Management Accounting (Study Text) 276 | P a g e

Chapter Learning Objectives

Upon completion of this chapter you will be able to:

 Forecasting using historical data

 Linear regression analysis
 Scatter diagrams and correlation
 Sale forecasting
 Regression and forecasting
 The components of time series
 Finding the trend
 Finding the seasonal variations
 Time series analysis and forecasting

Management Accounting (Study Text) 277 | P a g e

1 Session content diagram

Forecasts in budgeting (using historical data)

Budgets are based on forecasts. Forecasts might be prepared for:

 the volume of output and sales

 sales revenue (sales volume and sales prices)
 costs.

The purpose of forecasting in the budgeting process is to establish realistic

assumptions for planning. Forecasts might also be prepared on a regular basis
for the purpose of feed-forward control reporting.

A forecast might be based on simple assumptions, such as a prediction of a 5%

growth in sales volume or sales revenue. Similarly, budgeted expenditure might
be forecast using a simple incremental budgeting approach, and adding a
percentage amount for inflation on top of the previous year’s budget.

On the other hand, forecasts might be prepared using a number of forecasting

models, methods or techniques. The reason for using these models and
techniques is that they might provide more reliable forecasts.

This chapter describes:

 the high low method

 the uses of linear regression analysis
 Techniques of time series analysis.

More complex models might be used in practice, but these are outside the scope
of the syllabus.

Management Accounting (Study Text) 278 | P a g e

2 The high low method

This is a method of breaking semi variable costs into their two components. A
semi variable cost being a cost which is partly fixed and partly variable.

In the exam in computational questions, semi variable costs must be broken

down into their 2 components using the high low method.

The following example will be used to illustrate the method:

Step 1 Find the variable cost per unit

Increase in cost
Variable cost per unit
Increase in activity

Step 2 Find the fixed cost

A semi variable cost consists of 2 components. We have found the variable part.
The bit that is left must be fixed.

Management Accounting (Study Text) 279 | P a g e

Step 3 Calculate the expected cost

Example 1

Great Limited has had the following output and cost results for the last 4 years:

Output units Cost

Rs
Year 1 5,000 26,000
Year 2 7,000 34,000
Year 3 9,000 42,000
Year 4 10,000 46,000

In year 5 the output is expected to be 13,000 units. Calculate the expected

costs?

Inflation may be ignored.

3 Regression analysis

Regression analysis is concerned with establishing the relationship between a

number of variables. We are only concerned here with linear relationships
between 2 variables.

There are a variety of methods available for identifying the relationship:

(1) Least Squares Regression Analysis

(2) The high low method.
(3) Draw a scatter diagram and a line of best fit

The scatter diagram

The data is plotted on a graph. The y-axis represents the dependent variable, i.e.
that variable that depends on the other. The x-axis shows the independent
variable, i.e. that variable which is not affected by the other variable:

From the scatter diagram, the line of best fit can be estimated. The aim is to use
our judgement to draw a line through the middle of data with the same slope as
the data.

Least squares regression analysis

Regression analysis finds the line of best fit computationally rather than by
estimating the line on a scatter diagram. It seeks to minimise the distance
between each point and the regression line.

Management Accounting (Study Text) 280 | P a g e

 Example 2

Marco Polo Ltd is a small supermarket chain, that has 6 shops. Each shop
advertises in their local newspapers and the marketing director is interested in
the relationship between the amount that they spend on advertising and the sales
revenue that they achieve. She has collated the following information for the 6
shops for the previous year:

Shop Advertising expenditure Sales revenue

Rs 000 Rs 000
1 80 730
2 60 610
3 120 880
4 90 750
5 70 650
6 30 430

She has further performed some calculations for a linear regression calculation
as follows:

 the sum of the advertising expenditure (x) column is 450

 the sum of the sales revenue (y) column is 4,050
 when the two columns are multiplied together and summed (xy) the total is
326,500

 when the advertising expenditure is squared (x2) and summed, the total is
38,300, and
 when the sales revenue is squared (y2) and summed, the total is
2,849,300

Calculate the line of best fit using regression analysis.

