Chapter 2

Obtaining Data
METHODS OF DATA COLLECTION
PLANNING & CONDUCTING SURVEYS
PLANNING & CONDUCTING EXPERIMENTS
 There are two types of statistical data
according to their sources. Those
Sources coming from primary sources are
of Data referred to as primary data. Primary
sources include government
agencies, business establishments,
organizations and individuals who
carry original data or who have
firsthand information relevant to a
given problem. Data obtained from
secondary sources like newspapers,
magazines, journals and republished
materials are called secondary data.
 There are several techniques that may
be used in gathering statistical data.
Collection Those involved in marketing studies
of Data usually employ either the interview
method or the questionnaire method
to gather information on consumers’
preference and certain buying habits.
Behavioral scientists who are
engaged in comparative and
correlational studies usually employ a
process of observation while scientific
researches very often resort to
experimentation.
 Makers of feasibility studies utilize
records of data available in various
Collection government agencies like National
of Data Census and Statistics Office, the
Central Bank, the National Economic
and Development Authority and the
different departments of the
government.
 • Interview Method - this is a
Collection person-to-person encounter
of Data between the one soliciting
information (interviewer) and the
one supplying the data
(interviewee). The form of
interview may vary according to
the preference of either or both
parties. It could either be a
personal interview or a telephone
interview.
 • Questionnaire Method - utilizes
Collection questions to obtain information.
of Data They are either mailed or hand-
carried to the intended
respondents. Those who resort to
this method of collecting data
often cite the fact that it is more
economical than interviews and it
can actually involve a greater
number of individuals in the
population with the same amount
of funds.
 • Observation Method – data
Collection pertaining to the behaviors of an
of Data individuals at the time of
occurrence of a given situation are
obtained by direct observation.
Subjects may be observed
individually or collectively
depending on the objectives of the
investigator.
 • Use of Documents - researchers
Collection who make use of vital statistics,
of Data such as number of households,
birth rates, death rates and
marriages find the use of
documents and other existing
records available in both private
and government offices very
economical not only in terms of
cost but also in terms of time and
effort.
 • Method of Experimentation – How
Collection does weather condition affect the
of Data growth of bacteria? Does a
gasoline additive decrease the
gasoline consumption of cars? Is
drug A more effective than drug B
in relieving muscle pains? Data
needed to answer these questions
may be obtained through a series
of experiments.
 In research, we seldom use the entire
Determining population because of the cost and
the Sample time involved. In fact, most

Size researchers do not use the population

in their study. Instead, the sample
which is small representative of a
population is used. The characteristics
of the whole or entire population is
described using the characteristics
observed from the sample.
 To determine the sample size from a
Determining given population, the Slovin’s formula
the Sample is used.

Size

Where:
n = sample size
N = population size
e = margin of error
 Observe that there is a margin of
Determining error. When we use a sample, we do
the Sample not get the actual value but just an

Size estimate of the parameter. Hence,

there is an error when using the
sample.
 It is a procedure used to determine
Sampling the individuals or members of a
Technique sample.

Sampling procedures are used to

answer the question concerning who
will be included in the sample.
Generally, there are two sampling
techniques, the probability and the
non-probability sampling.
 PROBABILITY SAMPLING
Sampling • A sampling technique wherein
Technique each member or element of the
population has an equal chance of
being selected as members of the
sample.

• Probability sampling is a sampling

technique without bias because
selection of members of the
sample is not predetermined.
 There are several probability sampling
Sampling techniques namely:
Technique • Random Sampling - In this
technique, each individual in the
population has an equal chance of
being drawn into the sample.
Selecting the members or
elements of the sample using this
technique can be done using
lottery method or the use of table
of random numbers.
 • Systematic Random Sampling - It
Sampling is a subset of population chosen by
Technique randomly selecting one of the first
k elements and then including
every kth element thereafter.
 • Stratified Random Sampling - The
Sampling word stratified comes from the
Technique root word strata, which means
groups of categories. When we
used this method, we are actually
dividing the elements of
population into different
categories or sub-populations and
then the members of the sample
are drawn or selected
proportionality from each sub-
population.
 • Clustered Random Sampling -
Sampling Cluster sampling is a sampling
Technique technique wherein groups or
clusters instead of individuals are
randomly chosen. In this method,
we will select or draw members of
the sample by group and then we
select a sample of elements from
each cluster or group randomly. It
is sometimes called area sampling
because this is usually applied
when the population is large.
 • Multi-stage Sampling - Multi-stage
sampling is a combination of
Sampling several sampling techniques.
Technique Usually, this method is used by the
researchers who are interested in
studying a very large population.
This is done by starting the
selection of the members of the
sample using cluster sampling
and then dividing each cluster or
group into strata. Then, from each
stratum, individuals are drawn
randomly using simple random
sampling.
 NON- PROBABILITY SAMPLING
• A sampling technique wherein
Sampling members of the sample are drawn
Technique from the population based on the
judgement of the researchers. This
technique lacks objectivity of
selection; hence, it is sometimes
called subjective sampling.
Inferences made based on the
sample obtained using this
technique are not so reliable.
 NON- PROBABILITY SAMPLING
• Non-probability sampling
Sampling techniques are used because they
Technique are convenient and economical.
Researchers use this method
because they are inexpensive and
easy to conduct. Under this
technique, there are several
methods which can be used to
draw or select the members of the
sample.
 • Convenience Sampling - This
technique is used because of the
Sampling convenience it offers to the
Technique researcher. It may be used
occasionally; however, we cannot
depend on it in making inferences
about a population.
 • Quota Sampling - In this type of
sampling, the proportions of the
Sampling various subgroups in the
Technique population are determined and
the sample is drawn to have the
same percentage in it. This is very
similar to the stratified random
sampling. The only difference is
that the selection of the sample is
not done randomly.
 • Purposive Sampling - Another
method of drawing to members of
the sample using non-probability
Sampling sampling is by using purposive
Technique sampling. Let us suppose that we
want to determine or predict the
candidate who will win in the
upcoming election. We can
conduct the survey or interview in
places or precints where people
voted for the winner in a series of
post elections because we feel
objectively that they will win again
vote for the next winner in the
upcoming election.
 Statistical data collected should be
Methods of arranged in such a manner that will

