A TERM PAPER ON SAMPLING AND SAMPLING

TECHNIQUES

SAMPLING AND SAMPLING TECHNIQUES

1
 INTRODUCTION

The selection of a representative sample though comes across as an intricate,

confusing, and technical subject; it is still an essential part of any research

process. In research reports, the description of sampling process is presented

in methods section. Frequently, the misinterpretations in terminology are on

account of the contrasting meanings and usage. It would thus be ideal to

examine the related terminology so as to make the underlying assumptions

more clear.

Sampling is a process of selecting a sample from the target population.

Population: Population is the aggregation of all the units in which a

researcher is interested. In other words, population is the set of people or

entire to which the results of a research are to be generalized. For example,

a researcher needs to study the problems faced by postgraduate nurses of

India; in this the ‘population’ will be all the postgraduate nurses who are

Indian citizen.

Target Population: A target population consist of the total number of people

or objects which are meeting the designated set of criteria of interests to the

researcher. In other words, it is the aggregate of all the cases with a certain

phenomenon about which the researcher would like to make a

generalization. For example, a researcher is interested in identifying the

complication of diabetes mellitus type-II among people who have migrated

to Mehsana.

2
Accessible population: also known as the study population is the subset of

the target population to which the researcher has reasonable access for

selection of subjects to the research study. They may be limited to an

institution, city, region, state or a country.

A sample is a limited part of a population whose properties are studied to

gain about the whole (Webster, 1985).

 Sample is a group of people, objects, or elements that are taken from a

larger population in a study. In research studies, individuals are

usually mentioned as subjects or participants.

 The selected sample should be represented of the entire population.

By studying the sample the researcher generalises the results to the

population from which the sample has been chosen.

 In the above example, sample will refer to the HIV patients taking

treatment at the selected district hospital during the data collection

period

An element is the most fundamental unit about which information is

collected. In the above example, a single HIV patient refers to the element.

In sampling, the population is divided into a number of parts called

sampling units.

Sampling frame Is a list of the eligible participant who meet the

characteristics of the population and are accessible to the researcher. It is

the source or list of all the subjects, objects or elements from which the

sample is drawn. It defines the researchers population of interest. For

3
example, a list of all HIV patients taking treatment at selected district

hospital during the data collection period.

PROBLEMS IN SAMPLING FRAME

Incomplete sampling frame: This sampling frame does not include all the elements in the

population. Such incomplete frames cannot yield representative samples. Example, a list of

under 5 age group children in a specific geographical area may not contain the names of all

the under 5 age group children due to non registration.

Blanks or foreign elements in sampling frame: some sampling frames have blanks or

contains element not relevant to the target population. Example , the list of members in

Trained Nurses Association of a specific state may contain a few members from the other

state.

Duplicate listing: Sometimes elements appear more than once in the sampling frame.

Randomization: Is a procedure which guarantees an equal opportunity to each individual in

the population to be a part of the sample so as to minimize the differences among groups by

equally distributing them based on certain characteristics.

Representativeness: Means the sample must be similar to the population, As the

representative sample reflects the characteristics of the population , it allows the sample

findings to be generalised to the population.

SOURCES AND AVAILABILITY OF SAMPLING FRAMES

1. Depends on the delimited population as specified by the research design

Examples: membership lists of social groupings, work rosters of organizations that contain

the names of persons who fit the delimited population

4
2. Information about the sampling units are preferable to those that contain

simply names and addresses

a. Permits comparison of subjects who cooperated with those who chose

not to cooperate

b. Sheds light on the possibility of sampling bias introduced by noncooperation and the extent

to which the sample drawn is representative of the larger frame.

STYLES OF SAMPLING

1. Simple random sampling

a. Basic approach upon which statistical significance testing and the assessment of

confidence intervals are based

b. Tests of statistical significance (e.g., the Mest, the F-test or chi square) indicate how

frequently the results obtained from a study occur by chance .

c. Based on sample statistics, a confidence interval indicates the range of scores within which

the true population value most probably falls.

d. Proper technique assures that all subjects in a sampling frame have an equal chance of

being selected

e. Every unit is assigned a number

f. From a table of random numbers, subject IDs are selected until the desired number of units

is reached

5
2. Systematic sampling

a. Every nth subject is taken from an unnumbered sampling frame until the desired quantity

of subjects is selected.

b. Unacceptable if there are repeated patterns in the listing (e.g., names listed on each page

are rank ordered in some way).

c. Economical in terms of time

3. Stratified sampling

Assures inclusion of certain characteristics of a sample and/or exclusion of others. Useful

when the researcher wants to include certain characteristics in the sample in proportion to

their presence in the larger population or disproportionately. Example: If only males are to be

studied, a sampling frame also containing females would have to be stratified according to

gender and then limited to the selection of males only. If the males and females were to be

compared, even though the researcher is sampling from a frame of elderly bedridden patients

(usually composed of more females than males), then a disproportionately larger number of

males and disproportionately smaller number of females would have to be selected in order to

have an equal number of both sexes. If one were interested in certain matters related to the

overall population of elderly, bedridden patients, then after stratifying according to gender,

males and females would have to be selected in numbers proportionate to their presence in

the larger elderly population. The selection within each stratum could be accomplished either

by simple random sampling or systematically if the available list were in an unbiased form

(e.g., alphabetical).

