by ______

independent variable

The cost driver used to estimate the value of the amount to be predicted in regression analysis is the _____

scale

The manufacture of similar products that differ in size is described by the term _____

Noticing outliers and nonlinearity

What are one of the things graphs are useful for?

trend and/or seasonality, outliers, data shift

What are some issues in implementing cost estimation methods?

it helps predict future costs, it helps identify the key cost drivers for a cost object, and the cost drivers and cost estimating relationships are useful in planning and decision making

What are the 3 important ways cost estimation facilitates strategic management?

cost drivers

What are the casual factors used in the estimation of a cost driver called?

r-squared (coefficient of determination), t-value, the standard error of the estimate, and the p-value

What are the four key measures in a regression analysis?

to facilitate: strategy development and implementation, planning and decision making, target costing and pricing, effective performance measurement, evaluation, and compensation

What are the reasons strategic management requires accurate cost estimates?

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 driver, graph the dat, select and employ an appropriate estimation method, and evaluate the accuracy of the cost estimate

What are the six steps of cost estimation?

R-squared, or coefficient of determination, t-value, and p-value

What are the statistical measures that can be used to evaluate the reliability of a regression analysis?

the high-low method and regression analysis

What are the two cost estimation methods used in this chapter?

a biased estimation

What can occur if either the highest or lowest point is not representative of the general relationship?

each period of data is calculated using the same accounting basis and all transactions are property recorded in the period in which they occurred

What does consistent mean?

the accuracy of the estimates from the regression

What does precision refer to?

the degree to which changes in the dependent variable can be explained by changes in the independent variable

What does r-squared tell us?

whether the regression reflects actual relationship

What does reliability indicate?

cost estimation objectives, available data, cost/ benefit considerations

What does the choice of aggregation level for the dependent variable depend on?

uses algebra to determine a unique estimation line between representative high and low points in the data

What does the high-low method do?

the risk that a particular independent variable only has a chance relationship to the dependent variable

What does the p-value measure?

application of the cost estimation model in planning and decision making, identification of key cost drivers, and prediction of future costs

What does the strategic role of cost estimation include?

the reliability of that independent variable

What does the t-value measure?

the resulting regression equation is not representative of most of the data

What happens if an outlier data point is not removed from a regression analysis?

the value of r-squared will be close to 1, regression will have high reliability, the data values in a graph will fall relatively near to the regression equation line

What happens in a regression with high R-squared?

2 standard-error distances

What is a 95% confidence interval?

when two or more independent variables are used

What is a multiple linear regression?

a statistical method for obtaining the unique cost-estimating equation that best fits a set of data points

What is a regression analysis?

when one independent variable is used

What is a simple linear regression?

the development of a well-defined relationship between a cost object and its cost drivers for the purpose of predicting the cost

What is cost estimation?

estimates costs for a particular cost object based on info on other cost objects and variables, where the info for all variables is taken from the same period of time

What is cross-sectional regression?

the distance measured from the regression line to one of the data points

What is each error in a regression analysis?

graph the data

What is important to do to identify unusual patterns?

two or more independent variables are highly correlated with each other

What is multicollinearity?

the degree to which an independent variable has a valid, stable, long-term relationship with the dependent variable

What is reliability?

the cost to be estimated (the cost object)

What is the dependent variable?

Y= a + (bx)

What is the equation for the high low method?

define the cost object

What is the first step in cost estimation?

choose variables that 1. change when the dependent variable changes and 2. do not duplicate other independent variables

What is the goal in choosing independent variables?

the cost driver used to estimate the value of the dependent variable

What is the independent variable?

a measure of cost estimation accuracy; calculated by taking the absolute value of each error then averaging those errors

What is the mean absolute percentage error?

identifying cost drivers

What is the most important step in developing the cost estimate?

Y= a + (bX) + e

What is the regression equation?

a measure of the dispersion of the actual observations around the regression line (a measure of accuracy)

What is the standard error of the estimate?

the application of regression analysis to predict future amounts, using prior period's data

What is time-series regression?

activity-based costing and linear estimation methods

What methods are needed when technology and complexity issues arise?

any outliers and any shift or nonlinearity in the data

What must be given special attention in developing a cost estimate?

0.05 or less

What p-value signifies a small risk that the independent variable has only a chance relationship to the dependent variable?

more than 2

What should the t-value be?

the one that best satisfies the objective of accuracy

What should the time period selected for estimating cost be?

the standard error of the estimate

What statistical measure can be used to evaluate the precision of a regression analysis?

correlation

When a given variable tends to change predictably in the same (or opposite) direction of a given change in another variable ___________ exists.

structural cost drivers

Which drivers involve plans and decisions that have a long-term and strategic impact on the firm?

the high low method

Which method studied in this chapter is the least accurate but easiest to understand?

regression analysis

Which method studied in this chapter is the most accurate, but has the greatest computational complexity?

the relationships between costs and activity-based or volume-based cost drivers

Which relationships are often best fit by the linear cost estimation methods explained in this chapter?

because of certain time-series patterns to the data such as trend and/or seasonality, an outlier in data, or data shift

Why does nonlinearity most often happen?

estimates for the coefficients for the independent variables are unreliable

Why is multicollinearity a problem for a regression analysis?

the relevant range marks the range of the cost driver within which a cost estimate can be obtained

Why is the relevant range important in high-low cost estimation?