Management Accounting (Study Text) 281 | P a g e

 Detailed proof of totals in example 2

Advertising Sales
Expenditure Rs 000
Rs 000
x y xy x2 y2
80 730 58,400 6,400 532,900
60 610 36,600 3,600 372,100
120 880 105,600 14,400 774,400
90 750 67,500 8,100 562,500
70 650 45,500 4,900 422,500
30 430 12,900 900 184,900
450 4,050 326,500 38,300 2,849,300

Interpretation of the line

Mathematical interpretation (No good! No marks!)

If x = 0, then y = 300 and then each time x increases by 1 y increases by 5

Business interpretation

If no money is spent on advertising then sales would still be Rs 300,000. Then for every
additional Re 1 increase in advertising sales revenue would increase by Rs 5.

Linear regression in budgeting

Linear regression analysis can be used to make forecasts or estimates whenever

a linear relationship is assumed between two variables, and historical data is
available for analysis.

Two such relationships are:

 A time series and trend line. Linear regression analysis is an alternative

to calculating moving averages to establish a trend line from a time series.
(Time series is explained later in this chapter)
 The independent variable (x) in a time series is time.
 The dependent variable (y) is sales, production volume or cost etc.
 Total costs, where costs consist of a combination of fixed costs and
variable costs (for example, total overheads, or a semi variable cost
item). Linear regression analysis is an alternative to using the high low
method of cost behaviour analysis. It should be more accurate than the
high low method, because it is based on more items of historical data, not
just a ‘high’ and a ‘low’ value.
 The independent variable (x) in total cost analysis is the volume of
activity.
Management Accounting (Study Text) 282 | P a g e
  The dependent variable (y) is total cost.
 The value of a is the amount of fixed costs.
 The value of b is the variable cost per unit of activity.

When a linear relationship is identified and quantified using linear regression

analysis, values for a and b are obtained, and these can be used to make a
forecast for the budget.
For example:
 a sales budget or forecast can be prepared, or
 total costs (or total overhead costs) can be estimated, for the budgeted
level of activity.

Regression and Forecasting

The regression equation can be used for predicting values of y from a given x
value.

(1) If the value of x is within the range of our original data, the prediction is
known as Interpolation.
(2) If the value of x is outside the range of our original data, the prediction is
known as Extrapolation.

In general, interpolation is much safer than extrapolation.

Example 2 – CONTINUED

Marco Polo Ltd has just taken on 2 new stores in the same area and the
predicted advertising expenditure is expected to be Rs 150,000 for one store and
Rs 50,000 for the other.

(a) Calculate the predicted sales revenues?

(b) Explain the reliability of the forecasts.

Limitations of simple linear regression

1) Assumes a linear relationship between the variables.

2) Only measures the relationship between two variables. In reality the
dependent variable is affected by many independent variables.
3) Only interpolated forecasts tend to be reliable. The equation should not be
used for extrapolation.
4) Regression assumes that the historical behaviour of the data continues
into the foreseeable future.
5) Interpolated predictions are only reliable if there is a significant correlation
between the data.

Management Accounting (Study Text) 283 | P a g e

4 Correlation

Regression analysis attempts to find the relationship between a number of

variables. Correlation is concerned with establishing how strong the relationship
is.

Clearly in the first diagram, the regression line would be a much more useful
predictor than the regression line in the second diagram.

Degrees of correlation

Two variables might be:

(a) perfectly correlated

(b) partly correlated
(c) uncorrelated

Perfect correlation

Management Accounting (Study Text) 284 | P a g e

 All the pairs of values lie on a straight line. There is an exact linear relationship
between the two variables.

Partial correlation

In the first diagram there is not an exact relationship, but low values of x tend to
be associated with low values of y, and high values of x tend to be associated
with high values of y.

In the second diagram again there is not an exact relationship, but low values of
x tend to be associated with high values of y and vice versa.

No correlation

The values of the two variables seem to be completely unconnected.

Positive and negative correlation

Correlation can be positive or negative.

