There are other methods that are more accurate than the high-low method in segregating mixed costs.

The scatter graph method segregates total costs graphically. By plotting all relevant data points in a graph, the fixed and variable cost components can be determined.

## Cost Function

Like all other methods of cost segregation, the scatter graph method follows the same cost function:

**y = a + bx**

where: y = total cost; a = total fixed costs; b = variable cost per level of activity (or units); x = level of activity (or number of units).

## Steps in Performing the Scatter Graph Method

- Plot the data points in a graph. The level of activity is placed on the x-axis (independent variable) and the total cost on the y-axis (dependent variable).
- Draw a straight line that estimates the
**line of best fit**. The line of best fit is a line that represents all the data points in a given set. This line shall be used in estimating the fixed costs and variable costs. - The total fixed cost is equal to the y-intercept (the value of y at x=0, or the point where the line crosses the y-axis).
- The variable cost per unit or slope (b) can be computed using any two coordinates in the line of best fit.

b = y2 - y1 x2 - x1

## Example

The following data was gathered for five production runs of ABC Company. Estimate the cost function using the scatter graph method.

Batch |
Units (x) |
Total Cost (y) |

1 |
680 |
$29,800 |

2 |
820 |
$34,000 |

3 |
570 |
$27,500 |

4 |
660 |
$29,000 |

5 |
750 |
$31,900 |

**Solution:**

Step 1: Plot the data points in a graph.

Step 2: Estimate the line of best fit.

Step 3: Determine the total fixed costs.

The total fixed cost is equal to the y-intercept. Based on the graph above, the line of best fit crosses the y-axis at approximately $12,000, hence total fixed costs is equal to $12,000.

**a = $12,000**

Step 4: Compute for the variable cost per unit.

The variable cost per unit or slope is computed using **any** two data points in the line of best fit. Let us use coordinates that we can easily determine: x=0, y=12,000 and x=900, y=36,000 (approximately).

b = | y2 - y1 | = | 36,000 - 12,000 | = | 24,000 |

x2 - x1 | 900 - 0 | 900 |

**b = $ 26.67 per unit**

Again, any two points found in the line of best fit can be used (e.g., at x=300, y=20,000; or at x=700, y=33,000.) It is advisable to use two data points whose values can be easily approximated or determined.

The cost function for this particular set using the scatter graph method is:

*y = $12,000 + $26.67x*.

## Conclusion

Compared to the high-low method which considers the highest level and lowest level of activity only, the scatter graph method is more reliable since it considers all data points. However, drawing the line of best fit involves objective estimation (if done manually). This issue is addressed by a more accurate method: computing for the fixed and variable costs *mathematically* through linear regression.