What is Sample?
A sample is a subset of a population. Sample is a relatively small fraction selected from a population; the sample is supposed to be a true representative of the population. The researchers have to decide on how to obtain the sample and, once the sample data are in hand, how to use them to estimate the characteristic of the whole population. Sampling involves questions of sample size, how to select the sample, and what measurements to record.
Types of Sample:
Sample are three types. They are:
Random sample: Every individual in the population has an equal chance of being selected as a sample. It is free from bias, therefore it is a true representative of the population.
Numerical sample: A sample in which the proportion by number of, say, long, medium and short fibers, would be the same in the sample as in the population.
Biased sample: When the selection of an individual is influenced by factors other than chance, a sample ceases to be truly representative of the bulk and leads to bias in results.
What is Population? All elements, individuals or units that meet the selection criteria for a group to be studied and from which a representative sample is taken for detailed examination. It is the total system that need to be studied.
What is Sampling?
It is not possible or desirable to test all the raw material or all the final output from a production process because of time and cost constraints. The total raw material bought or the total end production is not 100% tested due to cost effectiveness and time constraints. The destructive type of testing will also increase the wastage in the process, which will ultimately increase the cost of testing, resulting in overall profit being decreased. Therefore sampling techniques are employed and representative samples of the whole material are tested.
The aim of sampling is to produce an unbiased sample in which the proportions of, for instance, the different fiber lengths in the sample are the same as those in the bulk. Or to put it another way, each fiber in the bale should have an equal chance of being chosen for the sample
For the testing of cotton fiber, a 20 mg weight of sample is taken from a 250 kg bale. The sample only represents a portion of the bulk, but the quality of the whole population will be evaluated on the basis of it. The sample from the bale is taken in such a way that each group’s fiber length has an equal opportunity to be selected. The main objective is to get an unbiased test sample that represents the whole population; each and every part of the possible length group is represented in the sample.
Causes of Bias in Sampling:
Bias due to physical characteristics: Longer fibers have a greater chance of being selected.
Position relative to the person: Lab assistant may pick bobbins from the top layer of a case of yarn (just to make his job easier or may be because of his ignorance), but the bobbin chosen will be biased due to their position.
Subconscious bias: Person selecting cones will pick the best-looking ones that are free from ridges, cub webbed ends and so on. This affects the test results.
Importance of Sampling in Textile Testing: Textile testing is destructive in nature, i.e. the materials used for testing go as waste after testing and hence it is not desirable to test all of the material. As textile production is always huge and bulk it is impossible to test all the final output from a production process. Thus, only representative samples of the material are tested. Sampling saves time and cost.
Sampling methods depends on the following factors:
Form of the material
Amount of material available
Nature of the test
Type of testing instrument
Information required
Degree of accuracy required
Sampling for textile testing:
Fiber stage
Yarn stage
Fabric stage
Garment stage
Fiber Sampling Techniques:
Since 100% testing of fiber is not possible, random sampling is done. There are some types of techniques used in fiber testing.
Zoning technique:
Zoning is a method that is used for selecting samples from raw cotton or wool or other loose fiber where the properties may vary considerably from place to place. Zoning is a popular technique for fiber as it is used for selecting samples from raw material such as cotton or wool or other loose natural fibers. The properties of these natural fibers may vary significantly from place to place. As cotton in bulk is not homogeneous, a number of sub-samples must be taken at random from different places in the bulk. When samples are drawn from cotton bales, the required amount of fibers should be taken one by one at random from different parts of the bale. You can show Figure-1 for details of zoning techniques.
Figure 1: Zoning technique
Step 1: A sample that weighs 2 ozs (approximately 906.72 gm) is drawn by selecting about 80 large tufts from different parts of the bulk.
Step 2: This sample is then divided into four parts.
Step 3: Sixteen small tufts are taken at random from each part (approximately 20 mg).
Step 4: Each tuft is halved four times, discarded alternately by turning the tuft through right angle between successive halving. Sixteen wisps are thus produced from each part.
Step 5: These wisps are combined to form a tuft.
Step 6: Each tuft is mixed by doubling and drawing between fingers.
Step 7: Each tuft is divided into four parts.
Step 8: A new tuft is obtained by combining a part of each of four tufts.
