0% found this document useful (0 votes)
3 views6 pages

Regression Analysis for Cost Estimation

Uploaded by

Arnold Miano
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
3 views6 pages

Regression Analysis for Cost Estimation

Uploaded by

Arnold Miano
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd

COST ESTIMATION METHOD

Engineering method
These methods are based on the use of
engineering analysis of technological relationship
between inputs and outputs e.g. method studies
and time and motion studies.

The procedure in such a study is to make an


analysis based on direct observation of the
underlying physical quantities required for an
activity and then to convert the final result into
cost estimate.

This method is useful for estimating costs of


repetitive processes where input and output
relationship is clearly defined e.g. the cost
associated with direct materials, direct labour and
machine time.

Account analysis (Inspection of accounts)


method
This method requires that departmental managers
and the accountant inspect each item of
expenditure within the accounts for some output
level and then classify each of these items as
wholly fixed, wholly variable or mixed.

A single average unit cost figure is selected for the


items categorised as variable whereas a single
total cost for the period is used for the items
categorised as fixed.
Mixed costs are decomposed into their variable
and fixed components.
High low method (Two point method)
Under this method, records of costs in the
previous period are reviewed and the costs of 2
periods are selected. These are the period with the
highest level of outputs and the period with the
lowest output. A line passing through these two
points is then established and used in estimating
costs.

Illustration 2.1
The production manager of XYZ Company, is
concerned about the apparent fluctuation in
efficiency and wants to determine how labour
costs (in Sh.) are related to volume. The following
data presents results of the 12 most recent weeks.

Week No. Units Produced(X) Labour


Costs(Y)
1 34 340
2 44 346
3 24 287
4 36 262
5 30 220
6 49 416
7 39 337
8 21 180
9 41 376
10 47 295
11 34 215
12 24 275
Required:
Estimate the cost function using:
The high low method
Regression analysis

Assume that the Company intends to produce


45 units
34 units next period
Estimate the labour cost to be incurred.

Note:
The main problems of the high low method are:
Reliability is low
It Ignores all the other points except the highest
and lowest which in most cases are outliners.

2.3 REGRESSION ANALYSIS


A regression equation identifies an estimated
relationship between a dependent variable (the
cost) and one or more independent variables (the
cost driver). When the equation includes only one
independent variable then it is referred to as
simple regression and its form is:

Ỹ= a + bx

Where, Ỹ is the predicted value of Y


a and b are Constant
x is the cost driver
When the equation includes 2 or more
independent variables, it is referred to as multiple
regression and is of the form:

Y = a + b 1 x1 + b2 x2 + …….bn xn for n
independent variables.

Simple Regression
Regression analysis determines mathematically
the regression line of best fit. It is based on the
principle that the sums of squares of the vertical
deviation from the line established is the least
possible

I.e. ∑ (Y −Y^ )2 is minimised

where Y is the observed value of the dependent


variable
Ŷis the predicted value of Y

The equation can be solved by the use of normal


equations and these are:

1. y = na + b (x)

xy = a (x) + b (x2)

From these normal equations:


b = n xy – x y
nx 2– (x)2

a = Y - b x
n n

using above illustration show the regression line


of y on x

You might also like