• Embed Doc
  • Copy Link
  • Readcast
  • Collections
  • CommentGo Back
Download
 
© Copy Right: Rai University
11.556 83
RESEARCH METHODOLOGY
Hello, students today we shall be continuing our discussing onissues in sampling. Before proceeding further let us recaptulatewhat we had studied in the last lecture first.We have learned that a sample is a part or aggregate selected witha view to obtaining information about the whole group alsoknown as population. The population is composed of a numberof units. The total number of units in the population and in thesample are known as population size and sample size. We alsocame to know that sampling is the scientific technique of drawinga sample. Any characteristic of population is called parameter andthat of sample is called statistic. Also, the standard deviation of sampling distribution is called standard error, larger the samplesize lower will be the standard error. We have also studied varioussources of sampling and non-sampling error along with principlesof sampling.For the process of statistical inference to be valid we must ensurethat we take a representative sample of our population.Whatever method of sample selection we use it is vital that themethod is described.How do we know if the characteristics of a sample we take matchthe characteristics of the population we are sampling? The shortanswer is wedon’t. We can, however, take steps that make it aslikely as possible that the sample will be representative of thepopulation.Two simple and effective methods of doing this are making surethe sample size is large and making sure it is randomly selected.A large sample size is more likely to be representative of apopulation than a small one.Think of extreme cases. If we want to know the average heightof the population and we select just one person and measuretheir height it is unlikely to be close the population average. If wetook 1,000,000 people, measured their heights and took the average,this figure would be likely to be close to the population average.
Types of Sampling
The type of enquiry you want to have and the nature of data thatyou want to collect fundamentally determines the technique ormethod of selecting a sample.The procedure of selecting a sample may be broadly classifiedunder the following three heads:
•
Non-Probability Sampling Methods: Subjective orJudgement Sampling
•
Probability Sampling
•
Mixed SamplingNow let us discuss these in detail. We will start with the non-probability sampling then we will move on to probability sampling.
Non-Probability Sampling Methods
The common feature in non probability sampling methods isthat subjective judgments are used to determine the populationthat are contained in the sample .We classify non-probabilitysampling into four groups:1. Convenience Samples2. Judgement Samples3. Quota Samples4. Snowball samples
A. Convenience Samples
•
These types of samples are used primarily for reasons of convenience.
•
It is used for exploratory research and speedy situations.
•
It is often used for new product formulations or to providegross-sensory evaluations by using employees, students,peers, etc.Convenience sampling is extensively used in marketing studiesand otherwise.This would be clear from the following examples1.Suppose a marketing research study aims at estimating theproportion of Pan (Beetle leaf) shops in Delhi, which store aparticular drink Maaza. It is decided to take a sample of size150. What the investigator does is to visit 150 Pan shopsnear his place of office as it is very convenient to him andobserve whether a Pan shop stores Maaza or not.This is definitely not a representative sample, as most Panshops in Delhi had no chance of being selected. It is onlythose Pan shops which were near the office of theinvestigator has a chance of being selected2.The other example where convenience sampling is oftenused is in test marketing. There might be some cities whosedemographic make-ups are approximately the same asnational average. While conducting marketing tests for newproducts, the researcher may take samples of consumersfrom such cities and obtain consumer evaluations aboutthese products as these are supposed to represent “national”tastes.3.A ball pen manufacturing company is interested in knowingthe opinions about the ball pen (like smooth flow of ink,resistance to’ breakage of the cover etc.) it is presentlymanufacturing with a view to modify it to suit customersneed. The job is given to a marketing researcher who visits acollege near his place of residence and asks a few students (aconvenient sample) their opinion about the ‘ball pen” inquestion.4.As another example a researcher might visit a few shops toobserve what brand of vegetable oil people are buying so asto make inference about the share of a particular brand he isinterested in.
LESSON 14:DESIGNING SAMPLE
 
