lOMoAR cPSD| 12139369

MODULE 2: DATA COLLECTION

DATA COLLECTION Everybody collects, interprets and uses information,

much of it in numerical or statistical forms in day-to-

AND BASIC Concepts

day life. It is a common practice that people receive
large quantities of information everyday through
conversations, televisions, computers, the radios,
in Sampling DESIGN newspapers, posters, notices and instructions. It is
just because there is so much information available
that people need to be able to absorb, select and
reject it. In everyday life, in business and industry,
Objectives: certain statistical information is necessary and it is
After successful completion of this independent to know where to find it how to collect it.
module, you should be able to:
Analysis of data can lead to powerful results. Data
• Determine the sources of data can be used to offset anecdotal claims, such as the
suggestion that cellular telephones cause brain
(primary and secondary data).
cancer. Anecdotal means that the information being
conveyed is based on casual observation, not
• Distinguish the different methods
scientific research. Because data are powerful, they can
data collection under primary and
be dangerous when misused. The misuse of data
secondary data.
usually occurs when data are incorrectly obtained or
analyzed. For example, radio or television talk shows
• Determine the appropriate
regularly ask poll questions for which respondents must
sample size.
call in or use the Internet to supply their vote. Most likely,
the individuals who are going to call in are those who
• Differentiate various sampling
have a strong opinion about the topic. This group is not
techniques.
likely to be representative of people in general, so the
• Know the sources of errors in results of the poll are not meaningful. Whenever we
sampling. look at data, we should be mindful of where the data
come from.

Even when data tell us that a relation exists, we

need to investigate. For example, a study showed
that breast-fed children have higher IQs than those
who were not breast-fed. Does this study mean that
a mother who breast-feeds her child will increase the
child’s IQ? Not necessarily. It may be that some
factor other than breast-feeding contributes to the IQ
of the children. In this case, it turns out that mothers who
breastfeed generally have higher IQs than those
who do not. Therefore, it may be genetics that leads to
the higher IQ, not breast-feeding.
 lOMoAR cPSD| 12139369

Data collection is the process of gathering 3. Determine the method to be used in data
and measuring information on variables of gathering and define the comprehensive
interest, in an established systematic fashion data collection points.
that enables one to answer stated research
questions, test hypotheses, and evaluate 4. Design data gathering forms to be used.
outcomes.
5. Collect data.
Without proper planning for data collection, a
Choosing of Method of Data Collection
number of problems can occur. If the data
collection steps and processes are not Decision-makers need information that is
properly planned, the research project can relevant, timely, accurate and usable. The cost
ultimately end up with a data set that does not of obtaining, processing and analyzing these
serve the purpose for which it was intended. data is high. The challenge is to find ways,
For example, if more than one person is which lead to information that is cost-effective,
involved in the data collection, but data relevant, timely and important for immediate
collectors do not follow consistent data use. Some methods pay attention to timeliness
collection practices, they can end up with data and reduction in cost. Others pay attention to
with different units, collection processes, and accuracy and the strength of the method in
variable names. using scientific.

Consequences from Improperly Collected The statistical data may be classified under two
Data categories, depending upon the sources.
approaches: Primary Data and Secondary
• Inability to answer research questions
Data.
accurately.
SOURCES OF DATA
• Inability to repeat and validate the study.
Whether conducting research in the social
• Distorted findings resulting in wasted
sciences, humanities arts, or natural sciences, the
resources.
ability to distinguish between primary and
secondary sources is essential.
• Misleading other researchers to pursue
fruitless avenues of investigation.
Primary Sources - Provide a first-hand
• Compromising decisions for public policy. account of an event or time period and are
considered to be authoritative. They
• Causing harm to human participants and represent original thinking, reports on
animal subjects. discoveries or events, or they can share new
information. Often these sources are created
Steps in Data Gathering at the time the events occurred but they can also
include sources that are created later. They
1. Set the objectives for collecting data
are usually the first formal appearance of
2. Determine the data needed based on the original research.
set objectives.
 lOMoAR cPSD| 12139369

