The formulas
- Interval = population size / sample size
- Selection points = random start, start + interval, start + 2 x interval, ...
- With monetary units, an item at least as large as the interval always contains a selection point
How it works
Systematic random selection is one of the random selection techniques AU-C 530 paragraph .A16 lists, next to simple random and probability-weighted selection. You divide the population by the sample size to get the interval, pick a random start inside the first interval, and take every interval from there.
With a dollar population the selection points are cumulative dollars, so large items are more likely to be picked and any item at least as large as the interval is certain to be picked. With an item count the points are record numbers. A pattern in the population that repeats at the same interval biases a systematic sample; check the ordering first.
Illustrative figures only. Check the result against your firm's methodology before relying on it.
Common questions
How do I pick the random start?
Draw a random number between 1 and the interval from a random number generator and record the seed in the workpaper.
Can one item get two selection points?
Yes, with monetary units, when the item is larger than the interval. It is tested once.
Should I use several random starts?
Several starts with a wider interval reduce the effect of a periodic pattern in the population. The total sample size stays the same.
Sources
Runs in your browser. The figures you type are not sent to CORAA or stored. Check the result against your firm's methodology before relying on it.