© Copy Right: Rai University
84 11.556
RESEARCH METHODOLOGY
B. Judgement Samples
•
It is that sample in which the selection criteria are based uponyour (researcher’s) personal judgment that the members of the sample are representative of the population under study.
•
It is used for most test markets and many product testsconducted in shopping malls.If personal biases are avoided,then the relevant experience and the acquaintance of theinvestigator with the population may help to choose arelatively representative sample from the population. It isnot possible to make an estimate of sampling error as wecannot determine how precise our sample estimates are.Judgement sampling is used in a number of cases, some of whichare:1.Suppose we have a panel of experts to decide about thelaunching of a new product in the next year. If for somereason or the other, a member drops out, from the panel,the chairman of the panel may suggest the name of anotherperson whom he thinks has the same expertise andexperience to be a member of the said panel. This newmember was chosen deliberately - a case of Judgmentsampling.2.The method could be used in a study involving theperformance of salesmen. The salesmen could be groupedinto top-grade and low-grade performer according to certainspecified qualities. Having done so, the sales manager mayindicate who in his opinion, would fall into which category.Needless to mention this is a biased method. However inthe absence of any objective data, one might have to resortto this type of sampling.
C. Quota Samples
This is a very commonly used sampling method in marketingresearch studies.Here the sample is selected on the basis of certainbasic parameters such as age, sex, income and occupation thatdescribe the nature a population so as to make of it representativeof the population.The Investigators or field workers are instructed to choose a samplethat conforms to these parameters.The field workers are assignedquotas of the number of units satisfying the requiredcharacteristics on which data should be collected.However, before collecting data on these units the investigatorsare supposed to verify that the units qualify these characteristics.Suppose we are conducting a survey to study the buying behaviorof a product and it is believed that the buying behaviour is greatlyinfluenced by the income level of the consumers. We assume thatit is possible to divide our population into three income stratasuch as high-income group, middle-income group and low-incomegroup. Further it is known that 20% of the population is in high-income group, 35% in the middle-income group and 45% in thelow-income group. Suppose it is decided to select a sample of size200 from the population. Therefore, samples of size 40, 70 and90 should come from high income, middle income and low incomegroups respectively. Now the various field workers are assignedquotas to select the sample from each group in such a way that atotal sample of 200 is selected in the same proportion as mentionedabove. For example, the first field
•
Selection is done by non-probability means and are basedupon the researcher’s judgement of appropriatedemographics.
D. Snowball Sampling
•
It is that samples in which the selection of additionalrespondents (after the first small group of respondents isselected) is based upon referrals from the initial set of respondents.
•
It is used to sample low incidence or rare populations
•
It is done for the efficiency of finding the additional, hard-to-find members of the sample.
Advantages of Non-probability Samples
•
It is much cheaper to probability samples.
•
It is acceptable when the level of accuracy of the researchresults is not of utmost importance.
•
Less research time is required than probability samples.
•
It often produces samples quite similar to the population of interest when conducted properly.
Disadvantages of Nonprobability Samples
•
You cannot calulate Sampling error. Thus, the minimumrequired sample size cannot be calculated which suggests thatthe you (researcher) may sample too few or too manymembers of the population of interest.
•
You do not know the degree to which the sample isrepresentative of the population from which it was drawn.
•
The research results cannot be projected (generalized) to thetotal population of interest with any degree of confidence.
Probability Sampling
Probability sampling is the scientific method of selecting samplesaccording to some laws of chance in which each unit in thepopulation has some definite pre-assigned probability of beingselected in the sample. The different types of probability samplingare :1.where each unit has an equal chance of being selected.2.Sampling units have different probabilities of being selected3.Probability of selection of a unit is proportional to thesample size.
Simple Random Sampling
It is the technique of drawing a sample in such a way that each unitof the population has an equal and independent chance of beingincluded in the sample.In this method an equal probability of selection is assigned toeach unit of population at the first draw.It also implies an equalprobability of selecting in the subsequent draws.Thus in simple random sample from a population of size N, theprobability of drawing any unit in the first draw is 1/N.Theprobability of drawing a second unit in the second draw is 1/N-1 .The probability of selecting a specified unit of population at anygiven draw is equal to the probability of its being selected at thefirst draw.
 
