Optimal sampling op hierarchical screening with inspection errors

For the multi-stage hierarchical Dorfman group testing problem, where inspection errors exist, we provide a simple procedure to determine the number to stages, the number of subgroups of each stage and sample size of each subgroup simultaneously. The optimal group testing plan established by this procedure minimizes the expected number of tests per item. This result can be easily extended to more general applications.     

The computational aspects of multiple attribute sampling procedures

One method of controlling the quality of incoming lots is through attribute sampling. To simultaneously control several (possibly dependent) attributes, properly chosen single attribute sampling plans can be merged into a multiple attribute sampling plan. The general form of such a plan is given and various alternatives are discussed. The multinomial distribution is used to develop formulae necessary for an analysis of a multiple attribute plan. Due to the lengthy nature of the calculations involved, a computer algorithm is outlined.     

Inspection errors in link sampling

Results of an investigation into the sensitivity to two types of inspection error of link sampling procedures described by Harischchandra and Srivenkataramana are reported. Relevant compound distributions are derived. Some comparisons with results obtained in a similar investigation for standard double sampling are also given.     

Statistical quality control at statistics canada

Over the past several years statistical quality control methodologies at Statistics Canada have evolved frotn forrnal Product Control (k Acceptance Sampling By Attributes) to a more complete use of all quality control information obtained to achieve what is now called Acceptance Control. The use of this additional information allows us to continually adapt our quality control methods to the existing conditions of survey operations. In this context this paper reviews the general approach to statistical quality control and its relation to survey processing operations in Statistics Canada.     

Sampling hyperparameters in hierarchical models: Improving on Gibbs for high-dimensional latent fields and large datasets

ABSTRACT

A common Bayesian hierarchical model is where high-dimensional observed data depend on high-dimensional latent variables that, in turn, depend on relatively few hyperparameters. When the full conditional distribution over latent variables has a known form, general MCMC sampling need only be performed on the low-dimensional marginal posterior distribution over hyperparameters. This improves on popular Gibbs sampling that computes over the full space. Sampling the marginal posterior over hyperparameters exhibits good scaling of compute cost with data size, particularly when that distribution depends on a low-dimensional sufficient statistic.     

Bayesian hierarchical model for protein identifications

In proteomics, identification of proteins from complex mixtures of proteins extracted from biological samples is an important problem. Among the experimental technologies, mass spectrometry (MS) is the most popular one. Protein identification from MS data typically relies on a ‘two-step’ procedure of identifying the peptide first followed by the separate protein identification procedure next. In this setup, the interdependence of peptides and proteins is neglected resulting in relatively inaccurate protein identification. In this article, we propose a Markov chain Monte Carlo based Bayesian hierarchical model, a first of its kind in protein identification, which integrates the two steps and performs joint analysis of proteins and peptides using posterior probabilities. We remove the assumption of independence of proteins by using clustering group priors to the proteins based on the assumption that proteins sharing the same biological pathway are likely to be present or absent together and are correlated. The complete conditionals of the proposed joint model being tractable, we propose and implement a Gibbs sampling scheme for full posterior inference that provides the estimation and statistical uncertainties of all relevant parameters. The model has better operational characteristics compared to two existing ‘one-step’ procedures on a range of simulation settings as well as on two well-studied datasets.     

A new policy for designing acceptance sampling plan based on Bayesian inference in the presence of inspection errors

The purpose of this article is to present a new policy for designing an acceptance sampling plan based on the minimum proportion of the lot that should be inspected in the presence of inspection errors. It is assumed that inspection is not perfect and every defective item cannot be detected with complete certainty. The Bayesian method is used for obtaining the probability distribution function of the number of defective items in the lot. To design this model, two constraints of producer risk and consumer risk are considered during the inspection process by using two specified points on operating characteristic curve. In order to illustrate the application of the proposed model, an example is presented. In addition, a sensitivity analysis is performed to analyze the model performance under different scenarios of process parameters and the results are elaborated. Finally, the efficiency of the proposed model is compared with the sampling method of Spencer and Kevan de Lopez (2017) at the same conditions.     

A Bayesian hierarchical approach to dual response surface modelling

In modern quality engineering, dual response surface methodology is a powerful tool to model an industrial process by using both the mean and the standard deviation of the measurements as the responses. The least squares method in regression is often used to estimate the coefficients in the mean and standard deviation models, and various decision criteria are proposed by researchers to find the optimal conditions. Based on the inherent hierarchical structure of the dual response problems, we propose a Bayesian hierarchical approach to model dual response surfaces. Such an approach is compared with two frequentist least squares methods by using two real data sets and simulated data.     

Multiple Sampling Inspection Plans for Attributes

A set of tables is presented enabling one to design multiple (Group sequential) sampling plans when various entry parameters are given. Table yielding item by item sequential sampling plans indexed by (AQL, AOQL) is also presented.     

Modified dorfman-sterrett screening (group testing) procedures and the effects of faulty inspection

Continuing previous work on effects of errors in inspection on group sampling schemes, a modification of Dorfman-Sterrett schemes is studied. The modification consists of reversion to group sampling when a specified number of decisions of nonconformance have occurred in the course of inspection of individual items.     

