In Proceedings of 10th CONTECSI International Conference on Information Systems and Technology Management, São Paulo, SP, Brasil.
ISSN/ISBN: Not available at this time. DOI: 10.5748/9788599693094-10CONTECSI/RF-92
Note - this is a foreign language paper: POR
Abstract: In this paper, the investigated question is structured as follows: Are there significant deviations in the distribution of the first digit of State expenditure in relation to the behavior predicted by Newcomb-Benford's Law? This question elucidates an application of statistical data analysis for the accounting audit which uses an interdisciplinary approach to assess 109,888 endeavors notes issued by 20 Management Units (UGs) in two northeastern states, with 10 UGs in each state. The objective of the research is to detect the approach of statistical analysis in the occurrence of significant deviations in the distribution of the first digit of State expenditure in relation to the standard distribution defined in the Newcomb-Benford Law (NB-Law). One accounting model based on hypothesis tests, Z-test, Chi-square, and Relative Discrepancy and Semi-Absolute Deviation was applied to the analysis of data, assessing the conformity between the observed and expected distribution in the NB-Law. As a result of the research, it was found the occurrence of excess in digit 7 and scarcity in digits 8 and 9 for the UGs. Such behavior denotes a tendency to escape bidding processes. It was concluded that NB-Law is a valid methodology to aid the audit public.
Bibtex:
@inproceedings{,
AUTHOR={José Isidio de Freitas Costa and Silvana Karina de Melo Travassos and and Tiago de Moura Soeiro and Josenildo dos Santos},
TITLE={Statistical analysis in detection of deviation occurrence in the distribution of first significant digit of state public spending in relation to the standard distribution defined in Newcomb-Benford’s law},
BOOKTITLE={Proceedings of 10th CONTECSI International Conference on Information Systems and Technology Management},
ADDRESS={São Paulo, SP, Brasil},
YEAR={2013},
URL={},
}
Reference Type: Conference Paper
Subject Area(s): Economics, Statistics