CHAPTER 1: SAMPLING AND SAMPLING DISTRUBUTION

5.1 Basic definitions

A subset of the population selected for the study is known as sample. The group from which the
samples are selected is called Universe or Population.

Sample survey: is a procedure, which makes one able to draw inferences about the population by
observing or measuring few items.

5.2 Objectives of sampling are:

1- To obtain maximum information about the characteristics of the population with less time,
energy and expenditure
2- To obtain the best possible values of parameter.

Sampling refers to the method of selecting a sample from the universe. A proper procedure is to be
adopted for evaluating the sample plan in order to select representative units of the universe.
Sampling occupies a key role in the study and has acquired the status of a technical job.

The number of units in the sample is called Sample size.

* Sample size should never be too small nor too large but optimum. Optimum fulfills the needs of
efficiency, representativeness, reliability and validity.

The size of sample for a study is determined on the basis of the following factors
i- the size of the population
ii- the availability of resources
iii- the degree of accuracy
iv- the homogeneity or heterogeneity of the population
v- the nature of the study
vi- the method of sampling technique adopted
vii- the nature of respondents
5.3 WHY SAMPLING

It is often not feasible to study the entire population. The following are some of the major reasons
why sampling is necessary

5.3.1 The Destructive Nature of Certain Testes

Statistics for mgt(II) lecture note by Meharu. Sep. 2023 edited Page 1
Many experiments especially in quality control demand destructing outputs. Consider the following
tests:
- Testing wine or coffee
- Blood test for a patient
- Testing strength of light bulbs
- Seed test for germination etc.

Unless sample is taken from the entire population the wine tester should drink all the wine, all the
blood from the patient should be poured-out, all the light bulbs produced should be destroyed and
nothing would remain for sale. Here sample is a must.

5.3.2 The Physical Impossibility of checking all Items in the Population

The populations of fish, birds and other wild lives are large and are constantly moving being born and
dying. There is no mechanism to contact all items or individual members of the population.
5.3.3 The Cost of studying all the Items in a Population is Often Prohibitive

Public opinion polls and consumer testing organizations usually contact fewer families out of
millions. Consider a multinational corporation with 50 million customers worldwide. If this company
plans to undertake market survey out of the 50 million it will take 2000 samples, if it takes 20 br. to
mail samples and tabulate the responses of 2000 samples, total survey will cost Br. 40000. While the
same survey involving 50 million populations would cost about one billion br.
5.3.4 The Adequacy of Sample Results

Even if funds were available, it is doubtful whether the additional accuracy of 100% sample i.e.,
studying the entire population is essential in most problems. To determine monthly index of food
prices, bread, beans, milk etc, it is unlikely that the inclusion of all grocery stores and shops would
significantly affect the index, Since, the prices of such commodities usually do not vary by more than
a few cents form one store to another. 100% accuracy cannot be all ways guaranteed by studying the
entire population. The chance of error in collecting and analyzing bulk data has its own disadvantage.

Statistics for mgt(II) lecture note by Meharu. Sep. 2023 edited Page 2
4.3.5 To Contact the Whole Population would often be Time Consuming

A market survey may take two or three days for field interviews by taking a sample of 2000
customers. By using the same staff and interviewers and working seven days a week it would take
nearly 200 years to contact 50 million customers.

5.4 ERRORS

Avery important consideration in sampling is to select the sample in such a way that it is very likely
to have characteristics similar to the population as a whole. Otherwise, the sample could have
characteristics quite different form the population. In that case you could draw erroneous conclusions
about the population on the basis of improperly chosen sample. Error can be sampling or non-
sampling error.

Sampling error is related with the sampling technique and approaches .while non-sampling error is
related with administering the survey.
Sampling errors can be identified and rectified using some mathematical techniques.
While the non-sampling errors are very difficult to identify and rectify before making conclusions.

Inferential statistics is a systematic method of inferring satisfactory conclusions about the population
on the basis of examining a few representative units termed as sample. The process of selecting
samples is called sampling. Generalization of the sample data results to the population, which is one
of the characteristic features of research, needs scientific approach of searching for facts. Therefore,
sampling must be scientific.

5.5 ADVANTAGES AND DISADVANTAGES OF SAMPLE SURVEY

If the sample is drawn on scientific approach, the adopted sample design is good and the sample size
is adequate. Sample method has some merits over the census method. That are:
1- Sampling saves time and money.
2- It is much convenient as it involves less personal staff.
3- It is useful when population is infinitely large.
4- It can be more accurately supervised and data can be carefully selected.