Primary Data - are data documented by the agency may have been different from the
primary source. The data collectors purpose of the user of these secondary data.
documented the data themselves. S e c o n d l y, t h e r e m a y h a v e b e e n b i a s
introduced, the size of the sample may have
The first hand information obtained by the been inadequate, or there may have been
investigator is more reliable and accurate since arithmetic or definition errors, hence, it is
the investigator can extract the correct necessary to critically investigate the validity of
information by removing doubts, if any, in the the secondary data.
minds of the respondents regarding certain
questions. High response rates might be The primary data can be collected by the
obtained since the answers to various following five methods:
questions are obtained on the spot. It permits
1. D i r e c t p e r s o n a l i n t e r v i e w s - T h e
explanation of questions concerning difficult
researcher has direct contact with the
subject matter.
interviewee. The researcher gathers
Secondary Sources - offer an analysis, information by asking questions to the
interpretation or a restatement of primary interviewee.
sources and are considered to be
2. Indirect/Questionnaire Method - This
persuasive. They often involve
methods of data collection involve sourcing and
generalisation, synthesis, interpretation,
accessing existing data that were
commentary or evaluation in an attempt to
originally collected for the purpose of the study.
convince the reader of the creator's
argument. They often attempt to describe or Designing good “questioning tools” forms an
explain primary sources. important and time consuming phase in the
development of most research proposals.
Secondary Data - are data documented by a
Once the decision has been made to use these
secondary source. The data collectors had the
techniques, the following questions should be
data documented by other sources.
considered before designing our tools:
In secondary data, data are primary data for
the agency that collected them, and become • What exactly do we want to know, according
secondary for someone else who uses these to the objectives and variables we identified
data for his own purposes. earlier? Is questioning the right technique to
obtain all answers, or do we need additional
Secondary data are less expensive to collect techniques, such as observations or
both in money and time. These data can also analysis of records?
be better utilized and sometimes the quality of
such data may be better because these might • Of whom will we ask questions and what
have been collected by persons who were techniques will we use? Do we understand
specially trained for that purpose. the topic sufficiently to design a
questionnaire, or do we need some loosely
On the other hand, such data must be used structured interviews with key informants or
with great care, because such data may also a focus group discussion first to orient
be full of errors due to the fact that the purpose ourselves?
of the collection of the data by the primary
 lOMoAR cPSD| 12139369

• Are our informants mainly literate or Example:

illiterate? If illiterate, the use of self-
administered questionnaires is not an - Can you describe exactly what the
option. traditional birth attendant did when your
labor started?
• How large is the sample that will be
interviewed? Studies with many respondents
- What do you think are the reasons for a high
o f t e n u s e s h o r t e r, h i g h l y s t r u c t u r e d drop-out rate of village health committee
questionnaires, whereas smaller studies members?
allow more flexibility and may use
A closed-ended question is a type of
questionnaires with a number of open-ended
question that includes a list of response
questions.
categories from which the respondent will
Key Design Principles of a Good select his answer. It is useful if the range of
Questionnaire possible responses is known. This type of
question is usually appropriate for collecting
1. Keep the questionnaire as short as possible. objective data.

2. Decide on the type of questionnaire (Open Example:

Ended or Closed Ended).
Did you eat any of the following foods
3. Write the questions properly. yesterday?
4. Order the questions appropriately.
• Fish or meat Yes No
5. Avoid questions that prompt or motivate the • Eggs. Yes No
respondent to say what you would like to hear.
• Milk or cheese Yes No
6. Write an introductory letter or an
introduction. Take Note!

7. Write special instructions for interviewers or Question wording and question order have a large
respondents. effect on the responses obtained.

8. Translate the questions if necessary. Example:

9. Always test your questions before taking the Two surveys were taken in late 1993/early
survey. (Pre-test) 1994 about Elvis Presley.

An open-ended question is a type of question One survey asked: “In the past few years,
that does not include response categories. The there have been a lot of rumors and stories
respondent is not given any possible answers about whether Elvis Presley is really dead. How
to choose from. This type of question is usually do you feel about this? Do you think there is any
appropriate for collecting subjective data. It possibility that these rumors are true and that
permit free responses that should be recorded Elvis Presley is still alive, or don’t you think so?”
in the respondent’s own words.
 lOMoAR cPSD| 12139369

Second survey asked: “A recent television - Unrealistic Controlled Environments

show examined various theories about Elvis
- Inability to Control for All Variables
Presley’s death. Do you think it is possible that
Elvis is alive or not?” 5. Observation is a technique that involves
systematically selecting, watching and
8% of the respondents to the first question said
recoding behaviors of people or other
it is possible that Elvis is still alive and 16% of
phenomena and aspects of the setting in which
respondents to the second question said it is
they occur, for the purpose of getting (gaining)
possible that Elvis is still alive.
specified information. It includes all methods
3. A focus group is a group interview of from simple visual observations to the use of
approximately six to twelve people who share high level machines and measurements,
similar characteristics or common interests. A sophisticated equipment or facilities such as:
facilitator guides the group based on a - Radiographic
predetermined set of topics.
- biochemical
4. Experiment is a method of collecting data
where there is direct human intervention on the - X-ray machines
conditions that may affect the values of the - Microscope
variable of interest.
- Clinical examinations
Bear in mind that the experimental method has
several limitations that you should be aware of. - Microbiological examinations