Sampling inspection for resubmitted lots

Lot resubmissions are allowed in situations where the original inspection results are suspected or when the supplier is allowed to opt for resampling as per the provisions of the contract etc. This paper examines the situation of resampling of lots and derives the performance measures of a resampling scheme having a single sampling plan for inspection. The usefulness and limitations of resampling of resubmitted lots are also discussed     

Pointwise and functional approximations in Monte Carlo maximum likelihood estimation

We consider the use of Monte Carlo methods to obtain maximum likelihood estimates for random effects models and distinguish between the pointwise and functional approaches. We explore the relationship between the two approaches and compare them with the EM algorithm. The functional approach is more ambitious but the approximation is local in nature which we demonstrate graphically using two simple examples. A remedy is to obtain successively better approximations of the relative likelihood function near the true maximum likelihood estimate. To save computing time, we use only one Newton iteration to approximate the maximiser of each Monte Carlo likelihood and show that this is equivalent to the pointwise approach. The procedure is applied to fit a latent process model to a set of polio incidence data. The paper ends by a comparison between the marginal likelihood and the recently proposed hierarchical likelihood which avoids integration altogether.     

Matching Performance of Continuous Sampling Plans with Single Sampling Plans

Single sampling plans are widely used for appraising incoming product quality. However, for situations where a continuous product flow exists, lot-by-lot demarcations may not exist, and it may be necessary to use alternate procedures, such as CSP-1, for continuous processes. In this case, one would like to be able to understand how average performance of the continuous sampling procedures compares to the more commonly used single sampling plans.

In this study, a model is devised which can be used to relate plan performance between single sample lot acceptance procedures and Dodge's(1943) CSP-1 continuous sampling plan. It is shown that it is generally not possible to match up performance based upon operating characteristic curve expressions for the two plans. Instead, the plans are matched by equating expressions for π(p), the long run proportion of product which is accepted, under both procedures. This is shown to be equivalent to matching up properties on an average outgoing quality basis. The methodology may be extended for any derivative plan under MIL-STD-1235B (1982), the military standard for continuous acceptance sampling.     

A general class of hierarchical ordinal regression models with applications to correlated roc analysis

The authors discuss a general class of hierarchical ordinal regression models that includes both location and scale parameters, allows link functions to be selected adaptively as finite mixtures of normal cumulative distribution functions, and incorporates flexible correlation structures for the latent scale variables. Exploiting the well‐known correspondence between ordinal regression models and parametric ROC (Receiver Operating Characteristic) curves makes it possible to use a hierarchical ROC (HROC) analysis to study multilevel clustered data in diagnostic imaging studies. The authors present a Bayesian approach to model fitting using Markov chain Monte Carlo methods and discuss HROC applications to the analysis of data from two diagnostic radiology studies involving multiple interpreters.     

Minimum Average Total Inspection of Variable Lot-size Sampling Plan for Continuous Production

This paper explores the problem of minimizing the average total inspection (ATI) of Read & Beattie's variable lot-size sampling plan for continuous production. The solution procedure is developed to find the optimal parameters (n,  c) that will meet the average outgoing quality limit (AOQL) requirement, while also minimizing the ATI for this variable lot-size plan.     

A flexible sampling scheme for variables inspection with loss consideration

This article develops a variables sampling scheme for resubmitted lots by incorporating the concept of Taguchi loss function. The probability of lot acceptance is derived based on the exact sampling distribution and two-point condition on operating characteristic curve is used to determine the plan parameters that meet both the producer's and consumer's quality and risk requirements. Moreover, the performance of the proposed variables resubmitted sampling plan is investigated and compared with the classical variables single sampling plan. The results indicate that the developed resubmitted sampling plan can provide the same protection with less inspection when the submitted lot is good enough. Tables of the plan parameters under various conditions are provided and the use of the proposed plan is also illustrated with an example.     

On a problem in two-stage sampling

Beattie 1962 proposed an alternate procedure for monitoring continuous processes which, unlike existing continuous samplingplans under Mil-Std-1235B, does not require periods of 100% inspection. The procedure, which is a composite of two Cumulative (Cusum) procedures, will be analyzed in terms of Cusum average run length (ARL) performance. An algorithm is proposed for generating sample plans based upon specifications on ARL performance in each of the Cusum sampling zones and the overall sampling risks of the procedure. The algorithm is fully described, and implemented using exact expressions for the Cusum ARL. An illustrated example is provided, describing how a continuous sampling maybe selected which matches performances about the AQL for a related plan in ISO 3951.     

Pitman closeness for hierarchical bayes predictors in mixed linear models

The present article considers the Pitman Closeness (PC) criterion of certain hierarchical Bayes (HB) predictors derived under a normal mixed linear models for known ratios of variance components using a uniform prior for the vector of fixed effects and some proper or improper prior on the error variance. For a generalized Euclidean error, simultaneous HB predictors of several linear combinations of vector of effects are shown to be the Pitman-closest in the frequentist sense in the class of equivariant predictors for location group of transformations. The normality assumption can be relaxed to show that these HB predictors are the Pitman-closest for location-scale group of transformations for a wider family of elliptically symmetric distributions. Also for this family, the HB predictors turn out to be Pitman-closest in the class of all linear unbiased predictors (LUPs). All these results are extended for the HB predictor of finite population mean vector in the context of finite population sampling.     

Three-stage group screening with errors in observations

This paper examines the performance of three-stage group screening in terms of the expected number of runs and the expected number of incorrect decisions. A few tables are given at the end to provide the reader with a guideline in choosing a proper screening strategy.     

Robustness of the posterior mean in normal hierarchical models

We consider the problem of robustness in hierarchical Bayes models. Let X = (X₁,X₂, … ,X_p)^τ be a random vector, the X₁ being independently distributed as N(θ₁,σ²) random variables (σ² known), while the θ₁ are thought to be exchangeable, modelled as i.i.d, N(μ,τ²). The hyperparameter µ is given a noninformative prior distribution π(μ) = 1 and τ² is assumed to be independent of µ having a distribution g(τ²) lying in a certain class of distributions g. For several g's, including e-contaminations classes and density ratio classes we determine the range of the posterior mean of θ₁ as g ranges over g.