Search results

The purpose of this paper is to propose the group acceptance sampling plans for when the lifetime of the submitted product follows the Pareto distribution.

The single‐point approach (only consumer's risk) is used to find the plan parameter of the proposed plan for specified values of consumer's risk, producer's risk, acceptance number, number of testers and experiment time.

Tables are constructed using the Poisson and the weighted Poisson distribution. Extensive tables are provided for practical use.

The tables in this paper can be used only when the lifetime of a product follows the Pareto distribution of 2nd kind.

The result can be used to test the product to save cost and time of the experiment. The use of the weighted Poisson distribution provides the less group size (sample size) as than the plans in the literature.

By implementing the proposed plan, the experiment cost can be minimized.

The novelty of this paper is that Poisson and the weighted Poisson distributions are used to find the plan parameter of the proposed plan instead of the binomial distribution when the lifetime of submitted product follows the Pareto distribution of 2nd kind.

The purpose of this paper is to present the optimal double sampling attribute plan using the weighted Poisson distribution.

For the given AQL and LQL, sum of producer’s and consumer’s risks have been attained. Based on the weighted Poisson distribution, the sum of these risks has been optimized.

In the final inspection, the producer and the consumer represent the same party. So, the sum these two risks should be minimized. In this paper, the sum of risks has been tabulated using the weighted Poisson distribution for different operating ratios. These tabulated values are comparatively less than the sum of risks derived using Poisson distribution.

The sampling plan presented in this paper is particularly useful for testing the quality of finished products in shop floor situations.

The purpose of this paper is to present the single sampling attribute plan for given acceptance quality level (AQL) and limiting quality level (LQL) involving minimum sum of risks using weighted Poisson distribution.

For the given AQL and LQL, sum of producer's and consumer's risks have been attained. Based on weighted Poisson distribution, the sum of these risks has been arrived at, along with the acceptance number and the rejection number. Also, the operating characteristic function for the single sampling attribute sampling plan, using weighted Poisson distribution, has been derived.

In the final inspection, the producer and the consumer represent the same party. So, the sum these two risks should be minimized. In this paper, the sum of risks has been tabulated using weighted Poisson distribution for different operating ratios. These tabulated values are comparatively less than the sum of risks derived using Poisson distribution.

The sampling plan presented in this paper is particularly useful for testing the quality of finished products in shop floor situations.

This paper introduces a Bayesian two-sided group chain sampling plan (BT-SGChSP) by using binomial distribution to estimate the average proportion of defectives. In this Bayesian approach, beta distribution is used as a suitable prior of binomial distribution. The proposed plan considers both consumer's and producer's risks. Currently, group chain sampling plans only consider the consumer's risk and do not account for the producer's risk. All existing plans are used to estimate only a single point, but this plan gives a quality region for the pre-specified values of different design parameters. In other words, instead of point wise description for the designing of sampling plan based on a range of quality by involving a novel approach called quality region.

The methodology is based on five phases, which are (1) operating procedure, (2) derivation of the probability of lot acceptance, (3) constructing plans for given acceptable quality level (AQL) and limiting quality level (LQL), (4) construction of quality intervals for BT-SGChSP and (5) selection of the sampling plans.

The findings show that the operating characteristic (OC) curve of BT-SGChSP is more ideal than the existing Bayesian group chain sampling plan because the quality regions for BT-SGChSP give less proportion of defectives for same consumer's and producer's risks.

There are four limitations in this study: first is the use of binomial distribution when deriving the probability of lot acceptance. Alternatively, it can be derived by using distributions such as Poisson, weighted Poisson and weighted binomial. The second is that beta distribution is used as prior distribution. Otherwise, different prior distributions can be used like: Rayleigh, exponential and generalized exponential. The third is that we adopt mean as a quality parameter, whereas median and other quintiles can be used. Forth, this paper considers probabilistic quality region (PQR) and indifference quality region (IQR).

The proposed plan is an alternative of traditional group chain sampling plans that are based on only current lot information. This plan considers current lot information with preceding and succeeding lot and also considers prior information of the product.

This paper first time uses a tight (three acceptance criteria) and introduces a BT-SGChSP to find quality regions for both producer's and consumer's risk.

This paper introduces group chain acceptance sampling plans (GChSP) for a truncated life test at preassumed time by using the minimum angle method. The proposed method is an approach, where both risks associated with acceptance sampling, namely consumers’ and producer’s risks, are considered. Currently, the GChSP only considers the consumer's risk (CR), which means the current plan only protects the consumer not the producer since it does not take into account the producer's risk (PR) at all.

There are six phases involved when designing the GChSP, which are (1) identifying the design parameters, (2) implementing the operating procedures, (3) deriving the probability of lot acceptance, (4) deriving the probability of zero or one defective, (5) deriving the proportion defective and (6) measuring the performance.

The findings show that the optimal number of groups obtained satisfies both parties, i.e. consumer and producer, compared to the established GChSP, where the number of group calculated only satisfies the consumer not the producer.

