EZ-R Stats, LLC

Compliance testing often relies on attribute sampling when a test is to be based upon a random sample. If the entire population is expected to be consistent, then a sample will be drawn from the entire population, i.e. an unrestricted sample. This is in contrast to situations where there is some variation expected to occur, in which case a stratified sample may be drawn.

If the supporting documents for data being audited are contained in a central location, e.g. no travel or other logistics are involved, then stop and go sampling may be a more efficient and effective method for random sampling for the following reasons:

1. There is no need to compute a required sample size,
2. There is no need to perform a preliminary analysis of the population attributes such as expected error rate, and
3. There is little or no risk in "over sampling", i.e. testing more samples than required and therefore spending excess audit time doing the testing.

Stop and Go sampling is a statistically valid process which involves the following steps:

1. Assign a random number to each item in the population (e.g. using "Mersenne Twister" or other statistically valid random number generator)
2. Sort the population by assigned random number, either ascending or descending
3. Select the first 10 - 20 items (auditor judgment as to number), test them and put the results into an Excel spreadsheet.
4. Run a "stop and go" sample report and review the results (see example below)
5. If the resulting sample precision is too large, then select another group of transactions by sorted assigned random number (auditor judgment as to number)
6. Test the samples and record the results in the same Excel spreadsheet.
7. Run another "stop and go" sample an review the results.
8. Repeat steps 5 through 7 until satisfactory results have been obtained.

The report from the Stop and Go Sample will show the intermediate results, sample statistics as well as calculate the estimate of the population at four confidence levels - 80%, 90%, 95% and 98%. The results will also be charted for easy review. The charts show the upper and lower bounds, as well as the point estimate for each calculation.

The procedure for determining the results from attribute sampling consists of these steps:

1. Specify the data source (Excel, Access, text file)
2. Specify the name of the workbook or file
3. Select the work sheet or table which contains the data
4. Specify the names of the columns containing the sample indicator and the sample results
5. Select the "Attribute Sample - Unrestricted" command from the drop down list
6. Click the "OK" button
7. Review the report under the "Report" tab

Output is in three formats:

1. Electronic work paper (see example)
2. Chart (below)
3. Text report

An example of the chart output is shown below (attribute test for signature on documents as tested in 25 samples):