• Journal of the Korea Society for Simulation
• /
• v.9 no.2
• /
• pp.75-87
• /
• 2000

In this paper, nonstationary multiple sampling plans are discussed which are difficult to solve by analytical method when there exists dependency between the sample data. The initial solution is found by the sequential sampling plan using the sequential probability ration test. The number of acceptance and rejection in each step of the multiple sampling plan are found by grouping the sequential sampling plan's solution initially. The optimal multiple sampling plans are found by simulation. Four search methods are developed U and the optimum sampling plans satisfying the Type I and Type ll error probabilities. The performance of the sampling plans is measured and their algorithms are also shown. To consider the nonstationary property of the dependent sampling plan, simulation method is used for finding the lot rejection and acceptance probability function. As a numerical example Markov chain model is inspected. Effects of the dependency factor and search methods are compared to analyze the sampling results by changing their parameters.

• Communications for Statistical Applications and Methods
• /
• v.5 no.1
• /
• pp.107-120
• /
• 1998

This research aims here to develop a certain extended double sampling plan, EDS, which is an extension of ordinary double sampling plan in the sense that the second-stage sampling effort and second-stage critical value are allowed to depend on the point at which the first-stage continuation region is traversed. For purpose of comparison, single sampling plan, optimal ordinary double sampling plan(ODS) and sequential probability ratio test are considered with the same overall error rates, respectively. It is observed that the EDS idea allows less sampling effort than the optimal ODS.

• Journal of Korean Society for Quality Management
• /
• v.25 no.3
• /
• pp.22-38
• /
• 1997

In a traditional sequential acceptance sampling plan, it is assumed that the sampled items are independent each other. In this paper, stochastically dependent sequential acceptance sampling plans are dealt when there exists dependency between sampled items. Monte-Calro algorithm is used to find the acceptance and rejection probabilities of a lot. The number of defectives for the test to be accepted and rejected in probability ratio sequential test can be found by using these probabilities. The formula for measures of performance of these sampling plans is developed. Type I and II error probabilities are estimated by simulation. This research can be a, pp.ied to sequential sampling procedures in place of control charts where there is a recognized and necessary dependency during the production processes. Also, dependent multiple acceptance sampling plans can be derived by extending this sequential sampling procedure. As a numerical example, a Markov dependent process model is given, and the characteristics of the sampling plans are examined according to the change of the dependency factor.

• Journal of Korean Institute of Industrial Engineers
• /
• v.28 no.4
• /
• pp.351-359
• /
• 2002

In this paper, stochastically dependent single and sequential acceptance sampling plans are dealt when the process follows a Polya process model. A Monte-Cairo algorithm is used to find the acceptance and rejection probabilities of a lot. The number of defectives for the test to be accepted and rejected in a probability ratio sequential test can be found by using these probabilities. The formula to measure performance of these sampling plans is developed. Type I and II error probabilities are estimated by simulation. Dependent multiple acceptance sampling plans can be derived by extending the sequential sampling procedure. In numerical examples, single and sequential sampling plans of a Polya dependent process are examined and the characteristics are compared according to the change of the dependency factor.

• Journal of Korean Institute of Industrial Engineers
• /
• v.25 no.1
• /
• pp.8-20
• /
• 1999

In this paper, a design and estimation procedure for the stochastically dependent nonstationary multiple acceptance sampling plans is developed. At first, the rough-cut acceptance and rejection numbers are given as an initial solution from the corresponding sequential sampling plan. A Monte-Carlo algorithm is used to find the acceptance and rejection probabilities of a lot. The conditional probability formula for a sample path is found. The acceptance and rejection probabilities are found when a decision boundary is given. Several decision criteria and the design procedure to select optimal plans are suggested. The formula for measuring performance of these sampling plans is developed. Type I and II error probabilities are also estimated. As a special case, by setting the stage size as 1 in a dependent sampling plan, a sequential sampling plan satisfying type I and II error probabilities is more accurate and a smaller average sample number can be found. In a numerical example, a Polya dependent process is examined. The sampling performances are shown to compare the selection scheme and the effect of the change of the dependency factor.