- Ethical, moral, and legal Concerns

 lOMoAR cPSD| 12139369

It gives relatively more accurate data on size can produce accuracy of results.
behavior and activities but Investigators or Moreover, the results from the small sample
observer’s own biases, prejudice, desires, and size will be questionable. A sample size that is
etc. and needs more resources and skilled human too large will result in wasting money and time
power during the use of high level machines. because enough sample will normally give an
accurate result.
The secondary data can be collected by the
following five methods: The sample size is typically denoted by n and
it is always a positive integer. No exact sample
1. Published report on newspaper and size can be mentioned here and it can vary in
periodicals. different research settings. However, all else
being equal, large sized sample leads to
2. Financial Data reported in annual reports.
increased precision in estimates of various
3. Records maintained by the institution. properties of the population.

4. I n t e r n a l r e p o r t s o f t h e g o v e r n m e n t Take Note!
departments.
- Representativeness, not size, is the more
5. Information from official publications. important consideration.

Take Note! - Use no less than 30 subjects if possible.

• Always investigate the validity and reliability - If you use complex statistics, you may need
of the data by examining the collection a minimum of 100 or more in your sample
method employed by your source. (varies with method).

• Do not use inappropriate data for yo

research.
ur
• The choice of methods of data collection
largely based on the accuracy of t
information they yield. is
he
SAMPLE SIZE

“How many participants should be chosen for

survey”?
a
One of the most frequent problems
statistical analysis is the determination of t
in Representative Sample
appropriate sample size. One may ask why
he
sample size is so important. The answer to this
is that an appropriate sample size is required
for validity. If the sample size it too small, it will
not yield valid results. An appropriate sample
 lOMoAR cPSD| 12139369

Desired Confidence
Z - Score
Level
80% 1.28
85% 1.44
90% 1.65
95% 1.96
99% 2.58

3. Degree of Variability

Depending upon the target population and

attributes under consideration, the degree of
variability varies considerably. The more
heterogeneous a population is, the larger the
Choosing of sample size depends on non-
sample size is required to get an optimum level
s t at i s t i c al c ons i der at i ons and s t at i s t i c al
of precision.
considerations.
Methods in Determining the Sample Size
• Non-statistical considerations – It may
include availability of resources, man power, • Estimating the Mean or Average
budget, ethics and sampling frame.
The sample size required to estimate the
• Statistical considerations – It will include population mean µ to with a level of confidence
the desired precision of the estimate. with specified margin of error e, given by

Three criteria need to be specified to 2

Zσ
determine the appropriate sample size: n≥
( e )
1. Level of Precision
where:
Also called sampling error, the level of

precision, is the range in which the true value Z is the z-score corresponding to level of
of the population is estimated to be. confidence.

2. Confidence Interval e is the level of precision.

It is statistical measure of the number of times Take Note:

out of 100 that results can be expected to be
within a specified range. For example, a If When σ is unknown, it is common practice to
confidence interval of 90% means that results conduct a preliminary survey to determine s
of an action will probably meet expectations and use it as an estimate of σ or use results
90% of the time. from previous studies to obtain an estimate of
σ. When using this approach, the size of the
To find the right z – score to use, refer to the table: sample should be at least 30. The formula for
the sample standard deviation s is
 lOMoAR cPSD| 12139369

which we know only after we have taken the

∑ (x − x̄)2 sample.
s=
n− 1
There are two ways to solve this dilemma:
Example:
1. We could determine a preliminary value for
A soft drink machine is regulated so that the p based on a pilot study or an earlier study.
amount of drink dispensed is approximately
normally distributed with a standard deviation Example:
equal to 0.5 ounce. Determine the sample size
needed if we wish to be 95% confident that our If last month 37% of all voters thought that
sample mean will be within 0.03 ounce from state taxes are too high, then it is likely that the
the true mean. proportion with that opinion this month will not
be dramatically different, and we would use the
Solution: The z – score for confidence level value 0.37 for p in the formula.
95% in the z – table is 1.96.
2. Simply to replace p in the formula by 0.5.
2
1.96(0.5)
n≥ = 1067.11 When p = 0.5, the maximum value of
( 0.03 )
p(1- p)=0.25. This is called the most
conservative estimate, since it gives the
We need a 1068 sample for our study. largest possible estimate of n.

• Estimating Proportion (Infinite The conservative formula using the strong law
Population) of large number.

The sample size required to obtain a 2

confidence interval for p with specified margin 1 Z
n≥ ≈ 385
of error e is given by 4 (e)

2 Where:
Z
n≥ p(1 − p)
(e) Confidence level is 95%.

Where: The level of precision is 0.05.