© Copy Right: Rai University
11.556 85
RESEARCH METHODOLOGY
Selection of a Simple Random Sample
As we all know Simple Random Sample refers to that method of selecting a sample in which each and every unit of population isgiven independent and equal chance to be included in the sample.But, Random Sample does not depend only upon selection of units but also on the size and nature of the population.One procedure may be good and simple for a small sample but itmay not be good for the large population.Generally, the method of selecting a sample must be independentof the properties of sampled population.Proper precautions should be taken to ensure that your selectedsample is random. Although human bias is inherent in anysampling scheme administered by human beings.Random selection is best for two reasons - it eliminates bias andstatistical theory is based on the idea of random sampling.We can select a simple random sample through use of tables of random numbers , computerized random number generator orlottery method . Thus, the three methods of drawing simplerandom sample are:
•
Mechanical method and using tables of random numbers,
•
sealed envelopes (lottery system) etc.
Lottery Method
This is the simplest method of selecting a random sample.We will illustrate it by means of example for betterunderstanding:Suppose, we want to select “r” candidates out of “n”. We assign the numbers from 1 to n i.e to each and everycandidate we assign only one exclusive number. These numbersare then written on n slips which are made as homogeneous aspossible in shape, size, colour, etc.These slips are then put in a bag and thoroughly shuffled andthen “r” slips are drawn one by one. The “r” candidatescorresponding to numbers on the slips drawn will constitute arandom sample.This method of selecting a simple random sample is independentof the properties of population. Generally in place of slips youcan use cards also. We make one card corresponding to one unit of population by writing on it the number assigned to that particularunit of pipulation. The pack of cards is a miniature of populationfor sampling purposes. The cards are shuffled a number of timesand then a card is drawn at random from them. This is one of themost reliable methods of selecting a random sample.
Mechanical Randomisation or Random NumbersMethod
The explained method of lottery is very time consuming andcumbersome to use if population is very large.Therefore the most practical and inexpensive method of selecting a random sample consists in the use of RandomNumbers Tables, which has been constructed that each of thedigits 0,1,2,3,4,5,6,7,8,9 appear with approximately the samefrequency and independently of each other.If we have to select a simple random sample from a populationof size N(d”99) then the numbers can be combined two by twoto give pairs from 00 to 99.Similarly if Nd”999 or Nd”9999 and so on, then combining thedigits three by three ( or four by four and so on ), we get numbersfrom 000 to 999 or (0000 to 9999) and so on. Since each of thedigits 0,1,2,3,4,5,6,7,8,9 appear with approximately the samefrequency and independently of each other, so does each of thepairs 00 to 99 or triplets from 000 to 999 or quadruplets 0000 to9999 and so on .Thus, the method of drawing the random sample consists in thefollowing steps:i.Identify the N units in the population with the numbersfrom 1 to Nii.Select at random, any page of the random number tables andpick up the numbers in any row or column or diagonal atrandom.iii.The population units corresponding to the number of unitselected in step (ii) comprise the random sample.I will tell you about the different sets of random numberscommonly used in practice. The numbers in these tables havebeen subjected to various statistical tests for randomness of aseries and their randomness has been well established for all practicalpurposes.1.Tippets (1927) Random Number Table: (Tracts forcomputers No. 15 Cambridge University Press)Tippet number tables consist of 10,400 four digitednumbers, giving in all 10,400 x 4 , i.e.,41600 digits selected atrandom from the British Census Report.2.Fisher and Yates (1938) Tables (in statistical tables forbiological, Agricultural and Medical Research) comprise15,000 digits arranged in twos. Fisher and Yates obtainedthese tables by drawing numbers at random from 10
th
to 19
th
digits of A.S.Thomson’s 20- figure logarithmic tables.3.Kendall and Babington Smith’s (1939) random tables consistof 1,00,000 digits grouped into 25,000 sets of 4 digitedrandom numbers (Tracts for computers No. 24 CambridgeUniversity Press)4.Rand Corporation (1955) (free oress, Illinois) randomnumber tables consist of one million random digitsconsisting of 5 digits each.5.TI-82: Generating Random NumbersYou can generate random numbers on the TI-82 calculator usingthe following sequence. N is the number of different values, whichcould be, and S is the minimum number.int (N*rand+S)If you have two values (A and B) that you need random numbersbetween, then you can generate them using the following formuleN=B-A+1int (N*rand+A)Notice it is B-A+1 not B-A. Everyone agrees there are 10 numbersbetween 1 and 10 (inclusive). But, if you take 10-1, you get 9, not10. Also, in the formula above, replace the N by the actual numberof different values.Since the calculator remembers the last formula put in, and evaluatesit when you hit enter, to generate more random numbers, just hit
of 00

Leave a Comment

You must be to leave a comment.
Submit
Characters: ...
You must be to leave a comment.
Submit
Characters: ...