6
4. Cluster sampling

Used when there is an absence of an adequate frame for subjects. Example: In studying

hospital nurses, one might have a list of hospitals in a certain area, but not the nurses within

them. One way, therefore, to select nurses would be to select a few hospitals and then study

all the nurses within them. Another would be to select hospitals, then floors within them, then

study all the nurses on the selected floors.

5. Quota sampling

Useful when the research involves face-to-face interviews requiring the specification of a

number of persons possessing particular characteristics (e.g., 20 females under 30 years of

age who jog, 10 males over 40 who smoke, and when there is no clear sampling frame but a

physical place where subjects can be located. Example: Interview of patients attending a

particular clinic.

6. Snowball sampling

Useful in situations where no actual sampling frame exists, and when few desired subjects

are known. The investigator starts with the few known subjects and from them attempts to

connect with still others of the same kind until the desired sample size is reached

7. Convenience sampling

Uses whatever cooperative subjects are easily at hand because of the way the subjects were

selected, their representativeness is in question. Sample size and methods to determine the

minimum needed

7
GENERAL RULES

a. For survey and correlational research, draw as large a sample as is financially possible,

within certain limits

b. Generally, sample sizes larger than 1,000 to 1,200 subjects from populations of over

100,000 are unnecessary, as the increased accuracy of the statistics gained from larger

samples does not justify the larger numbers and costs

c. Samples smaller than 200 or 300 subjects usually lead to confidence intervals that are too

wide to be satisfying and also limit the kinds of subsample analyses that may be necessary

METHODS TO DETERMINE SAMPLE SIZE

a. Power analysis if

— The effect size can be specified

— Some judgment about sample variances can be made

b. Standard error formulas if

— The researcher wants to be 95% sure that the true percentage or correlation falls within a

limited range of plus or minus a few percentage points or correlational points.

c. Rules of thumb

— Informal standards that over time have come to be accepted by professionals in various

fields but typically are not easily traced back to their original sources

Example: — 20 to 30 subjects for each independent variable if the fundamental statistical

analysis is to be multiple regression

— a minimum of 5 subjects for each item if factor analyses are to be done

8
d. Other factors

— The greater the homogeneity of the population, the smaller the size of the sample needed

— If the study is theory building, a smaller sample is required than if the purpose is theory

testing or descriptive of a large population

— The more variables and delimitations, the greater the need for larger numbers as

comparisons of subgroups and combinations of variables necessitate larger numbers

— If a sampling frame contains a large number of subjects who are no longer available, then

a much larger number will be needed in order to reach the minimal size originally calculated

GENERAL SAMPLING SUGGESTIONS (QUANTITATIVE)

A. Know as much as possible about the population and sampling frame.

B. Find and use a sampling frame that is representative or clearly heuristic, given the research

interest, that has more than names and addresses associated with it.

C. Use sound sampling procedures (e.g., stratified random sampling).

D. Within limits, draw as large a sample as is technically and financially feasible.

E. Use follow-up procedures to achieve as high a return rate of questionnaires as possible or

to gain the cooperation of phone or in-person interviewees.

SAMPLING (QUALITATIVE DESIGNS)

A. Qualitative research approaches often utilize small samples and emphasize depth versus

breadth. The researcher is attempting to obtain understanding through an in-depth,

information-rich, and detailed exploration of the phenomenon, group, or person.

B. The sample is chosen purposively versus randomly or by convenience.

9
C. The sample refers to the unit(s) of analysis to be explored such as an individual, a group, a

culture, an organization or agency, an event or occurrence, a process, or a particular

phenomenon that people experience.

D. The sampling process necessitates an emphasis both on what to sample and how to

sample.

E. "The 'what' to sample may include events, places, persons, artefacts, activity, and time"

(Kuzel, 1992, p. 34).

F. The "how" to sample includes determining which of the various purposive sampling

strategies to use.

1. Extreme or deviant case—highly unusual case

2. Intensity sampling—manifest phenomenon intensely (e.g., above/below average)

3. Maximum variation sampling—purposefully choosing a wide range of variation on

dimensions of interest

4. Homogeneous sampling—focused, reduced variation

5. Typical case—highlights normal, average

6. Stratified purposeful sampling—particular subgroup of the population

7. Critical case—if true of this case, likely to be true of all other cases

8. Snowball or chain sampling—identify cases from people who know people etc.

9. Criterion sampling—cases that meet some criterion

10. Theory-based sampling—manifestation of a theoretical concept

10
11. Confirming and disconfirming cases—seeking exceptions, testing variations

12. Opportunistic sampling—following new or unexpected leads

13. Random purposeful sampling (still small sample size)—random within a

purposeful category

14. Combination or mixed purposeful sampling—based on triangulation, multiple needs

(Patton, 1990, pp. 182-183)

G. Theoretical sampling is used to generate grounded theory where the researcher decides on

theoretical/analytic grounds what data to collect next and where to find them. What groups or

subgroups of populations, events, activities (to find varying dimensions, strategies, etc.) does

one turn to next in data collection? And for what theoretical purpose? The process of data

collection is controlled by the emerging theory (Strauss and Corbin, 1998)

H. The researcher continues to sample individuals, events, situations, and/or setting to the

point of redundancy or saturation where no new or disconfirming information or evidence is

found.