Presentation allow a reader to distinguish their

essential features. Depending on the
of Data type of information and the objectives
of the person presenting the
information, data may be presented
using once or a combination of three
forms: textual, tabular and graphical.
 TEXTUAL FORM - this form is utilized
Methods of when the data to be presented are

Presentation purely qualitative or when very few

numbers are involved. This method is
of Data generally not desirable when too
many figures are involved as the
reader may fail to grasp the
significance of a certain quantitative
relationships but it becomes an
effective device when the objective is
to call the reader’s attention to some
data that require special emphasis.
Methods of
Presentation
TABULAR FORM - this is a more
effective device of presenting data by
of Data means of statistical tables. People
who wants to make some
comparisons and draw relationships
usually find the tabular arrangement
more convenient and understandable
than the textual presentation.
Methods of GRAPHICAL FORM – this is perhaps

Presentation the most effective device

attracting people’s attention where
for

of Data the readers who look for comparisons

and trends may skip statistical tables
but may pause to examine graphs.
Construction of a good graph requires
more skill, more time and occasionally
more expense than does a statistical
table.
Tabular Sometimes, we could hardly grasp

Method information from a textual

presentation of data. Thus, we may
present data by using tables. By
organizing the data in tables,
important features about the data can
be readily understood and
comparisons can be easily made.
 The tabular method makes use of rows
and columns like a frequency distribution
or a frequency table. The data are
Tabular presented in a systematic and orderly

Method manner, which catches one’s attention

and may facilitate the comprehension
and analysis of the data presented.
However, in the case of grouped
frequency distribution, information on the
exact values like the highest or lowest
values may be sacrificed which
necessitates reference to the original data.
On the other hand, the frequency
distribution can present the patterns of
variation and other characteristics of the
data.
 • Decide on the number of classes.
Although there are no hard and fast
Construction rules in choosing the number of

of Frequency classes, as the choice is essentially

arbitrary, extra care must be
Distribution exercised so that the resulting
Table frequency distribution will not have
so few classes that not much
accurate information is obtained, nor
will t have so many classes that the
very purpose of grouping is defeated.
The use of 5 to 20 class intervals,
depending on the nature of the data,
is often justified.
Construction • Decide on the number of classes. The

of Frequency number of classes in a given situation

depends on the nature, magnitude
Distribution and range of data. Sturge suggested
Table the following formula to approximate
the number of classes (k).

k=1+3.3log n

where n = population/sample size

Construction 2. Calculate the range of the data by

of Frequency subtracting the lowest value from the

highest value in the set of data.
Distribution
Table
R = highest value - lowest value
Construction 3. Divide the range by the desired

of Frequency number of class intervals. The result if

not exact, may be rounded to the next
Distribution unit if the scores to be grouped are

Table expressed as whole numbers, otherwise

it may be rounded to the next number
with the same number of the decimal
places as the given measurements. The
figure may now be employed as the
interval size “i”.

i=R/k
 4. Determine the class limits which is the
range of values in a class consisting of a
Construction lower limit and an upper limit. This
of Frequency number should be less than, or equal to,

Distribution the lowest value in the data. Since the

first class interval should contain the
Table lowest value and since the number of
classes has already been decided upon,
the choice of the first lower limit could
be done on a trial-and-error basis. The
general practice, however, is to use, if
possible, a lower limit that is divisible by
the interval size or the class width.
 5. List the class boundaries, which is a
point that represents halfway or a
Construction dividing point between successive
of Frequency classes. List all the class boundaries by

Distribution adding the class width to the class

boundary of the previous boundary.
Table
Construction 6. Determine the class marks, which is

of Frequency the midpoint of the class interval by

averaging the class limits or the class
Distribution boundaries. The class marks serve as the
Table representative of each class.

7. Tally the frequencies for each class.

8. Sum the frequency column and check

against the total number of population/
sample size.
 Example 1

Construction A sample of 40 companies belonging to

of Frequency a certain industry reported the following

Distribution number of employees. Construct a

frequency distribution table. Construct a
Table frequency distribution using seven class
intervals for below data.

43 58 21 24 31 49 40 51 55 28
50 33 62 30 25 39 59 29 36 42
38 46 42 16 50 41 37 35 40 52
47 35 57 55 36 45 32 45 42 36
Construction of Frequency
Distribution Table
 The following figures represent the lives of
60 batteries rounded to the nearest tenth
ASSIGNMENT of a year. Construct a frequency
distribution using 8 classes with the first
starting at 1.8.
3.7 4.3 3.1 4.0 1.8 3.0 2.9 3.3 4.7 3.1
2.5 4.0 3.1 4.2 3.6 2.2 4.3 3.6 4.8 3.5
3.7 3.1 2.7 3.4 1.8 3.1 3.2 3.8 3.1 4.9
3.6 2.5 4.3 3.6 3.6 2.9 3.9 3.6 3.2 4.8
3.5 3.6 1.8 2.0 4.1 2.4 4.0 3.7 3.8 3.0
3.1 1.9 2.6 2.9 3.0 3.5 3.8 3.1 4.1 4.3