Basics of Sampling.
Let us first know what Sampling is.
Sampling, is the process of selecting a few (a sample) from a larger group (the
sample population). This will become the basis for estimating the occurrence of an
unknown situation, problem or outcome in relation to the larger group.
A sample is therefore a subset of the population you are interested in. This
selection process a sample from the total population has advantages and
disadvantages.
The benefits are obvious as you select a small group of people saving you time and
costs; but the downside is that will not have the whole picture of what the entire
population thinks or perceives. Hence, there is a possibility of errors in your
estimate.
Sampling is therefore a trade-off between certain advantages and disadvantages.
While on the one hand you save time and resources,on the other hand, you may
compromise the accuracy of your findings.
By sampling you only estimate the actual situation that is widespread in the total
population from which the sample comes is signed. If you determine a certain data
from the total sample population,and if your method of research is correct, your
findings should be reasonably accurate.
However, if you select an example and use it as a basis for estimating it situation
in the total population, an error is possible.
Tolerance of this possibility of error is an important consideration when selecting
a sample.
If you pick 100 people out of 1000 people you might get an estimate of what 1000
people might think that do not represent all the thoughts of 1000 people.
We can take an example: job satisfaction among public sector employees in Germany.
If you look at the number of people who work German public sector - the number is a
staggering 13 million or 16% of Germany's total population.
All 13 million people for your research will be very time-consuming and cost-
effective.
Therefore, your best bet is to select an appropriate sample of 13 million
residents.
Or you can do it by location - Munich, Berlin or Frankfurt or by department -
Interior, Finance, Defense etc.
There are a number of terminologies used in sampling. Let's take a quick look at
them. So as our example of research, job satisfaction is under public sector
employees in Germany, the sample population or study population is the total
population - that is 13 million.
Sample or Sample size is the selected one denoted by n; we will find out how many
samples we will need.
Sampling design - that is how sample is selected (the techniques to select sample
from 13 million)
Sampling unit - each employee is a unit. 13 million public sector employees are 13
million sampling units.
Sample statistics - the findings you collect from your sample are sample
statistics.
Sampling consideration - There are two things to consider when sampling.
1) The size of the sample - Findings based on larger samples are more confident
than those based on smaller ones. As a rule, the larger the sample size, the more
accurate the findings.
2. The degree of variation in the sample population The greater the variation in
the study population, for a given sample size, the greater the uncertainty. So if
you have a large group of people thinking differently, then you have that in your
data collection a number of variations in the answers. That will increase your
insecurity.
If a population is homogeneous (uniform or similar) with respect to the
characteristics being studied, a small sample size can be a fairly good estimate;
but if the sample is heterogeneous (dissimilar or varied) you must select a larger
sample to obtain the same accuracy. Of course, if all elements in a population are
identical,
then the selection of even one sample will provide an absolutely accurate estimate.
For example, if you want to know what the average is of employees in an
organization and in that organization everyone earns $30000.
If you survey just one employee, anyway you will get the average salary as 30000.
(The same can be applied everywhere: one employee's perception can represent the
entire group because they are all identical!!).
