Page 115 - DMGT206_PRODUCTION_AND_OPERATIONS_MANAGEMENT
P. 115
Production and Operations Management
Notes Variable sampling measures product or service characteristics, such as weight, length,
volume, or time, which can be measured.
Example: Inspectors at Escorts measure the diameter of tractor engine pistons to
determine whether the product adheres to the specifications (within the allowable tolerance)
and identity differences in diameter over time.
Variable sampling is more elaborate and expensive compared to attribute sampling.
It typically involves special equipment, employee skills, exacting procedures, and time,
effort and cost.
But, it is required where the analyst requires actual measurements to draw inferences
about the lot and the performance of the operation where it came from, or where the
inspection procedure calls for destructive testing.
In variable sampling, the sample size required for the same level of protection is smaller.
This may, in many cases, more than offset the higher unit cost of inspection and result in
an overall lower total cost.
A sampling plan is the overall scheme for the acceptance or rejection of a lot based on information
gained from a sample. It is used to identify both the size and type of sample and the criteria used
to either accept or reject the lot. Different types of sampling plans can be used. These include
'single sampling', 'double sampling' and 'multiple sampling, etc.
Single Sampling Plan
With a single sampling plan, a randomly selected sample of 'n' units is taken from a lot of 'N'
units. The quality of each sampled unit is determined and the number of non-conforming
samples, 'c1' are compared to a number 'c' is called the acceptance number. If 'c' or more than 'c'
sampled units are nonconforming, the entire shipment is rejected. The decision is based solely
on the results from a single sample of 'n' units. The schematic diagram is shown in Figure below.
Figure 5.5: Single Method Sampling Plan
Double Sampling Plan
Double sampling is a two-stage process in which the first, a smaller sample is taken. There are
two acceptance numbers. The result may be a clear accept decision if the conditions of the first
110 LOVELY PROFESSIONAL UNIVERSITY