Statistics for mgt(II) lecture note by Meharu. Sep. 2023 edited Page 3
 5- It is useful in case of inspecting the quality of units, which we have to resort to sampling, such
as testing the quality of bulbs, tubes, strength of stencils, testing explosives, etc.
Sampling method has its limitations and problems, which are:
1- It would give unreliable data if not designed and executed carefully. Samples are like
medicines. They can be harmful if taken carelessly or without knowledge of their effect.
2- The service of skilled, trained, qualified personnel for supervision; and sophisticated
equipment and statistical techniques are required. In the absence of these, it may not be
reliable.
3- Sample survey is not useful when information is needed about each and every unit of the
population.
5.6 TYPES OF SAMPLING TECHNIQUES

Sampling technique refers to the method of selecting a sample from the universe (population). It
occupies a key role in a study and has acquired the status of being a technical job. The right type of
sampling technique is of paramount importance in the execution of a sample survey in accordance
with the objectives and the scope of the inquiry. The sampling methods may broadly be classified as:

1- Probability sampling (simple, stratified, & systematic)

2- Non-probability sampling (judgment, convenient, quota, incidental, purposive, self-
selected, etc.)
3- Mixed sampling (cluster sampling)

5.6.1 RANDOM (PROBABILITY) SAMPLING

Random sampling method is a method of selection of a sample such that each item within the
population has equal chance of being selected.

In this method, there is no place for investigator’s bias in sample selection since it depends on
probability. It provides more accurate estimates in the sense of greater precision.

I. Simple Random Sampling Method (SRSM): involves very simple method of drawing a sample
from a given population. The selection of samples is random in character.
The oldest method adopted in simple RS is the use of lottery system.

Statistics for mgt(II) lecture note by Meharu. Sep. 2023 edited Page 4
Suppose population size is 100 and sample size is 10. i.e. N = 100 and n = 10. Hundred chits would
be prepared bearing the serial number of units in the universe. These chits would be put together and
shuffled thoroughly, and then ten would be drawn one by one. The sampling units corresponding to
the number on the selected chits will form a random sample. This method gives a sample, which is
quite independent of the natures of universe. This method is commonly in practice even at present.
The other most practical and inexpensive method is the method of “Random Number Tables” (RNT).
If we have to select a sample of size n from a universe of size N less than 9, then the numbers can be
paired as 0 to 9.If we have to select a sample of size n from a universe of size N less than 99, then the
RNT will be from 00 to 99.If N is less than 999, then from 000 to 999 and so on.

Then, select any K from the RNT and if K  N, the kth unit will be selected as a sample and if K > N,
divide K by N and take the remainder or the R thunit as a sample. This process continues till n number
of samples are selected.

Example: From 40 big enterprises in Addis Ababa, we want to study the case of only 5 of them. Let
12, 59, 67, 81 and 97 be the numbers selected from the RNT. Then which of the items of the
population are selected for the sample.

Solution: N = 40, n = 5, K = 12, 59, 67, 81, 97.

Since N = 40 is a two digited number, the RNT will be from 00 to 99.
K = 12 < N  The 12th item is selected for the sample.
K = 59 > N  59  40 = 1 + 19/40 The 19th item is selected.
K = 67 > N  67  40 = 1 + 27/40 The 27th item is selected
K = 81 > N  81 40 = 2 + 1/40 The 1st item is selected
K = 97 > N  97  40 = 2 + 17/40 The 17th item is selected
The 1st, 12th, 17th, 19th and 27th items are selected for the ‘study’.

II Stratified Random Sampling Method (STRSM)

Under this method, the whole population is divided into a number of homogeneous groups or strata.
From each of these strata, random sample of size n is selected. Thus, stratified RS means selecting a
number of random samples, one from each stratum of the universe. It is used when each group has
small variation within itself but wide variation between the groups.

Statistics for mgt(II) lecture note by Meharu. Sep. 2023 edited Page 5
The sample may be either proportionate or disproportionate. Suppose the universe is divided into two
groups consisting of 100 and 160 respectively and their respective sample sizes being 10 % of the
universe. Meaning a sample of size 10 + 16 = 26 is drawn in proportion to the total number of items.
But in disproportionate stratified RSM, samples are taken from each stratum regardless of the number
of units in the universe. Thus in the above example, an equal number of units i.e. 12 from each
stratum may be drawn in which the total number of items in the sample is 24.
- The size of sample items which must be selected from the ith stratum is denoted by ni and is given by

nN i Where n – total Sample size

ni = N – total Population size

N
Ni - population of the stratum

ni -sample of the stratum

Example: In unity University College a survey is to be conducted on 120 students’ tendency towards
Mathematics. The total number of students in each field is as indicated below. Give the sample size of
each field of study.

Ni N1 N2 N3 N4 N5
Field of study Accounting Business Law Marketing Architecture
No. of students 3000 2000 1500 2500 1000

Solution: n = 120
N1 = 3000, N2 = 2000, N3 = 1500, N4 = 2500, N5 = 1000
N = N 1 + N2 + N3 + N4 + N5 = 10,000Then,

nN 1
120 x 3000 nN 2 12
n1 = = = 36 n2 = = x 2000 = 24
N 10,000 N 1000

Statistics for mgt(II) lecture note by Meharu. Sep. 2023 edited Page 6
 n 120 n
n1 = , N1 = x 3000 = 36 i.e. = 0.012
Or N 10,000 N
12 12 12
n3 = x 1500 = 18 , n 4 = x 2500 = 30 , n5 = x
1000 1000 1000
III. Systematic Random Sampling Method (SYRSM)

In this method, a random starting point is selected from the list representing the universe and the
remaining units are automatically selected in a definite sequence at an equal spacing from one
another. This method is recommended if the sample units are arranged in systematic order such as
chronological, geographical, alphabetical, etc. and also if the sample units in the universe are
uniquely identified. Systematic sampling is also called sampling by regular intervals or sampling by
fixed intervals.

