Scribd Logo
Upload

Welcome to Scribd!

  • 107 views

    Cost Estimation and Behaviour

    Uploaded by

    Camila Miranda Kanda
    Cost estimation involves developing a functional relationship between a cost object and its cost drivers to understand cost behavior. There are three types of cost behavior: fixed, variable, and mixed. The high-low method uses two data points to estimate fixed and variable cost components, but has weaknesses. Regression analysis fits a line to minimize errors for all data points, providing a more accurate estimation. It also measures the precision and reliability of estimates using R-squared, t-values, and p-values.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Cost Estimation and Behaviour

    Uploaded by

    Camila Miranda Kanda
    107 views5 pages
    Cost estimation involves developing a functional relationship between a cost object and its cost drivers to understand cost behavior. There are three types of cost behavior: fixed, variable, and mixed. The high-low method uses two data points to estimate fixed and variable cost components, but has weaknesses. Regression analysis fits a line to minimize errors for all data points, providing a more accurate estimation. It also measures the precision and reliability of estimates using R-squared, t-values, and p-values.

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Cost estimation involves developing a functional relationship between a cost object and its cost drivers to understand cost behavior. There are three types of cost behavior: fixed, variable, and mixed. The high-low method uses two data points to estimate fixed and variable cost components, but has weaknesses. Regression analysis fits a line to minimize errors for all data points, providing a more accurate estimation. It also measures the precision and reliability of estimates using R-squared, t-values, and p-values.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    107 views5 pages

    Cost Estimation and Behaviour

    Uploaded by

    Camila Miranda Kanda
    Cost estimation involves developing a functional relationship between a cost object and its cost drivers to understand cost behavior. There are three types of cost behavior: fixed, variable, and mixed. The high-low method uses two data points to estimate fixed and variable cost components, but has weaknesses. Regression analysis fits a line to minimize errors for all data points, providing a more accurate estimation. It also measures the precision and reliability of estimates using R-squared, t-values, and p-values.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 5

    Cost Estimation and Behaviour

    Cost estimation is the process of developing a well-defined functional relationship between a cost
    object and its cost driver(s) in order to understand the cost behavior. The purposes of cost
    estimation are:
    (1) to identify the key cost drivers for each cost object to help managers control costs
    (2) to measure the variable and/or fixed components of the cost item so as to help managers
    make correct decisions, and
    (3) to predict its value in the future so as to help managers correctly plan for the future.

    Cost behaviour describes the way that the total amount spent of a specific cost item on a cost
    object reacts to changes in its cost driver(s) (e.g., production quantity or sales volume). There three
    possible cost behavior: (i) the total cost may stay the unchanged (i.e., fixed cost), (ii) the total cost
    may change proportionately in response to the change in the activity level (i.e.,variable cost), or
    (iii) it may partially change proportionally and partially remain constant (i.e., mixed cost). If costs
    are mixed, then we need to identify and separate the fixed component from the variable
    component. This, in turn, helps us to classify costs as either variable or fixed cost. This
    classification helps managers to make optimal decisions and perform their planning and control
    functions.

    How to Estimate Cost Functions:


    There are six steps in the cost estimation process:
    1. Define the Cost item to be estimated.
    2. Determine the Cost Drivers.
    3. Collect Consistent and Accurate Data.
    4. Plot (Graph) the Data.
    5. Select and Employ the Estimation Method.
    6. Assess the Accuracy of the Cost Estimation.

    Linear Methods of Cost Estimation

    Basic assumptions
    (1) Changes in total costs can be explained by changes in the level of a single cost driver.
    (2) Cost behavior can adequately be approximated by a linear function of the activity level within the
    relevant range

    Basic Linear Function:

    1
    Based on the above two assumptions, we can express the relationship between a particular cost
    item and its cost driver in a mathematical form using the straight line equation as follows:

    y = a + b(x)

    where: y= Total costs


    a= fixed cost component
    b= slope coefficient (variable cost rate)
    x= the volume (quantity) of the cost driver
    Note that:

    1. If the estimated value of a = 0 and b > 0 then we can conclude that the cost behavior
    isVariable.
    2. If the estimated value of b = 0 and a > 0 then we can conclude that the cost behavior is
    Fixed.
    3. If the estimated values of both a & b > 0 then we can conclude that the cost behavior is
    Mixed.

