Analytics has three types of sampling:

  • record sampling (attributes sampling)
  • monetary unit sampling
  • classical variables sampling

The type of sampling you choose depends on the nature of the analysis you are doing, and the nature of the data.

For guidance on which type of sampling to use, see Sampling data.

The sampling commands are designed to be used in a specific sequence.

Sequence for classical variables sampling

  1. CVSPREPARE – stratifies a population, and calculates the appropriate sample size for each stratum
  2. CVSSAMPLE – draws the sample of records
  3. CVSEVALUATE – projects errors found in the sample to the entire population of records

Sequence for record sampling, or monetary unit sampling

  1. SIZE – calculates the appropriate sample size
  2. SAMPLE – draws the sample of records
  3. EVALUATE – projects errors found in the sample to the entire population of records
Command Description

CVSPREPARE

Stratifies a population, and calculates a statistically valid sample size for each stratum, for classical variables sampling.

CVSSAMPLE

Draws a sample of records using the classical variables sampling method.

CVSEVALUATE

For classical variables sampling, provides four different methods for projecting the results of sample analysis to the entire population.

SIZE

Calculates a statistically valid sample size, and sample interval, for record sampling or monetary unit sampling.

SAMPLE

Draws a sample of records using either the record sampling or monetary unit sampling method.

EVALUATE

For record sampling or monetary unit sampling, projects errors found in sampled data to the entire population, and calculates upper limits on deviation rate, or misstatement amount.