Positive correlation means that high values of one variable are associated with
high values of the other and that low values of one are associated with low
values of the other.

Negative correlation means that low values of one variable are associated with
high values of the other and vice versa.

Management Accounting (Study Text) 285 | P a g e

 The correlation coefficient

The degree of correlation can be measured by the Pearsonian correlation

coefficient, r (also known as the product moment correlation coefficient).

r must always be between -1 and +1.

If r = 1, there is perfect positive correlation

If r = 0, there is no correlation
If r = -1, there is perfect negative correlation

For other values of r, the meaning is not so clear. It is generally taken that if r >
0.8, then there is strong positive correlation and if r < -0.8, there is strong
negative correlation, however more meaningful information can be gathered from
calculating the coefficient of determination, r2.

Example 2 – AGAIN

Required:

Calculate the coefficient of correlation for the previous scenario.

The coefficient of determination, r2

The coefficient of determination, r2 measures the proportion of changes in y that

can be explained by changes in x. Calculate the coefficient of determination for
Example 2 and comment. We can say that it determines the percentage change
in dependent variable due to the change in independent variable.

5 Adjusting forecasts for inflation

The accuracy of forecasting is affected by the need to adjust historical data and
future forecasts to allow for price or cost inflation.

 When historical data is used to calculate a trend line or line of best fit, it
should ideally be adjusted to the same index level for prices or costs. If the
actual cost or revenue data is used, without adjustments for inflation, the
resulting line of best fit will include the inflationary differences.
 When a forecast is made from a line of best fit, an adjustment to the
forecast should be made for anticipated inflation in the forecast period.

Management Accounting (Study Text) 286 | P a g e

 Example 3

Production overhead costs at company BW are assumed to vary with the number
of machine hours worked. A line of best fit will be calculated from the following
historical data, with costs adjusted to allow for cost inflation over time.

Total production Number of

Cost
Year Overheads machine hours index

Rs
20X1 143,040 3,000 192
20X2 156,000 3,200 200
20X3 152,320 2,700 224
20X4 172,000 3,000 235

Required:

(a) Reconcile the cost data to a common price level, to remove differences
caused by inflation.
(b) If the line of best fit, based on current (20X4) prices, is calculated as:

y = 33,000 + 47x

where y = total overhead costs in Rs and x = machine hours:

Calculate the expected total overhead costs in 20X5 if expected production

activity is 3,100 machine hours and the expected cost index is 250.

6 Time series analysis

A time series is a series of figures recorded over time, e.g. unemployment over
the last 5 years, output over the last 12 months, etc.

A graph of a time series is called a histogram.

Examples of a time series

Examples of time series might include the following:

 quarterly sales revenue totals over a number of years
 annual overhead costs over a number of years
 daily production output over a month.

Where the item being measured is subject to ‘seasonal’ variations, time series
measurements are usually taken for each season. For example, if sales volume
varies in each quarter of the year, a time series should be for quarterly sales.

Management Accounting (Study Text) 287 | P a g e

 Similarly, if the sales in a retail store vary according to the day of the week, a
time series might measure daily sales

Four Components of time series:

1) The trend
2) Seasonal variations
3) Cyclical variations
4) Residual variations

We are only interested in the first two – the trend and the seasonal variation.

Time series analysis is a term used to describe techniques for analysing a time
series, in order to:

 identify whether there is any underlying historical trend and if there is,
measure it
 use this analysis of the historical trend to forecast the trend into the future
 identify whether there are any seasonal variations around the trend, and if
there is measure them
 apply estimated seasonal variations to a trend line forecast in order to
prepare a forecast season by season.

In other words, a trend over time, established from historical data, and adjusted
for seasonal variations, can then be used to make predictions for the future.

The trend

Most series follow some sort of long term movement - upwards, downwards or
sideways. In time series analysis the trend is measured.

Seasonal variations

Seasonal variations are short-term fluctuations in value due to different

circumstances which occur at different times of the year, on different days of the
week, different times of day, etc e.g.:

 Ice cream sales are highest in summer

 Sales of groceries are highest on Saturdays
 Traffic is greatest in the morning and evening rush hours.

