Chapter III - Sampling for Research

Steps in Sampling Design Characteristics of a good sample design Different types of sample design Random sampling

Why Sample? 1. Population or target population

refers to the entire group of people, events or things of interest that the researcher wishes to investigate. It includes all relevant cases sharing some common characteristic For eg., if the CEO of a computer firm wants to know the kind of advertising strategies adopted by computer firms in Pune, then all computer firms situated there will constitute the population. If a banker is interested in investigating the saving habits of blue-collar workers in an automobile industry, then all blue collar workers in automobile industries across the country will make up the population. a population is a group of individuals or persons, objects, or items from which samples are taken for measurement, for example, a population of doctors or professors, books or students. Thus, a population is the total collection of elements about which we wish to make some inferences

2. Element
is a single member of the population. If 1000 blue collar workers in a particular organization happen to be the population of interest to a researcher, each single blue collar worker therein is an element. If 500 pieces of machinery are to be approved after selecting a few, there would be 500 elements in this population.

3. Sampling Frame

is a listing of all the elements in the population from which the sample is drawn. The sampling frame is sometimes referred to as the population frame or working population. The payroll of an organization would serve as the sampling frame if its members were to be studied. The telephone directory is also a sampling frame, a list of class students, a university register listing all students, faculty and administrators during a particular academic year or semester

4. Sample

A sample is a sub-section of a population that

mirrors the traits of that population. A statistical sample is a miniature picture or cross section of the entire group or aggregate from which the sample is taken. It is therefore the reflection of the universe and bears all the characteristics of the universe. A sample is a finite part of a statistical population whose properties are studied to gain information about the whole (Webster). When dealing with people, it can be defined as a set of respondents (people) selected from a larger population for the purpose of a survey. Sample is a number of individual cases selected (drawn or pulled) from a larger population.

5. Subject

A subject is a single member of the

sample just as an element is a single member of a population. If a sample of 50 machines from a total of 500 machines is to be inspected, then every one of the 50 machines is a subject.

What is sampling?
Basic idea of sampling is that by selecting some of the elements in a population we may draw conclusions about the entire population. We sample as a means to an end. To study a group and be able to say something about it without having to study every case in the population, we must sample. It is often the case that attempting to study every case in the entire group will be too overwhelming and/or costly. Furthermore, given the totality of constraints, we may end up with more errors than we would through sampling.

Relationship between population, sampling frame and sample

sample Each is a subject

population
Each is an element

Sampling frame

Sample versus Census a. Census method deals

b.

with the investigation of the entire population. Under this, data is collected for each and every unit of the universe. This method provides more accurate and exact information as no unit is left out. Sampling method involves the selection of a small group which is representative of the whole universe.

Census vs Sample
There are some reasons for sampling instead of doing a census: 1. Economy (lower cost) 2. Time factor (greater speed of data collection- (eg, doctor during outbreak of disease) 3. The large size of many populations 4. Inaccessibility of some of the population 5. Greater accuracy of results

Steps in Sampling Design

Researcher has to consider the following points : 1. Type of Universe: can be finite or infinite. finite - number of items is certain - population of a city, number of workers in a factory, children in a school infinite -number of items is infinite, i.e., we cannot have any idea about the total number of items - number of stars in the sky, listeners of a specific radio programme 2. Sampling unit: Sampling unit may be geographical one such as state, district, village etc., or a construction unit such as a house, flat etc. or it may be a social unit such as a family, club, school etc. or an individual. researcher will have to decide one or more of such units that he has to select for his study.

Steps in Sampling Design (contd)

3. Sampling Frame (source list):
- is a list from which the sample is drawn. It contains the names of all items of a universe (in case of finite universe only). If source list is not available, researcher has to prepare it. Such a list has to be comprehensive, correct, reliable and appropriate. It is extremely important for the source list to be as representative of the population as possible. to be selected from the universe to constitute a sample. The size of the sample should neither be excessively large, nor too small. It should be optimum. An optimum sample is one which fulfills the requirements of efficiency, representativeness, reliability and flexibility.

4.

Size of sample: refers to the number of items

Steps in Sampling Design (contd)

5. Parameters of interest: The characteristics of interest will determine the sample size. There may also be some important sub-groups in the population about whom we would like to make estimates. Budgetary constraints: Cost considerations from the practical point of view, have a major impact upon decisions relating to not only the size of the sample but also to the type of sample. Sampling procedure: Finally, the researcher must decide the type of sample to be used, i.e., he must decide about the technique to be used in selecting the items of the sample. There are several sample designs out of which the researcher must choose one for his study.

6.

7.

Characteristics of a good sample

Representativeness: A sample must be

representative of the population. In measurement terms, a sample must be valid. The validity of a sample depends upon its accuracy and precision. Accuracy: This is defined as the degree to which bias is absent from the sample. An accurate (unbiased) sample is one which exactly represents the population. It is free from any influence that causes any difference between sample value and population value. It should control bias in every way. Precision: The sample must yield precise estimate. Precision is measured by the standard error or standard deviation of the sample estimate. The smaller the standard error, the higher is the precision of the sample. Size: A good sample must be adequate in size in order to be reliable. The sample size should be such that the inferences drawn are accurate to a reasonable level of confidence.