There are three limitations identified for this paper. The first limitation is the distribution, in which this paper only proposes the GChSP for generalized exponential distribution. It can be extended to different distribution available in the literature. The second limitation is that the paper uses binomial distribution when deriving the probability of lot acceptance. Also, it can be derived by using different distributions such as weighted binomial distribution, Poisson distribution and weighted Poisson distribution. The final limitation is that the paper adopts the mean as a quality parameter. For the quality parameter, researchers have other options such as the median and the percentile.

The proposed GChSP should provide an alternative for the industrial practitioners and for the inspection activity, as they have more options of the sampling plans before they finally decide to select one.

This is the first paper to propose the minimum angle method for the GChSP, where both risks, CR and PR, are considered. The GChSP has been developed since 2015, but all the researchers only considered the CR in their papers.

We extend Vuong’s (1989) model-selection statistic to allow for complex survey samples. As a further extension, we use an M-estimation setting so that the tests apply to general estimation problems – such as linear and nonlinear least squares, Poisson regression and fractional response models, to name just a few – and not only to maximum likelihood settings. With stratified sampling, we show how the difference in objective functions should be weighted in order to obtain a suitable test statistic. Interestingly, the weights are needed in computing the model-selection statistic even in cases where stratification is appropriately exogenous, in which case the usual unweighted estimators for the parameters are consistent. With cluster samples and panel data, we show how to combine the weighted objective function with a cluster-robust variance estimator in order to expand the scope of the model-selection tests. A small simulation study shows that the weighted test is promising.

This paper aims to quantify the impact of craft worker shortage on construction project safety performance.

A database of 50 North American construction projects completed between 2001 and 2014 was compiled by taking information from a research project survey and the Construction Industry Institute Benchmarking and Metrics Database. The t-test and Mann-Whitney test were used to determine whether there was a significant difference in construction project safety performance on projects with craft worker recruiting difficulty. Poisson regression analysis was then used to examine the relationship between craft worker recruiting difficulty and Occupational Safety and Health Administration Total Number of Recordable Incident Cases per 200,000 Actual Direct Work Hours (TRIR) on construction projects.

The result showed that the TRIR distribution of a group of projects that reported craft worker recruiting difficulty tended to be higher than the TRIR distribution of a group of projects with no craft worker recruiting difficulty (p-value = 0.004). Moreover, the average TRIR of the projects that reported craft worker recruiting difficulty was more than two times the average TRIR of projects that experienced no craft recruiting difficulty (p-value = 0.035). Furthermore, the Poisson regression analysis demonstrated that there was a positive exponential relationship between craft worker recruiting difficulty and TRIR in construction projects (p-value = 0.004).

The projects used to construct the database are heavily weighted towards industrial construction.

There have been significant long-term gains in construction safety within the USA. However, if recent craft shortages continue, the quantitative analyses presented herein indicate a strong possibility that more safety incidents will occur unless the shortages are reversed. Innovative construction means and methods should be developed and adopted to work in a safe manner with a less qualified workforce.

The Poisson regression model is the first model that quantifiably links project craft worker availability to construction project safety performance.

This paper studies the density of bank branches in districts of Slovakia and aims to identify determinants that explain or justify districtural differences in the density of bank branches.

Bank branch density is measured by the number of branches in a district, and banks are further differentiated by size and profile. Potential determinants of bank branch density are sought through univariate and bivariate Poisson regressions amongst economic factors, socioeconomic factors, technological factors, urbanization factors, and branch market concentration.

Using data from 2016, it has been found that branch numbers in districts are determined chiefly by five factors that describe their economic development, population size with its characteristics, and existent branch concentration. The spatial distribution of bank branches in the territory of Slovakia is not random, but is found to be affected by environmental factors measurable at the districtural level. Only 22 Slovak districts representing administrative or economic centers are expected to be over-branched.

The study helps to identify factors that need be accounted for in planning and redesigning of branch networks or in implementing mergers and acquisitions on a bank level. The results are also useful in regional policy and regulatory oversight.

The present study is unique since the decision-making processes of Slovak commercial banks in planning the location and density of their branch networks have not been rationalized and researched as of yet.

We propose a generic algorithm for numerically accurate likelihood evaluation of a broad class of spatial models characterized by a high-dimensional latent Gaussian process and non-Gaussian response variables. The class of models under consideration includes specifications for discrete choices, event counts and limited-dependent variables (truncation, censoring, and sample selection) among others. Our algorithm relies upon a novel implementation of efficient importance sampling (EIS) specifically designed to exploit typical sparsity of high-dimensional spatial precision (or covariance) matrices. It is numerically very accurate and computationally feasible even for very high-dimensional latent processes. Thus, maximum likelihood (ML) estimation of high-dimensional non-Gaussian spatial models, hitherto considered to be computationally prohibitive, becomes feasible. We illustrate our approach with ML estimation of a spatial probit for US presidential voting decisions and spatial count data models (Poisson and Negbin) for firm location choices.