Illustration 1

A business might have a flat trend in sales, of Rs 1 million each six months, but
with sales Rs 150,000 below trend in the first six months of the year and Rs
150,000 above trend in the second six months. In this example, the sales would
be Rs 850,000 in the first six months of the year and Rs 1,150,000 in the second
six months.

Management Accounting (Study Text) 288 | P a g e

  If there is a straight-line trend in the time series, seasonal variations must
cancel each other out. The total of the seasonal variations over each cycle
should be zero.
 Seasonal variations can be measured:
 in units or in money values, or
 as a percentage value or index value in relation to the underlying
trend.

Cyclical and residual factors

Cyclical variations

Cyclical variations are medium term to long term influences usually associated
with the economy. These cycles are rarely of consistent length. A further problem
is that we would need 6 or 7 full cycles of data to be sure that the cycle was
there. Cyclical variations are often associated with the economy.

Residual or random factors

The residual is the difference between the actual value and the figure predicted
using the trend, the cyclical variation and the seasonal variation, i.e. it is caused
by irregular items, which could not be predicted.

Calculation of the trend

There are three main methods of finding the underlying trend of the data:

(1) Inspection. The trend line can be drawn by eye with the aim of plotting the line
so that it lies in the middle of the data.
(2) Least squares regression analysis. The x axis represents time and the
periods of time are numbers, e.g. January is 1, February is 2, March is 3, etc.
(3) Moving averages. This method attempts to remove seasonal or cyclical
variations by a process of averaging.

Calculating a moving average

A moving average is in fact a series of averages, calculated from time series

historical data.
 The first moving average value in the series is the average of the values
for time period 1 to time period n. (So, if n = 4, the first moving average in
the series would be the average of the historical values for time period 1
to time period 4.)
 The second moving average value in the series is the average of the
values for time period 2 to time period (n + 1). (So, if n = 4, the second
moving average in the series would be the average of the historical values
for time period 2 to time period 5.)

Management Accounting (Study Text) 289 | P a g e

  The third moving average value in the series is the average of the values
for time period 3 to time period (n + 2). (So, if n = 4, the third moving
average in the series would be the average of the historical values for time
period 3 to time period 6.)

The moving average value is associated with the mid-point of the time periods
used to calculate the average.

The moving average time period

When moving averages are used to estimate a trend line, an important issue is
the choice of the number of time periods to use to calculate the moving average.
How many time periods should a moving average be based on?

There is no definite or correct answer to this question. However, where there is a

regular cycle of time periods, it would make sense to calculate the moving
averages over a full cycle.
 When you are calculating a moving average of daily figures, it is probably
appropriate to calculate a seven-day moving average.
 When you are calculating a moving average of quarterly figures, it is
probably appropriate to calculate a four-quarter moving average.
 When you are calculating a moving average of monthly figures, it might be
appropriate to calculate a 12-month moving average, although a
shorter-period moving average might be preferred.

The seasonal variation

Once the trend has been found, the seasonal variation can be determined. A
seasonal variation means that some periods are better than average (the trend)
and some worse. Then the model can be used to predict future values. There are
two main models:

(1) The additive model. Here the seasonal variation is expressed as an absolute
amount to be added on to the trend to find the actual result, e.g. ice cream sales
in summer are good and in general we would expect sales to be Rs 200, 000
above the trend.

Actual/Prediction = T + S + C + R

In exam questions we would not be required to calculate the cyclical variation,

and the random variations are by nature random and cannot be predicted and
also ignored. The equation simplifies to:

Prediction = T + S

(2) The multiplicative model. Here the seasonal variation is expressed as a ratio
/ proportion / percentage to be multiplied by the trend to arrive at the actual
figure, e.g. ice cream sales in summer are good and in general we would expect
sales to be 50% more than the trend

Management Accounting (Study Text) 290 | P a g e

 Actual/Prediction = T x S x C x R

Again this simplifies to:

Prediction = T x S

Measuring seasonal variations

The technique for measuring seasonal variations differs between an additive

model and a multiplicative model. The additive model method is described here.