ADVANTAGES OF SAMPLING

Sampling ensures convenience, collection of intensive and exhaustive data, suitability in

limited resources and better rapport. In addition to this, sampling has the following

advantages also.

11
1. Low cost of sampling

If data were to be collected for the entire population, the cost will be quite high. A sample is a

small proportion of a population. So, the cost will be lower if data is collected for a sample of

population which is a big advantage.

2. Less time consuming in sampling

Use of sampling takes less time also. It consumes less time than census technique.

Tabulation, analysis etc., take much less time in the case of a sample than in the case of a

population.

3. Scope of sampling is high

The investigator is concerned with the generalization of data. To study a whole population in

order to arrive at generalizations would be impractical.

Some populations are so large that their characteristics could not be measured. Before the

measurement has been completed, the population would have changed. But the process of

sampling makes it possible to arrive at generalizations by studying the variables within a

relatively small proportion of the population.

4. Accuracy of data is high

Having drawn a sample and computed the desired descriptive statistics, it is possible to

determine the stability of the obtained sample value. A sample represents the population from

which it is drawn. It permits a high degree of accuracy due to a limited area of operations.

Moreover, careful execution of field work is possible. Ultimately, the results of sampling

studies turn out to be sufficiently accurate.

12
5. Organization of convenience

Organizational problems involved in sampling are very few. Since sample is of a small size,

vast facilities are not required. Sampling is therefore economical in respect of resources.

Study of samples involves less space and equipment.

6. Intensive and exhaustive data

In sample studies, measurements or observations are made of a limited number. So, intensive

and exhaustive data are collected.

7. Suitable in limited resources

The resources available within an organization may be limited. Studying the entire universe is

not viable. The population can be satisfactorily covered through sampling. Where limited

resources exist, use of sampling is an appropriate strategy while conducting marketing

research.

8. Better rapport

An effective research study requires a good rapport between the researcher and the

respondents. When the population of the study is large, the problem of rapport arises. But

manageable samples permit the researcher to establish adequate rapport with the respondents.

DISADVANTAGES OF SAMPLING

The reliability of the sample depends upon the appropriateness of the sampling method used.

The purpose of sampling theory is to make sampling more efficient. But the real difficulties

lie in selection, estimation and administration of samples.

Disadvantages of sampling may be discussed under the heads:

13
Difficulties in selecting truly a representative sample

 Chances of bias

 Need for subject specific knowledge

 Changeability of sampling units

 Impossibility of sampling.

1. Chances of bias

The serious limitation of the sampling method is that it involves biased selection and thereby

leads us to draw erroneous conclusions. Bias arises when the method of selection of sample

employed is faulty. Relative small samples properly selected may be much more reliable than

large samples poorly selected.

2. Difficulties in selecting a truly representative sample

Difficulties in selecting a truly representative sample produce reliable and accurate results

only when they are representative of the whole group. Selection of a truly representative

sample is difficult when the phenomena under study are of a complex nature. Selecting good

samples is difficult.

3. Inadequate knowledge in the subject

Use of sampling method requires adequate subject specific knowledge in sampling technique.

Sampling involves statistical analysis and calculation of probable error. When the researcher

lacks specialized knowledge in sampling, he may commit serious mistakes. Consequently, the

results of the study will be misleading.

14
 CONCLUSION

Regardless of the research approach taken, adequacy and appropriateness of the sample are

essential components of research design. It is equally essential that these processes are

described for consumers of research, both to de-mystify the steps involved and, more

importantly, to allow the reader to judge the credibility of the findings (Selby et al., 1990).

All decisions made by the researcher about sample size should be made explicit and the steps

taken to control bias should be described.

15
 REFERENCES

 Altman, D.G., 1980. Statistics and ethics in medical research III. How large a sample?

Brit. Med. J 281, 1336–1338.

 Botti, M., Williamson, B., Steen, K., McTaggart, J., Reid, E., 1998. The effect of

pressure bandaging on complications and comfort in patients undergoing coronary

angiography: a multicenter randomized trial. Heart Lung: J. Acute Crit. Care 27, 360–

373.

 Endacott, R., 2004. Clinical research 1: research questions and design. Intense. Crit.

Care Nursing. 20 (4), 232–235.

 Kuzel, A.J., 1999. Sampling in qualitative inquiry. In: Crabtree, B.F., Miller, W.L.

(Eds.), Doing Qualitative Research, second ed. Sage, Thousand Oaks.

 LoBiondo-Wood, G., Haber, J., 2004. Nursing Research: Methods, Critical Appraisal

and Utilisation, third ed. Mosby, St Louis

16