Sampling is fundamental to all statistical methodology of behavioural and ng social research.
Bad sampling vitiates the data at the source. No amount of subsequent statistical findings
will improve its quality Sampling is the part of the strategy of research. It has acquired the
status of technical job.
DEFINITIONS OF SAMPLING
1. W. G. Cocharn. "In every branch of science we lack the resources, to study more than a
fragment of the phenomena that might advance our no knowledge" In this definition a
'fragment is the sample and 'phenomena is the population The sample observations are
applied to the phenomena, ie, es generalization
2. David S. Fox. "In the social sciences, it is not possible to collect data ve from every
respondent relevant to our study but only from some fractional part of the respondents. The
process of selecting the fractional part is called sampling" Sampling design' means the joint
procedure of selection and estimation Sampling should be such that error of estimation is
minimum.
Characteristics of A good Sample
1. True Representative. A good sample is the true representative of the population
corresponding to its properties. The population is known an aggregate of certain properties
and sample is called sub-aggregate of the universe
2. Free from Bias. A good sample is free from bias. It does not permit prejudices,
pre-conceptions and imaginations to influence its choice.
3. Objective. A good sample is an objective one. It refers to objectivity in selecting
procedure or absence of subjective elements from the situation.
4. Accurate. A good sample maintains accuracy. It yields accurate estimates or statistics and
does not involve errors.
5. Comprehensive. A good sample is comprehensive in nature. This is closely linked with
true-representativeness. A comprehensive sample is controlled by specific purpose of the
investigation. A sample may be comprehensive in traits but may not be a good
representative of the population.
6. Economical. A good sample is economical from energy, time and money point of view.
7. Approachable. The subject of good sample are easily approachable. The research tools
can be easily administered on them and data can be easily collected.
8. Good Size. The size of good sample is such that it yields an accurate result. The
probability of error can be estimated.
9. Feasible. A good sample makes the research work more feasible.
10. Practical. A good sample has the practicability for research situation
CONSIDERATIONS IN DETERMINING SAMPLE SIZE
Several factors can influence the size of the sample used in a research study, but with the
exception of cost, information about such factors is often incomplete and it becomes difficult
to set an exact size. Cost refers not only to the expenditure of money but also to the time
and effort required to obtain the sample data. In any survey, the actual cost of obtaining the
data in the sample should be estimated as accurately as possible. If standardized tests are
used what is the cost per test? How much does it cost to score the tests and summarize the
data? What, if any, costs will be encountered in locating the sample for testing? What is the
cost of test administration? These are all examples of questions that can be raised. A
searcher who is securing funds for a project from a funding agency usually is required to
produce quite accurate cost estimates. Researchers who are university professors (and poly
graduate students) often receive funds from a funding agency or from a source within the
university, thus, cost estimates are required. Even in the rare instances when facilities and
sources are available through a university at no hard-dollar costs, costs of proposed project
should be estimated at least time and effort estimates should be made.
Sample size is also related to statistical concepts when quantitative data are [Link]
hypotheses are often tested by statistical procedures. One concept is statistical precision
which deals with the magnitude of differences between statistics necessary attain statistical
significance. Another concept is the power of a statistical test, which is defined as the
probability of rejecting a false hypothesis. Generally, we want adequate statis tical precision
so that we are testing hypotheses with confidence.
Another concept is effect size. Effect size concerns the magnitude of an effect that may be
present in a relationship or in a difference between two or more groups. For example, the
difference between an experimental and control group may be expressed as an effect [Link]
a researcher designates a meaningful effect size, sample size can be estimated given the
power of the statistical test and the significance [Link] factors must be considered
simultaneously, but if enough prior information is available, sample size can be estimated for
a desired level of statistical precision. Prior information weld clade knowledge about the
variability of the dependent variable. Hinkle and Oliver (198) discuss estimating necessary
sample size given certain characteristics
Generally, increasing sample size enhances statistical precision. For example, whe polling
agencies estimate the proportions or percentages of votes candidates for office w receive, a
certain level of precision can be specified (such as 3 percent error) and sa size determined.
If the election is close and the polling agency wants to be 95 percen fidest that the estimate
for the percentage of a candidate's vote is within 3 percenta sample of about 170 is
necessary. It a greater percentage of error can be tolera smaller sample may be selected. If
very little error is desired, such as 1 percent, al sample is necessary. The greater the
variability of a dependent variable, the larger sample required for a specified level of
statistical power or effect size The general procedure for determining sample size involves
the following p