 Seasonal variations can be estimated by comparing an actual time series

with the trend line values calculated from the time series.
 For each ‘season’ (quarter, month, day etcetera), the seasonal variation is
the difference between the trend line value and the actual historical value
for the same period.
 A seasonal variation can be calculated for each period in the trend line.
When the actual value is higher than the trend line value, the seasonal
variation is positive. When the actual value is lower than the trend line
value, the seasonal variation is negative.
 An average variation for each season is calculated.
 The sum of the seasonal variations has to be zero in the additive model. If
they do not add up to zero, the seasonal variations should be adjusted so
that they do add up to zero.

 The seasonal variations calculated in this way can be used in forecasting,

by adding the seasonal variation to the trend line forecast if the seasonal
variation is positive, or subtracting it from the trend line if it is negative.

When a multiplicative model is used to estimate seasonal variations, the

seasonal variation for each period is calculated by expressing the actual sales for
the period as a percentage value of the moving average figure for the same
period.

Illustration of the calculation (Sales forecasting)

A small business operating holiday homes in Murree wishes to forecast next

year’s sales for the budget, using moving averages to establish a straight-line
trend and seasonal variations. Next year is 20X7. The accountant has assumed
that sales are seasonal, with a summer season and a winter season each year.

Management Accounting (Study Text) 291 | P a g e

 Seasonal sales for the past seven years have been as follows:

Sales
Summer Winter
Rs 000 Rs 000
20X4 124 70
20X5 230 180
20X6 310 270
20X7 440 360
20X8 520 470
20X9 650

Required:

a) Calculate a trend line based on a two seasons moving average.

b) Calculate the average increase in sales each season.
c) Calculate seasonal variations in sales.
d) Use this data to prepare a sales forecast for each season in 20Y0

Management Accounting (Study Text) 292 | P a g e

Solution (a)
Season Actual Two-season Seasonal Centre the Seasonal
and sales moving moving Moving variation
year total average average

(A) (B) = (A) – (B)

Rs 000 Rs 000 Rs 000 Rs 000 Rs 000
Summer 124
20X4
194 97
Winter 70 123.5 – 53.5
20X4
300 150
Summer 230 177.5 + 52.5
20X5
410 205
Winter 180 225.0 – 45.0
20X5
490 245
Summer 310 267.5 + 42.5
20X6
580 290
Winter 270 322.5 – 52.5
20X6
710 355
Summer 440 377.5
20X7
800 400
Winter 360 420.0 – 60.0
20X7
880 440
Summer 520 467.5 + 52.5
20X8
990 495
Winter 470 527.5 – 57.5
20X8
1,120 560
Summer 650
20X9

The trend line is shown by the moving averages.

(b) The average increase in sales each season in the trend line is:

(Rs 527,500 – Rs 123,500) / 8 seasons = Rs 50,500 each season

(c) Seasonal variations need to add up to zero in the additive model.

Management Accounting (Study Text) 293 | P a g e

 The seasonal variations calculated so far are:
Year Summer Winter
Rs 000 Rs 000
20X4 – 53.5
20X5 + 52.5 – 45.0
20X6 + 42.5 – 52.5
20X7 + 62.5 – 60.0
20X8 + 52.5 – 57.5

Total variations + 210.0 – 268.5

Summer Winter Total

Number of measurements 4 5
Average seasonal variation + 52.5 – 53.7 – 1.2
Reduce to 0 (share equally) + 0.6 + 0.6 + 1.2

Adjusted seasonal variation + 53.1 – 53.1 0.0

The seasonal variations could be rounded to + Rs 53,000 in summer and – Rs

53,000 in winter.

Example 4

W Ltd is preparing its budgets for next year.

