5.1 Assigning a value to any property of the material in a container or in a lot, consignment, or delivery involves a measurement process that includes both sampling and testing procedures. The correctness of the value assigned depends upon the variability due to testing and sampling plan. Even when the variability due to testing is minimized by carefully developed procedures, correct and consistent estimates of the true value of the property are possible only when the sampling procedure avoids systematic bias, minimizes variations due to sampling, and provides a laboratory sample of adequate size.
5.2 Practice D2258 may not give the most efficient sampling plan that might be devised in special situations but does present a general procedure that gives satisfactory precision with an economical amount of sampling. Many plans that include stratified sampling can be found in textbooks and through the use of statistical software tools and calculators.
5.2.1 If not specified by the purchaser, the manufacturer will define suitable production lots based on one or more of the following: supply lot, production shift/time segment, production equipment or production line, operator, designated shipment, production run, or a combination herein.
5.2.2 If not specified by the purchaser, the manufacturer will define sampling and testing frequency based on the following: process capability or capability analysis, historical trends, level of detection rate required, confidence level requirements, known variations or special causes, or both. Every attempt to ensure conforming product is being produced, identify potential nonconforming product or proper isolation and identification, will be carried out by the manufacturer.
5.2.3 Sampling count and number of specimens will be based on standard practice listed within the document. Increase or decrease in count or frequency might be applied based on typical standard deviation, precision and confidence level, Measurement System Analysis (MSA), gauge R&R study, or gauge linearity and bias study. Higher variations would indicate reason for an increase in count, while lower variations would indicate reason for decrease in count, while lower variations would indicate reason for decrease in count.
5.2.4 When selecting a suitable sample size, several considerations need to be made: (1) size of the lot being sampled, (2) historical trends, (3) distribution of the data, (4) level of accuracy and confidence, (5) cost, and (6) practicality.
5.2.5 Minimizing and reducing measurement error will improve product testing reliability, reduce overall variation of test data accuracy, and improve confidence level of the reported values.