Sampling Methodology for Overpayment Audit
You are conducting a billing compliance audit for a multi-specialty clinic with 50,000 claims per year. The compliance committee is concerned about potential overpayments for evaluation and management (E/M) services. They want to know the estimated overpayment amount with a 95% confidence level and a margin of error of ±5%. The total population of E/M claims is 20,000. You have a budget to review 200 claims. The clinic uses a mix of paper and electronic records, and some claims are missing documentation. The audit committee expects a report within 30 days.
1. What sampling approach would you recommend and why? Calculate the required sample size if using simple random sampling, and discuss whether the budgeted 200 claims is sufficient.
Read the worked answer
For a 95% confidence level and ±5% margin of error, the required sample size for a finite population is calculated as:
n = (Z^2 * p * (1-p)) / E^2, where Z=1.96, p=0.5 (maximum variability), E=0.05.
n0 = (1.96^2 * 0.5 * 0.5) / 0.05^2 = 384.16.
Adjust for finite population: n = n0 / (1 + (n0-1)/N) = 384.16 / (1 + 383.16/20000) ≈ 377.
Thus, a sample of 377 claims is needed. The budgeted 200 claims is insufficient for the desired precision. Options: (1) increase sample size to 377, (2) accept a larger margin of error (e.g., ±6.9% with n=200), or (3) use a stratified sampling approach focusing on high-risk claims to improve efficiency. Given the 30-day timeline and missing documentation, a stratified random sample by provider or claim amount might be more practical, but the auditor should communicate the precision limitations.
2. How would you handle missing documentation in the sample, and what effect does it have on the audit conclusion?
Read the worked answer
Missing documentation should be treated as a potential overpayment if the service cannot be supported. The auditor should:
- Attempt to locate documentation through other sources (e.g., EHR, paper records).
- If unavailable, classify as 'unsupported' and include in the overpayment estimate as a separate category.
- Consider the missing documentation rate as a finding itself (compliance risk).
- In the projection, use a conservative approach: assume missing documentation represents overpayment unless evidence suggests otherwise.
- Report the limitation and recommend improvements in documentation retention.