Different Types of Sampling design

There are two types: Probability sampling Non-probability sampling

Probability Sampling

the elements in the population have some known chance or probability of being selected as sample subjects. This method provides a scientific technique of drawing samples from a population according to some laws of chance in which each unit has some definite pre assigned probability of being chosen in the sample. Examples of probability sampling are A grain of rice in a bowl Lottery any chit can be picked

Probability Sample
A sample selected in such a way that every element has an equal chance of being selected. - based on probability theory and the ability to later use inferential statistics to compute the likelihood that sample characteristics are representative of the population. - allow for computation of the confidence that the sample and findings drawn from it are representative of the larger population. - are used when the representativeness of a sample is of importance in the interests of wider generalisability

Types of probability sampling

random sampling stratified random sampling systematic random sampling cluster (area) random sampling multi-stage random sampling

Probability Sampling (contd)

Simple Random Sample: A probability sample in which every member of a study population has been given an equal chance of selection. A simple random sample is free from sampling bias.

Stratified Random Sample: Stratification means division of the universe into groups according to the geographical, sociological or economic characteristics.
A probability sample in which the study population is divided into smaller groups or strata on the basis of some important characteristic. Simple random samples are then selected from each stratum.

Probability Sampling (contd)

Systematic random sampling- sample taken from list prepared on a systematic arrangement either on basis of alphabetical order or some number or any other method. In this, only first sample unit is selected at random and remaining units are automatically selected in a definite sequence at equal spacing from one another. For eg., 100 students in a class. You want a sample of 20 from these 100.You have their names listed on a piece of paper may be in alphabetical order. For systematic random sampling, divide 100 by 20, you will get 5. Randomly select any number between 1 and five. Suppose the number picked is 4, that will be the starting number. So student number 4 has been selected. From there you will select every 5th name until you reach the last one, number one hundred. You will end up with 20 selected students.
Cluster Sample: In this the population is grouped. Categories are not defined. Eg. If a bank has 15000 credit holders but wants to study only 450, it makes 100 clusters of 150 each. Then picks any three clusters to complete the sample. Multi-stage Sample:- generally used in selecting sample from very large area. As name suggests multi stage refers to sampling technique carried out in various stages. Here the population is regarded as made of a number of primary units, each of which is further composed of a number of secondary stage units which is further composed of third stage units and so on till the desired sampling unit is reached.

Non-probability samples
A sample that has been drawn in a way that doesnt give every member of the population a known chance of being selected.

Types of Non-probability samples accidental, haphazard, or convenience sampling purposive sampling or judgment sampling quota sampling snowball sampling

Types of Non-probability Samples:

1. Accidental, haphazard or Convenience sampling- known as
unsystematic or opportunistic sampling. Sample selected according to convenience of researcher Convenience in respect of availability of data, accessibility of units etc. called accidental or haphazard sampling because it uses who ever happens to be available. Random sampling is sacrificed to save time, money, and effort. The physical and organizational proximity of participants drives this type of sampling; eg., you decide to interview the first ten people you meet tomorrow morning. It saves time, money and effort. poorest way of getting samples, has lowest credibility and yields information-poor cases. constitutes the most common methods of sampling. includes the traditional "person on the street" interviews conducted frequently by television news programs to get a quick (although non-representative) reading of public opinion.

Types of Non-probability Samples: (contd)

2. Purposive

or judgement sampling we sample with a purpose in mind. When the

researcher deliberately selects certain units for study from the universe, it is called deliberate sampling or judgement sampling. - selection is done on the judgement of the researcher and nothing is left to chance. - Purposive samples consist of people whom you feel are important to the study because of specific personal traits, where they live, the work they do, or their involvement in a particular issue.

3. Quota Sampling
Quota sampling capitalizes on the first come,
first served principle. It is a practical and convenient method. It is also relatively inexpensive. However, the sample may not be representative of the universe and the inferences drawn may no be amenable to statistical treatment. Quota sampling is a special type of stratified sampling. Firstly, the population is stratified on some basis, preferably on the characteristics of the population under study. Then the interviewers are simply given quotas to be filled from the different strata, with some restrictions on how they are to be filled. In quota sampling, we select people nonrandomly according to some fixed quota

 4. Snow-ball sampling In snowball sampling what you do is to

get hold of one and he/she will tell you where the others are or can be found. When you find those others they will tell you where you can get more others and the chain continues. involves a process of chain referrals. You begin with a small group of people and ask them who the others are whom you might want to interview.

Non-Probability Sample When to Use

Non-probability samples can be used effectively in a wide variety of circumstances. . .

When a group that represents the target population already exists.

When it is impossible or overly difficult to obtain a list of names for sampling. (Example homeless.) When research is exploratory in nature and all of the cases of interest may not be identified ahead of time. It is critical to recognize that you cannot generalize with any known degree of accuracy from a non-probability sample. In other words, the data represent only those units of analysis you actually studied.