The following regression equation has been found to be a reliable estimate of W

plc's deseasonalised sales in units:

y = 10x + 420

Where y is the total sales units and x refers to the accountancy period. Quarterly
seasonal variations have been found to be:

In accounting period 33 (which is quarter 4) identify the seasonally adjusted sales

units:

A 525
B 589
C 750
D 975

Management Accounting (Study Text) 294 | P a g e

 Advantages and disadvantages

The advantages of forecasting using time series analysis are that:

 forecasts are based on clearly-understood assumptions

 trend lines can be reviewed after each successive time period, when the
most recent historical data is added to the analysis; consequently, the
reliability of the forecasts can be assessed
 forecasting accuracy can possibly be improved with experience.

The disadvantages of forecasting with time series analysis are that:

 there is an assumption that what has happened in the past is a reliable

guide to the future
 there is an assumption that a straight-line trend exists
 there is an assumption that seasonal variations are constant, either in
actual values using the additive model (such as dollars of sales) or as a
proportion of the trend line value using the multiplicative model.

None of these assumptions might be valid.

However, the reliability of a forecasting method can be established over time. If

forecasts turn out to be inaccurate, management might decide that they are not
worth producing, and that different methods of forecasting should be tried. On the
other hand, if forecasts prove to be reasonably accurate, management are likely
to continue with the same forecasting method.

Management Accounting (Study Text) 295 | P a g e

8 Chapter summary

Management Accounting (Study Text) 296 | P a g e

 Multiple choice question (MCQ)

1. Monthly sales of product R follow a linear trend of y = 9.72 +

5.816x, where y is the number of units sold and x is the number
of the month. Monthly deviatons from the trend follow an additive
model.

The forecast number of units of product R to be sold in month 23, which

has a seasonal factor of plus 6.5 is, to the nearest whole unit:

A 134
B 137
C 143
D 150

Management Accounting (Study Text) 297 | P a g e

9 Practice questions

Test your understanding 1

The following extract is taken from the production cost budget of S Limited:

Production (units) 2,000 3,000

Production cost (Rs) 11,100 12,900

Identify the budget cost allowance for an activity level of 4,000 units:

A Rs 7,200.
B Rs 14,700.
C Rs 17,200.
D Rs 22,200.

Test your understanding 2

The following data have been extracted from the budget working papers of BL
Limited

Production volume 1,000 2,000

Rs/unit Rs/unit
Direct materials 4.00 4.00
Direct labour 3.50 3.50
Production overhead – department 16.00 4.20
Production overhead – department 24.00 2.00

Identify the total fixed cost and variable cost per unit

Total fixed cost Variable cost per unit

A 3,600 7.50
B 3,600 9.90
C 7,600 7.50
D 7,600 9.90

Test your understanding 3

A domestic electrical appliance was introduced on to the market in 2003. At the

point of sale customers are offered the chance to purchase an insurance policy
to cover repairs and parts for the first five years of operation these policies
cannot be purchased later on, only when the appliance is first bought. The table
below shows the total industry sales of this appliance for the years 2003 to 2009
together with the number of insurance policies sold and a general price index for
electrical goods

Management Accounting (Study Text) 298 | P a g e

 Year Sales of Appliance Policy sales Price index for
(Rs 000) (number) Electrical Goods (2001 = 100)
2003 3,600 400 120
2004 6,250 300 125
2005 9,170 600 131
2006 14,000 1,200 140
2007 21,600 1,700 144
2008 27,000 2,200 150
2009 41,600 2,000 160

Required:

(a) Explain why it is important to adjust the original appliance sales figures for
inflation when identifying the relationship between the sales of the appliance and
the number of insurance policies sold. Deflate the appliance sales figures to 2001
prices.

(5 marks)

(b) Calculate the coefficient of determination between the deflated appliance

sales figures and the insurance policy sales, and interpret your value.

(6 marks)

(c) Calculate the least squares regression equation to predict insurance policy
sales from deflated appliance sales.

(3 marks)

(d) The total sales of the electrical appliance in 2010 are estimated at Rs 51
million at 2010 prices and the price index for electrical goods in the year 2010
based on 2001 is predicted to be 170.

Use the least squares regression equation to obtain a forecast of insurance

policy sales for 2010.

(3 marks)

(e) Explain the pitfalls of using this type of approach for predicting insurance
policy sales in 2010.

