J. J. A. Moors

A General Model for Repeated Audit Controls Using Monotone Subsampling

Abstract In categorical repeated audit controls, fallible auditors classify sample elements in order to estimate the population fraction of elements in certain categories. To take possible misclassifications into account, subsequent checks are performed with a decreasing number of observations. In this paper a model is presented for a general repeated audit control system, where k subsequent auditors classify elements into r categories. Two different subsampling procedures will be discussed, named “stratified” and “random” sampling. Although these two sampling methods lead to different probability distributions, it is shown that the likelihood inferences are identical. The MLE are derived and the situations with undefined MLE are examined in detail; it is shown that an unbiased MLE can be obtained by stratified sampling. Three different methods for constructing confidence upper limits are discussed; the Bayesian upper limit seems to be the most satisfactory. Our theoretical results are applied to two cases with r = 2 and k = 2 or 3, respectively.

Two-Step Sequential Sampling

Deciding upon the optimal sample size in advance is a difficult problem in general. Often, the investigator regrets not having drawn a larger sample; in many cases additional observations are done. This implies that the actual sample size is no longer deterministic; hence, even if all sample elements are drawn at random, the final sample is not a simple random sample. Although this fact is widely recognized, its consequences are often grossly underrated in our view. Too often, these consequences are ignored: the usual statistical procedures are still applied. This paper shows in detail the dangers of applying standard techniques to extended samples. To allow theoretical derivations only some elementary situations are considered. More precisely, the following features hold throughout the paper: - the population variable of interest is normally distributed; - estimation concerns population mean and variance; - all sample elements are drawn at random, with replacement; - only standard estimators, like sample mean and sample variance, will be considered. Nevertheless, the results are rather disturbing: standard estimators have sizable biases, their variances are (much) larger than usual, and standard confidence intervals do not have the prescribed confidence level any more. Crucial is of course the criterion used to decide whether or not to extend the original sample. Four criteria are applied. In the first three cases, an independent event, the observed sample mean and the observed sample variance, respectively, determine whether or not to double the original sample size. The fourth criterion compares the variances observed in two independent samples; the sample with the highest variance is extended. Only in this fourth case the size of the extension is a random variable. Note that a given criterion is used only once: after the original observation s the final sample size is determined; hence the title of our paper.

A Mixed Model for Double Checking Fallible Auditors

The paper discusses the problem of a fallible auditor who assesses the values of sampled records, but may make mistakes.To detect these mistakes, a subsample of the checked elements is checked again, now by an infallible expert. We propose a model for this kind of double check, which takes into account that records are often correct; however, if they are incorrect, the errors can take on many different values - as is often the case in audit practice.The model therefore involves error probabilities as well as distributional parameters for error sizes.We derive maximum likelihood estimators for these model parameters and derive from them an estimator for the mean size of the errors in the population.A simulation study shows that the latter outperforms some other - previously introduced - estimators.

Asymptotics of Multivariate Regression with Consecutively Added Dependent Varibles

We consider multivariate regression where new dependent variables are consecutively added during the experiment (or in time).So, viewed at the end of the experiment, the number of observations decreases with each added variable. The explanatory variables are observed throughout.In a previous paper we determined the least squares and maximum likelihood estimators for the parameters in this model.In this paper we discuss the estimation technique of iterative least squares to calculate the maximum likelihood estimates and we prove the consistency of the estimators in each iteration.Moreover, we introduce a general class of estimators for the regression parameters based on arbitrary starting estimators for the covariance matrix.We prove the consistency of these new estimators and - for sake of completeness - of the previously obtained least squares and maximum likelihood estimators as well.