3.

0 POPULATION AND SAMPLE

3.1a Population.
A population refers to any collection of specified groups of human beings or non-human entities
such as objects, educational institutions, time units, geographical areas, prices of wheat, or salaries
drawn by individuals. Some statisticians call it the universe. A population containing a finite
number of individuals, members, or units is a class. A population with an infinite number of
members is known as an infinite population. The population of pressures at various atmospheric
points is an example of an infinite population. The population of concrete individuals is called an
existent population, while the collection of all possible ways in which an event can materialize as
the hypothetical population. All the 400 students of the 10th class of a particular school are an
example of an existent type of population and the population of heads and tails obtained by tossing
a coin an infinite number of times is an example of a hypothetical population. The population is
properly defined so that there is no ambiguity as to whether a given unit belongs to the population.
For example, in a survey of achievement in mathematics, a researcher will have to define the
population of students by age or by grade, and, if necessary, he will also specify the type of schools,
the geographical area, and the academic year for which the data will be collected. Inferences
concerning a population cannot be drawn until the nature of the units that comprise it is identified.
If a population is not properly defined, a researcher does not know what units to consider when
selecting the sample.

3.1b Census
This refers to the total counting (enumeration) of the objects making a population in which one is
interested. Thus, population census refers to the counting of the human population which is of
great importance, especially to government users. A census can be either a Defacto or Dejure
count.

3.1c Sample.
A selected group of some elements from the totality of the population is known as the sample. It
is from the study of this sample that something is known and said about the whole population. The
assumption is that what is revealed about the sample will be true about the population as a whole.
But it may not be true always as it depends on the way the sample is drawn. If the sample is a

1
replica of the population, the foregoing assumption is true. But, if it is biased, such inferences
about the population cannot be true. A biased sample is one that is selected in such a way that it
yields a sample value which is much different from the true or population value. Hence it is basic
requirement for inferential research that the sample should be free from bias. In other words, it
should be representative of the population. A representative sample is a sample which has all those
characteristics present in the same amount or intensity in which they are found in the population.
Bias in selecting a sample can be avoided and it can be made representative of the population by
selecting it randomly. A random sample involves small errors in predicting population value and
this error can be estimated also. Thus the objective should always be to draw an unbiased random
and representative sample. In order to draw such a representative sample, a sample plan has to be
prepared. It means a plan which, if properly executed can guarantee that if we were to repeat a
study on a number of different samples each of a particular size drawn from a given population,
our findings would not differ from the findings that we would get if the given population as a
whole was studied by more than specified proportions of the sample. For example, not more than
5 points in 90% of the samples, that is, out of 100 samples the sample value (estimate of value)
will be correct within 5 points in 90 out of 100 samples. If the plan guarantees sufficiently well
that the chances are great enough that the selected sample is representative of the population, it is
known as a representative sampling plan. It ensures the selection of diverse elements and makes
sure that these diverse elements are adequately represented in the sample.

3.1c Frame
This is the complete list of all members of the population to be surveyed or the list of all the
population units from which the sample units are to be identified. Such a complete list is termed a
SAMPLING PFRAME. The sampling frame is highly essential to select a truly random sample.
Examples:
1. Voters register which contains the particulars of eligible voters
2. The list of Taxpayers

3.1d Sampling.
It is the process of selecting a sample from the population. For this purpose, the population is
divided into several parts called sampling units. Most of the educational phenomena consist of a

2
large number of units. It would be impracticable, if not possible to test interview, or observe each
unit of the population under controlled conditions to arrive at principles having universal validity.
Some populations are so large that their study would be expensive in terms of time, effort, money,
and manpower. Sampling is a process by which a relatively small number of individuals or
measures of objects or events is selected and analyzed in order to find out something about the
entire population from which it was selected. It helps to reduce expenditure, save time and energy,
permit measurement of greater scope, and produce greater precision and accuracy.

3.2 PROBABILITY AND NON-PROBABILITY METHODS

The various methods of sampling can be grouped under two broad heads:
1 Probability sampling and
2 Non-probability sampling

3.1 Probability sampling:- methods are those in which every item in the population has a known
probability of being chosen. This implies that the selection of sample items is independent of the
person making the study. Such a method is also called RANDOM SAMPLING.

Characteristics.
1. Each unit in the sample has some known probability of entering the sample.
2. Weights appropriate to the probabilities are used in the analysis of the sample.
3. Its observations are used for inferential purposes.
4. Inferential or parametric statistics are used.
5. There is risk of drawing conclusions.
6. Its representatives refer to characteristics.
7. Its comprehensiveness refers to size and area.

Probability sampling methods are as follows:

1. Simple random sampling
2. Stratified sampling
3. Systematic sampling
4. Cluster sampling

3
 5. Multi-stage sampling

3.2.1 Simple Random Sampling:-This is the simplest sampling design defined as the sampling
design in which every unit in the population has the same probability 1/N of being selected at each
draw. The probability of a unit been selected into sample is also for each unit namely n/N of
appearing in the sample.
N being the size of the population and n that of sample, Random number table can be reached by
a column or row provided the method is consistent.
Selection procedure:
a. Lottery
b. Use of table of random numbers
Advantages
1 It is an equitable method of selection i.e. no personal bias
2 The precision of estimate is the highest of all types of probability sampling methods.