(3 marks)

(Total: 20 marks)

Management Accounting (Study Text) 299 | P a g e

 Test your understanding 4

A company will forecast its quarterly sales units for a newproduct by using
a formula to predict the base sales units andthen adjusting the figure by a
seasonal index.

The formula is BU = 4,000 + 80Q

Where BU = Base sales units and Q is the quarterly period number.

The seasonal index values are:

Quarter 1 105%
Quarter 2 80%
Quarter 3 95%
Quarter 4 120%

Identify the forecast increase in sales units from Quarter 3 to Quarter 4:

A 25%
B 80 units
C 100 units
D 1,156 units

(2 marks)

Management Accounting (Study Text) 300 | P a g e

 Answer to MCQ :

1. D

Management Accounting (Study Text) 301 | P a g e

 Test your understanding answers

Example 1

Step 1 Calculate the variable cost per unit

Increase in cost
Variable cost per unit = –––––––––––––––––––
Increase in level of activity

Rs 46,000 – Rs 26,000
= –––––––––––––––––––
10,000 units – 5,000 units

= Rs 4 per unit

Step 2 Find the fixed cost

A semi-variable cost has only got 2 components – a fixed bit and a variable bit.
We now know the variable part. The bit that’s left must be the fixed cost. It can be
determined either at the high level or the low level.

High Low
Level Level

Rs Rs
Semi-variable cost 46,000 26,000
Variable part
Rs4/unit x 10,000 units 40,000
Rs4/unit x 5,000 units 20,000
––––– –––––
Fixed cost 6,000 6,000
––––– –––––

Step 3 Calculate the expected cost

Therefore cost for 13,000 units = 13,000 units x Rs 4 per unit + Rs 6,000 = Rs
58,000

Management Accounting (Study Text) 302 | P a g e

 Example 2

Example 2 – CONTINUED

(a)

Rs 000
Sales = 300 + 5 x 150 = 1,050
Sales = 300 + 5 x 50 = 550

(b) The second prediction is the more reliable as it involves interpolation. The
first prediction goes beyond the original data upon which the regression line was
based and thus assumes that the relationship will continue on in the same way,
which may not be true.

Example 2 – AGAIN

Management Accounting (Study Text) 303 | P a g e

 The coefficient of determination

r2 = 0.9922 = 0.984

This means that 98.4% of the changes in sales can be explained by changes in
advertising. The other 1.6% of changes are caused by other factors.

Example 3

(a) As the line of best fit is based on 20X4 prices, use this as the common price
level. Costs should therefore be adjusted by a factor:

Index level to which costs will be adjusted

–––––––––––––––––––––––––––––––
Actual index level of costs

Actual Cost Adjustment Costs at 20X4

Year overheads index factor price level
Rs Rs
20X1 143,040 192 x 235/192 175,075
20X2 156,000 200 x 235/200 183,300
20X3 152,320 224 x 235/224 159,800
20X4 172,000 235 x 235/235 172,000

(b) If the forecast number of machine hours is 3,100 and the cost index is 250:

Forecast overhead costs = [Rs 33,000 + (Rs 47 × 3,100 hours)] × (250/235)

= Rs 178,700 × (250/235)

= Rs 190,106
Example 4

y = 10x + 420

We are told that x refers to the accountancy period, which is 33, therefore:

y = 420 + 33 x 10 = 750

Management Accounting (Study Text) 304 | P a g e

 This is the trend, however and we need to consider the seasonal variation too.
Accounting period 33 is quarter 4. Quarter 4 is a bad quarter and the seasonal
variation is -30%, therefore the expected results for period 33 are 30% less than
the trend.

Expected sales = 750 x 70% = 525 units

Test your understanding 1

The high-low method

Step 1 Calculate the variable cost per unit

Increase in cost
Variable cost per unit = –––––––––––––––––––
Increase in level of activity

Rs 12,900 – Rs 11,100
= –––––––––––––––––––
3,000 units – 2,000 units

= Rs 1.80 per unit

Step 2 Find the fixed cost

A semi-variable cost has only got 2 components – a fixed bit and a variable bit.
We now know the variable part. The bit that’s left must be the fixed cost. It can be
determined either at the high level or the low level.

