Audit Sampling
Definition: Audit Sampling Audit sampling is the application of an audit procedure to less than 100 percent of the items within an account balance or class of transactions for the purpose of evaluating some characteristic of the balance or class.
Audit Risk (Error) Sampling Risk (Error) Type 1 Error (alpha risk; risk of underreliance) Type 2 Error (beta risk; risk of overreliance) Nonsampling Risk (Error)
Audit Sampling: Basic Steps n 1. Define objectives n 2. Specify population n 3. Identify characteristic of interest n 4. Determine sample size n 5. Selection of sample n 6. Evaluation of sample results n 7. Make audit decision
Types of Audit Sampling Statistical sampling Nonstatistical (Judgmental) Sampling
Distinguishing Features of Statistical Sampling n n Random or Systematic selection n n Mathematical evaluation
Representative Selection Methods For Statistical or Nonstatistical Sampling: Random – – Regular – – Probability Proportional to Size Systematic – – Regular – – Probability Proportional to Size Stratified Random For Nonstatistical Only: Haphazard
Unacceptable Selection Methods n n Block selection n n Judgmental selection (OK when not sampling)
Types of Sampling Plans n n Attribute Sampling (eg. Evaluation of Internal Control System) n n Variable Sampling (eg. Estimate Account Balances)
Determination of Sample Size MDR = R n n = R TR
Determination of Sample Size Factors affecting sample size (Independent variables) Population Confidence Level Tolerable Rate Precision Range n = N SD Z PR ().. 2
Risk Factor Table
Determination of Sample Size: Reliability 90%
Determination of Sample Size: Reliability 95%
Sample Size Estimation: Tests of Balances (Variable Sampling) n = _____________ BV x R TM
Sample Evaluation: Tests of Balances (Variable Sampling) n n Quantitative n n Qualitative
Perpetual Records? yes no yes no Ratio Difference or Ratio Mean Value PPS? Sample Evaluation Method: Decision Tree
Sample Evaluation: Tests of Balances (Variable Sampling) Mean Value Estimation Method EV = M x N Difference Estimation Method EV = TBV +/- ED ED = m(d) x N Ratio Estimation Method EV = TBV x (SAV÷SBV)
Sample Evaluation: Tests of Balances (Variable Sampling) Achieved Precision Range APR = N x SE x Z If APR > Materiality Not enough statistical evidence to accept or reject population; Increase sample size or have client fix the population If APR < ½ Materiality Decision interval = EV +/- APR If ½ Materiality < APR < Materiality Calculate Adjusted Achieved Precision Range AAPR = Materiality - APR Decision Interval = EV +/- AAPR