JOURNAL OF LIAONING TECHNICAL UNIVERSITY
(NATURAL SCIENCE EDITION)
LIAONING GONGCHENG JISHU DAXUE XUEBAO (ZIRAN KEXUE BAN)
辽宁工程技术大学学报（自然科学版）
COMPARISON OF RANDOM, SYSTEMATIC, SIEVE, CELL, AND LAHIRI SAMPLING METHODS IN MONETARY UNIT SAMPLING: A CASE STUDY OF LOCAL TAX RECEIVABLES
Aan Subarkah, Georgina Maria Tinungki, Nurtiti Sunusi
Abstract
This study evaluates the performance of five sampling selection methods in Monetary Unit Sampling (MUS) applied to local tax receivables data from Maros Regency Government in 2023. The research compares Random, Systematic, Cell, Lahiri, and Sieve sampling methods based on their beta risk and upper bound estimation accuracy. Using simulation with 110,616 iterations across 222 scenarios, the study examines seven types of local taxes with a total population value of IDR 43,984,236,590. Results indicate that all methods achieved 0% beta risk, successfully detecting 100% of material misstatements (5% overstatement). However, Sieve Sampling demonstrated superior efficiency with an Efficiency Index 4.59 times higher than other methods, utilizing 65% smaller sample sizes while maintaining detection effectiveness. The findings provide empirical evidence for audit practitioners in selecting optimal sampling methods for public sector financial audits in Indonesia.
Index Terms- Beta Risk, Local tax receivables, Monetary unit sampling, Public sector audit, Sampling methods.