• Journal of Industrial Technology
• /
• v.1
• /
• pp.67-71
• /
• 1981

The sequential sampling models are presented in a form which includes inspector error. The effect of inspector errors on the probability of type I and type II errors is discussed.

• Korean journal of applied entomology
• /
• v.40 no.2
• /
• pp.105-109
• /
• 2001

Dispersion pattern of the citrus red mite (CRM), Panonychus citri (McGregor) was determined to develop a monitoring method in the satsuma mandarin fields, Citrus unshiu L., in Jeju-do, during 1999 and 2000. CRM population was sampled by collecting leaves. Taylor's power law provided better description of mean-variance relationship for the dispersion indices compared to Iwao's patchiness regression. Slopes and intercepts of Taylor's power law from leaf samples did not differ among surveyed groves. Fixed-precision levels (D) of a sequential sampling plan were developed using Taylor's power law parameters generated from all motile stages of CRM in leaf sample. This sampling plan for leaf sample estimate was tested with resampling validation for sampling plan using 4 independent data sets. Resampling simulation analysis demonstrated that actual fixed-precision level values were better than desired D values of 0.20, 0.25 and 0.30. Required numbers for tree sampling at the density of more than 7 mites per tree were fewer than 18.

• Korean Journal of Environmental Biology
• /
• v.35 no.4
• /
• pp.427-436
• /
• 2017

A fixed-precision-level sampling plan was developed to establish control of the two-spotted spider mite, Tetranychus urticae, in two strawberry greenhouses (conventional plot, natural enemy plot). T. urticae was sampled by taking a three-leaflet leaf (1 stalk) from each plant (3 three-leaflet leaves) from each sampling position. Each leaflet was divided into three different units (1-leaflet, 2-leaflet, and 3-leaflet units) to compare relative net precision (RNP) values for selection of the appropriate sampling unit. The relative net precision values indicated that a 1-leaflet unit was more precise and cost-efficient than other units. The spatial distribution analysis was performed using Taylor's power law (TPL). Homogeneity of the TPL parameters in each greenhouse was evaluated by using the analysis of covariance (ANCOVA). A fixed-precision-level sequential sampling plan was developed using the parameters of TPL generated from the combined data of the conventional plot and natural enemy plot in a 1-leaflet sampling unit. Sequential classification sampling plans were also developed using the action threshold of 3 and 10 mites for pooled data. Using the results obtained in the independent data, simulated validation of the developed sampling plan by Resampling validation for sampling plan (RVSP) indicated a reasonable level of precision.

• Korean journal of applied entomology
• /
• v.48 no.1
• /
• pp.45-51
• /
• 2009

This paper presents sequential sampling plans for evaluating the pest density based on complete counts from probe in a rice storage warehouse. Both maize weevil and Indian meal moth population showed negative binomial dispersion patterns in brown rice storage. For cost-effective monitoring and action decision making system, sequential sampling plans by using the sequential probability ratio test (SPRT) were developed for the maize weevil and Indian meal moth in warehouses with 0.8 M/T storage bags. The action threshold for the two insect pests was estimated to 5 insects per kg, which was projected by a matrix model. The results show that, using SPRT methods, managers can make decisions using only 20 probe with a minimum risk of incorrect assessment.

• Research in Plant Disease
• /
• v.21 no.4
• /
• pp.268-272
• /
• 2015

Bacterial leaf blight caused by Pseudomonas syringae pv. porri is one of the major bacterial diseases of garlic (Allium sativum). In South Korea, the disease has only been observed in garlic-growing regions of Jeju island. The spatial distribution pattern of the disease was analyzed by binary power law, in which the natural logarithm of the observed variance is regressed on the natural logarithm of the binomial variance. The estimated slope (b=1.361) of the regression was greater than 1 which meant that the diseased plants were aggregated. The sequential sampling plans were developed for estimating the mean incidence rate ($p_m$) and classifying the mean incidence as being below or above the critical incidence rate ($p_t$). These results could be used on more efficient and higher precisive sampling for bacterial blight of garlic compared to fixed sample sized sampling.