Disadvantages
1 Without a sample frame, selection cannot be done.
2 If the population is larger, it is time-consuming, laborious and expensive.

3.2.2 Stratified Sampling: - This is a procedure of sampling in which the population to be sampled
is first divided into sub-populations called strata (stratum for singular) which are as much
internally homogenous as possible with respect to the variable under study. Selecting a random
sample from each sub-population independently according to some criteria. For instance, selecting
n from N objects. The population can be divided first into strata and then samplings taking from
each stratum. The stratification may be only on one variety as sex or may be more complex e.g.
males, females, ages, social classes, ethnicity area, occupation and education are often used as a
variable for strata.

Advantages
1. More representative
2. Increase in precision of estimate.

4
 3. Provision for reasonable accuracy.
4. More useful in heterogeneous population.
5. The sub population totals are known.

Disadvantages
1. It needs highly trained personnel.
2. Laborious in preparation of sample frame.
3. May be costly if stratified sampling frame are not available.

3.2.3 Systematic Sampling: - This is the method of sampling in which the first unit sample is
selected using random number and the remaining units are automatically selected by a pre-
determined rule.
The selection of a systematic random sample involves the following steps:-
i. Taking population size. N = 30
Sample size n = 10
Sampling fraction = n/N = 10/30 = 1/3
Sampling interval = N/n =30/10 = 3
ii. Select a random start, r(1 ≤ r ≤ K) i.e. which will be the first selected unit in the list of
sampling unit
iii. The other units are selected by successively adding K to the random start.

Advantages
1. Easy to select
2. Preparation of sample frame is not necessary
3. The sample is spread evenly over the entire population
4. When there are not periodic event that are associated with sampling intervals, the result
obtained they are satisfactory.
5. Saves time

Disadvantage

5
 1 If the sampling intervals coincide with any periodic interval, the result will not be a good
representation.
2. Randomness is not maintained, i.e. only the items within the range of the first selection
are given equal chance of selection.

3.2.4 Cluster Sampling: - This is a sampling method where the population is made up of groups
of element like in the case of stratification only that the groups in this case comprises of
heterogeneous elements (i.e. different kind of elements). Each and in the selection procedure a
probability selection procedure is applied to select groups (cluster) from all the groups that make
up the population and study is then been conducted as the selected cluster giving attentions to all
the elements in the selected cluster.

Advantages
1 Less field cost is required.
2 When there is no satisfactory sampling frame, this method can be used.

Disadvantages
1 If unit in the cluster are similar or correlated it is waste of resources.

3.1.5 Multi-stage Sampling: - It is more comprehensive and representative of the population. In

it the primary sample units are inclusive and secondary units are sub-groups within these ultimate
units to be selected which belong to one and only one group. Whenever stratification is done by
the researcher, stages of the population are usually available within a group or population. The
individuals are selected from different stages for constituting the multi-stage sampling.

Advantages.
1. It is a good representative of the population.
2. It is an improvement over the earlier methods.
3. It is an objective procedure of sampling. 4. Its observations may be used for inferential purposes.

Disadvantages.

6
1. It is difficult and complex.
2. It involves errors while considering the primary and secondary stages.
3. It is subjective.

3.3 Non-probability sampling.

There is no way of estimating the probability of each member of the population being included in
the study. The following are types of Non-probability sampling: -
i. Quota sampling
ii. Accidental sampling
iii. Purposive/Judgmental sampling

3.3.1 Quota sampling: - In this technique, the principles that apply are similar to that of
stratify, the difference is not random. Hence the knowledge of strata of the population
such as sex, age, education, etc is used to select sample elements that will be
representative i.e. Quota or proportion is assigned to elements of the population.
Advantages
1 Reduces the cost of selecting samples.
2 Introduces some stratification effect

Disadvantages
1 Introduces bias of the observers’ classification of units.
2 Introduces bias due to non-random selection of units.

3.3.2 Accidental Sampling: - Sometimes it might be difficult for a researcher to sample on a

random basis on the element of the population, this is because some elements on
random might not be reached or available for one reason or the other. An accidental
sampling can be adopted where a researcher can decide, for example, the first ten (10)
people he meets upon entering an organization will be interviewed for his/her research.

3.3.3 Purposive/Judgmental Sampling: - In this type of sampling, the selection procedure is

done on expert devices or some reason which is used as a basis for judging the inclusion

7
of an element in the sample e.g. a survey of the industry. The sample selected for study
is based on the rate of response of such industry in the past such selection procedure is
known as “judgmental”.

Advantages
1 Requires strong assumptions or knowledge of the population and sub-group
selected.
2 Variability and bias of estimates cannot be measured or controlled.

Exercise/Practical
1. Students should select a sample of size ten among their class (say) using various
sampling techniques described above.
2. Why does the sample prefer to population?