Management Accounting (Study Text) 305 | P a g e

 High level Low level

Rs Rs
Semi-variable cost 12,900 11,100
Variable part
Rs 1.80/unit x 3,000 units 5,400
Rs 1.80/unit x 2,000 units 3,600
––––– –––––
Fixed cost 7,500 7,500
––––– –––––

Therefore cost for 4,000 units = 4,000 units x Rs 1.80 per unit + Rs 7,500 = Rs
14,700.

Test your understanding 2

We know the cost per unit. We need to multiply by the number of units so that we
can find the total cost for 1,000 units and 2,000 units. Then we can apply the
high-low method.

Production volume 1,000 2,000

Rs/unit Rs/unit
Direct materials 4.00 4.00
Direct labour 3.50 3.50
Production overhead – department 16.00 4.20
Production overhead – department 24.00 2.00
–––––– ––––––
17.50 13.70
x No of units x 1,000 x 2,000
–––––– ––––––
Total cost 17,500 27,400
–––––– ––––––

Now we can do the high-low method.

The high-low method

Step 1 Calculate the variable cost per unit

Increase in cost
Variable cost per unit = –––––––––––––––––––
Increase in level of activity

Rs 27,400 – Rs 17,500
= –––––––––––––––––––
2,000 units – 1,000 units

Management Accounting (Study Text) 306 | P a g e

 = Rs 9.90 per unit
Step 2 Find the fixed cost

A semi-variable cost has only got 2 components – a fixed bit and a variable bit.
We now know the variable part. The bit that’s left must be the fixed cost. It can be
determined either at the high level or the low level.

High level Low

level
Rs Rs
Semi-variable cost 27,400
17,500
Variable part
Rs9.90/unit x 2,000 units 19,800
Rs9.90/unit x 1,000 units 9,900
–––––– –––––
–
Fixed cost 7,600 7,600
–––––– –––––
–

Test your understanding 3

(a) The factor affecting the number of policies sold is the number of appliances
sold. We do not know the number of appliances sold, however, just the value,
which is distorted by inflation. If we deflate the appliance sales we can remove
the distorting effect and see the underlying change in the level of activity.

2003 3,600 x 100/120 3,000

2004 6,250 x 100/125 5,000
2005 9,170 x 100/131 7,000
2006 14,000 x 100/140 10,000
2007 21,600 x 100/144 15,000
2008 27,000 x 100/150 18,000
2009 41,600 x 100/160 26,000

Management Accounting (Study Text) 307 | P a g e

 (b)

This means that 83.7% of the changes in policy sales can be explained by
changes in the level of the deflated appliance sales. The other 16.3% of changes
are caused by other factors.

Management Accounting (Study Text) 308 | P a g e

 d) Deflated appliance sales = 51m x 100/170 = Rs30m

Policy sales = 0.144 + 0.088 x 30

= 2.784 (000s)
= 2,784 policies

(e) (1) We are extrapolating. We have determined a regression equation

showing the relationship between deflated appliance sales and policy sales for
activity levels between Rs 3m and Rs 26m in terms of deflated sales. We are
making a prediction for activity levels outside this range and assuming that the
relationship would continue in the same way. This might not be so.

(2) Even if we had not been extrapolating we would be assuming that the historic
pattern that we had established in the past would continue into the future. Again
this might not be so.

Management Accounting (Study Text) 309 | P a g e

Test your understanding 4

Sales in quarter 3 (Q=3)

Base = 4000 + (80 ×3) = 4,240
Seasonal adjustment 95%
Actual sales = 4,028
Sales in quarter 4 (Q=4)
Base = 4000 + (80 ×4) = 4,320
Seasonal adjustment 120%
Actual sales = 5,184
Overall increase in sales = 5,184 – 4,028 = 1,156 units

Management Accounting (Study Text) 310 | P a g e

Management Accounting (Study Text) 311 | P a g e