    High-Low (HL) Method


    1. Identify the highest value of volume (X) and its associated value of cost (Y)
    2. Identify the Lowest value of volume (X) and its associated value of cost (Y)
    3. Use the above two points to estimate the parameter b (variable cost per unit) in the following
    cost function:

    b = Change in cost (y) (Hy – Ly)


    Change in volume (x) (Hx – Lx)

    4. Estimate the Fixed component a as follows:

    Substitute the value of b into the basic equation along with actual values of Y and X at either the highest
    point or the lowest point into the following equation; then solve for the intercept a:

    y = a + b(x)

    Total Cost (lowest cost driver level) = a + b(x at lowest quantity of cost driver)

    Using the highest cost-quantity pair will give the same answer for the intercept.

    5. Use the estimated cost function to predict future costs.

    2
    Example 1:
     Bill Garcia, a management accountant, wants to estimate future maintenance costs for a large
    manufacturing company; recent monthly data are as follows:

    January February March April May June July


    Total operating hours 3,451 3,325 3,383 3,614 3,423 3,410 3,500
    Maintenance costs ($) 22,943 22,510 22,706 23,030 22,413 22,935 23,176

     Garcia would like to estimate an underlying cost function for maintenance costs.

    1. Plot the Data.


    MaintCost

    July

    April
    June January

    Mrch

    February
    May

     b = Unit variable cost = $520 ÷ 289 hours = $1.80/hour


     a = Fixed cost = Total cost – Estimated variable cost
    Fixed cost = $23,030 – ($1.80/hour × 3,614 hours)
    Fixed cost = $23,030 – $6,505 = $16,525
     Estimated cost function:
    Total cost = Fixed cost + Variable cost
    Y = a + (b × X)]
    Y = $16,525 + ($1.80 × X)
    For values of the cost driver (operating hours) within the “relevant range,” the preceding
    equation can be used to estimate monthly maintenance costs. For example, for the month of
    August: Suppose that 3,600 operating hours are expected in August:
    Y = 16,525 + (1.80 x X)
    Y = 16,525 + (1.80 x 3,600) = $23,005 in maintenance costs

    3
    Major Weakness of High-Low Method:

    1. H-L method uses only two data points and ignores the rest of the data.
    2. H-L method could provide biased estimates if the two data points are outliers.
    3. H-L method does not provide information to evaluate how good the estimated function in
    representing the cost behavior or how accurate it is in predicting future costs.
    4. It allows only one independent variable to explain the behavior of cost.

    Regression Analysis

    Regression analysis is a statistical method for obtaining the unique cost-estimating equation that
    best fits a set of data points. Regression analysis fits the data by minimizing the sum of the
    squares of estimation error. Each error is the distance measured from the regression line to one of
    the data points. Because it minimizes the estimation errors in this way, regression analysis is also
    called least squares regression.

    A regression analysis has two types of analysis: Simple regression and multiple regression.
    Simple regression uses only one independent variable, while multiple regression uses two or more
    cost drivers. Similar to the high-low method, the regression equation has both an intercept and a
    slope. In addition, the amount of the estimations error is explicitly considered in the model.

    Simple Regression Model:

    Example 2:
    To illustrate a simple, linear regression cost-estimation model, we will repeat
    example 1 using OLS techniques. Following is the computer output:

    Model Unstandardized Coefficients t Sig.

    B Std. Error

    (Constant) 15805 3460.251 4.568 .006


    1
    OpHours 2.036 1. 4 1.456 .209

    R-Squared = 0.445

    Y = $15,805 + ($2.036 per operating hour  3600 hours in August) = $23,134

    4
    Evaluating the Regression Output

    Measuring Precision and Reliability

    In addition to a cost estimate, regression analysis also provides quantitative measures of its
    reliability. Reliability indicates whether the regression reflects actual relationships among the
    variables. Three key measures of reliability are explained here: (i) R-squared (also called the
    coefficient of determination), (ii) the t-value, and (iii) P value.

    R-squared

    – A number between zero and one that describes the explanatory power of the regression (the
    degree to which the change in Y can be explained by changes in X)
    – A relative measure of “goodness-of-fit” (i.e., the percentage change in Y that can be explained
    by changes in X)

    T-value

    – A measure of the statistical reliability of each independent variable in the cost function: does
    the independent variable have a valid, stable, relationship with dependent variable?
    – Variables with a low t-value should be evaluated and possibly removed to improve cost
    estimation
    – In a multiple-regression model, low t-values signal the possibility of multicollinearity, meaning
    two or more independent variables may be highly correlated with each other; removal of one or
    more of these variables may be desirable

    You might also like