Step 9: Sample is mixed again by doubling and drawing.
Step 10: A quarter of sample is taken out from each tuft to form final sample.
Core sampling techniques:
The core sampling technique is used for assessing the proportion of foreign matter, the waste percentage, and the moisture content in the compressed unopened bales of raw wool or cotton. A tube with a sharpened tip is forced into the bale and a core of wool or cotton is withdrawn. The technique was first used as core boring in which the tube was rotated by a transportable electric drill. It was then developed further to facilitate the cores to be cut by pressing the tube into the bale by hand. This enables samples to be taken in areas distant from sources of power.
Figure 2: Core sampling
Fiber sampling from combed slivers or roving or yarns:
Random draw method: This method is used for sampling card sliver, ball sliver and top. The sliver from which sample has to be taken is pulled in such a way that the end has no broken or cut fibers.
Cut square method: This method is used for obtaining fiber sample from yarn. Cut a certain length of the yarn and then untwist one of the ends of the yarn by hand. Then lay the untwisted yarn on a small velvet board and cover with a glass plate. Then cut the untwisted end of the yarn at about 5 mm from the edge of the plate. Remove all the fibers that project in front of the glass plate one by one with a pair of forceps and discard.
Random sampling:
The random sampling technique is the most widely used technique. It can be applied in both fiber and yarn testing. The steps involved are as follows: determine the size of the population; determine the sample size; prepare a random numbers table; determine the number of each item in a sample; collect the sample. The following types of random sampling are used in the industry:
Stratified random sampling: This is done by dividing the population into several mutually exclusive regions.
Cluster sampling: This is done by subdividing the population into groups or clusters and taking a sample from each.
Selected sampling: In this type, the samples are collected from one part of the population.
Systematic sampling: This is performed systematically at a regular interval.
Acceptance sampling: This is used to accept the incoming raw material or for quality assurance of outgoing consignments.
Sampling Errors:
The following types of errors might occur during sampling:
Sampling only from the surface of a liquid at rest
Sampling from edge of sheet
Sampling from one segment of a lot
Instrument calibration
Improper reading
Lack of accuracy of sample
Yarn Sampling Techniques: When selecting yarn for testing it is suggested that ten packages are selected at random from the consignment. If the consignment contains more than five cases, five cases are selected at random from it. The test sample then consists of two packages selected at random from each case. If the consignment contains less than five cases, ten packages are selected at random from all the cases with approximately equal numbers from each case. The appropriate number of tests are then carried out on each package.
Random sampling – yarn in package form:
Yarn is available in various forms of package such as bobbins, cops, cone and cheese and as hanks. Table of random number is normally used sampling yarn bobbins from comparatively small bulk size. Totally 10 packages may be selected at random.
If the bulk contains more than five cases, at least five cases are selected at random and then two packages are selected at random from each case.
If the number of cases is less than five, then ten packages are selected at random approximately, two from each package.
Fabric Sampling Techniques:
When taking fabric samples from a roll of fabric certain rules must be observed. Fabric samples are always taken from the warp and weft separately as the properties in each direction generally differ. Figure 3 shows correct sampling method for woven fabric. Fabric samples from warp and weft are taken separately as their properties vary substantially along warp and weft. Identify and mark the warp direction first. Make sure that no two specimens contain same warp or weft threads. Mark and cut samples at least 2 inches away from the selvedge. Also, make sure not to take samples from creased, wrinkled or damaged portions of the fabric, if any. In case of knit fabric, samples are taken from different parts of the fabric almost the same way as done for wovens.
Figure 3: Fabric sampling
References:
Advanced Textile Testing Techniques by Sheraz Ahmad, Abher Rasheed, Ali Afzal, Faheem Ahmad
A Practical Guide to Textile Testing by K. Amutha
Physical Testing of Textiles by B. P. Saville
Handbook of Textile Testing and Quality Control by Elliot B. Grover and D.S. Hamby
Physical Properties of Textile Fibres (Fourth edition) by W. E. Morton and J. W. S. Hearle
Founder & Editor of Textile Learner. He is a Textile Consultant, Blogger & Entrepreneur. He is working as a textile consultant in several local and international companies. He is also a contributor of Wikipedia.