- To get a systematic sample of size n from a population of size N, draw a random number i from 1 to

N
K, where K =
n , and then select i, i + K, i + 2K, i + 3K, …
Ai = A1 + (i – 1) K. Where A1 – the random starting point or the first sample item.
Ai – the ith item in the sample

Example 1: - From the files of 24 cases of the federal high court, the cases of only 4 of these is to be
seen. The fifth file was selected randomly. Indicate the remaining three elements of the sample.

Solution: - N = 24 , n = 4 , A1 = 5

N 24
= = 6
K=
n 4
Then A2 = A1 + (2 – 1) K
= A1 + K = 5 + 6 = 11. The 11th file is the second element

Statistics for mgt(II) lecture note by Meharu. Sep. 2023 edited Page 7
 A3 = A1 + (3 – 1) K
= A1 + 2K = 5 + 2 (6) = 17. The 17th file is the third element.
A4 = A1 + (4 – 1) K
= A1 + 3K = 5 + 3 (6) = 23. The 23rd file is the fourth element.

Example 2: - If the 4th and 12th elements of a systematic sample are 70 and 126 (in the population)
respectively, then which item of the population is the first element of this systematic sample.

Solution: - A4 = 70, A12 = 126, A1 =?

A4 = 70 = A1 + 3K taking these two simultaneous equations,
A12 = 126 = A1 + 11K
56 = 8K K = 7
Then A4= A1 + 3K
70 = A1 + 3(7)
 A1 = 70 – 21 = 49
The 49th item of the population is the random starting point for the systematic samples.

5.6.2 NON-RANDOM (NON-PROBABILITY) SAMPLING METHOD

In this method, the chance of including any elementary unit of the population in the sample cannot be
determined. It is simple to adopt and no complicated procedure is needed to draw a sample.

There are many non-random sampling techniques. Some of which are Judgment, Convenient and
Quota sampling.

Judgment Sampling: - The exercise of good perception and appropriate strategy are taken into
account. Samples are selected deliberately by the investigator. It is a personal view. So it becomes
satisfactory with regards to one’s research needs. For example, if a sample of 10 students is to be
singled out from a class of 50 for analyzing the habits of students, the investigator would select ten
students, who in his opinion are representative of the class.

Convenient Sampling: - Elements of the sample are selected by taking those elements of the
population, which are readily available or convenient for the investigator.

Example: Asking people form one area.

Statistics for mgt(II) lecture note by Meharu. Sep. 2023 edited Page 8
 Quota sampling: - In this technique, quota is set up according to given criteria, but the sample with
in prescribed quota is selected by personal judgment of the investigator. It is suitable in market and
public opinion surveys where stratification is very difficult. However, it suffers from representivness
as the interviewer may select samples convenient for him with regards to location and sample unit.

It is the combination of judgment and stratified sampling methods. so it enjoys the merits of both .

Example: - If we ask about Canada dry for a prescribed quota of 20 households, 15 students and 10
children, then this method is quota sampling.

5.6.3 MIXED SAMPLING METHOD (CLUSTER SAMPLING)

Groups of items (clusters), homogenous in character, are formed on location or class basis. Here a
sample of cluster is selected and next within cluster, sub groups are identified for inclusion in the
sample. It is also known as Area sampling as selection of units is made on the basis of place. The
clusters may or may not be equal in size. The smaller the size of the cluster, the greater will be the
accuracy. It is economical and much easier.

Example: - Suppose a survey is conducted about students’ capacity in auditing. From 10 colleges in
Addis Ababa if college X is selected and from 50 classes of college X if 6 classes are selected
randomly and considered for the study, then this technique is cluster sampling.

EX.1 A researcher used a random number table ranging from 000 to 999 and selected 85, 199, 350, 740 and
960 randomly. If the total number of observations is 120, which items should be included in the
sample.

Ex. 2 A stratified sample is going to be selected from four fields of study in Arat Kilo University. The
number of students in Mathematics, Statistics, Biology and Chemistry is 200, 360, 400 and 480
respectively. I f the ratio of population size to that of sample size is 40, how large a sample must be
taken from each of the four fields of study.

EX. 3 If the 3rd and 5th items of a systematic sample are 21 and 37 (in population) and if there are 8 items in
the sample, then
a – Give the remaining items in the sample.
b – Find the total number of items in the population.

Statistics for mgt(II) lecture note by Meharu. Sep. 2023 edited Page 9