Z is the z-score corresponding to level of Example:

confidence.
Suppose we are doing a study on the inhabitants
e is the level of precision. of a large town, and want to find out how
many households serve breakfast in the
P is population proportion. mornings. We don’t have much information on the
subject to begin with, so we’re going to assume
There is a dilemma in this formula:
that half of the families serve breakfast: this
It dependents on gives us maximum variability. So p = 0.5. We
x
p= want 99% confidence and at least 1% precision
N
 lOMoAR cPSD| 12139369

Solution: The z – score for confidence level Where:

99% in the z – table is 2.58.
no is Cochran’s sample size recommendation.
2
2.58
n≥ 0.5(1 − 0.5) = 16,641 N is the population size.
( 0.01 )
This is the link for online calculator of sample
We need a 16,641 sample for our study. size:

• Slovin’s Formula https://select-statistics.co.uk/calculators/

sample-size-calculator-population-proportion/
Slovin’s formula is used to calculate the
sample size n given the population size and h t t p s : / / www. c a lc u la t o r. n e t / s a m p le - s i z e -
error. It is computed as calculator.html

N
n≥
1 + Ne 2

Where:

N is the total population.

e is the level of precision.

Example:
A researcher plans to conduct a survey about
food preference of BS Stat students. If the
BASIC SAMPLING DESIGN
population of students is 1000, find the sample
size if the error is 5%.
The goal in sampling is to obtain individuals for
Solution: a study in such a way that accurate information
1000 about the population can be obtained.
n≥ = 285.71
1 + 1000(0.05)2 Reason for Sampling

The researcher need to survey 286 BS stat - Important that the individuals included in a
students. sample represent a cross section of
individuals in the population.
• Finite Population Correction
- If sample is not representative it is biased.
If the population is small then the sample size You cannot generalize to the population from
can be reduced slightly your statistical data.
n0
n≥ Some definitions are needed to make the
n −1
1+ o notion of a good sample more precise.
N
 lOMoAR cPSD| 12139369

Definitions: - Deliberately or purposively selecting a

“representative” sample.
• Observation unit - An object on which a Misspecifying the target population.
measurement is taken. This is the basic unit Failing to include all of the target population
of observation, sometimes called an element. in the sampling frame, called
In studying human populations, observation undercoverage.
units are often individuals. Including population units in the sampling
frame that are not in the target population,
• Target population - The complete collection
called overcoverage.
of observations we want to study.
- Having multiplicity of listings in the sampling
• Sampled population - The collection of all
frame.
possible observation units that might have
Substituting a convenient member of a
been chosen in a sample; the population
population for a designated member who is
from which the sample was taken.
not readily available.
• Sample - A subset of a population. - Failing to obtain responses from all of the
• Sampling unit - A unit that can be selected chosen sample. (Nonresponse)
for a sample. We may want to study - Allowing the sample to consist entirely of
individuals, but do not have a list of all
volunteers.
individuals in the target population. Instead,
households serve as the sampling units, and the Advantage of Sampling Over Complete
observation units are the individuals living Enumeration
in the households.
- Less Labor
• Sampling frame - A list, map, or other
specification of sampling units in the - Reduced Cost
population from which a sample may be - Greater Speed
selected. For a survey using in-person
interviews, the sampling frame might be a list - Greater Scope
of all street addresses.
- Greater Efficiency and Accuracy
• Sampling technique/Sampling Strategies - - Convenience
It is a plan you set forth to be sure that the
sample you use in your research study - Ethical Considerations
represents the population from which you
Two Type of Samples
drew your sample.
1. Probability Sample
• Sampling Bias - This involves problems in
your sampling, which reveals that your - Samples are obtained using some objective
sample is not representative of your chance mechanism, thus involving
population. randomization.

The following examples indicate some ways in

which selection bias can occur:
 lOMoAR cPSD| 12139369

- They require the use of a complete listing of - Most basic method of drawing a probability
the elements of the universe called the sample.
sampling frame.
- Assigns equal probabilities of selection to
- The probabilities of selection are known. each possible sample.

- They are generally referred to as random - Results to a simple random sample.

samples.
Advantage: It is very simple and easy to use.
- They allow drawing of valid generalizations
about the universe/population. Disadvantage: The sample chosen may be
distributed over a wide geographic area.
2. Non - probability Sample
When to use: This is preferable to use if the
- Samples are obtained haphazardly, selected population is not widely spread geographically.
purposively or are taken as volunteers. Also, this is more appropriate to use if the
population is more or less homogenous with
- The probabilities of selection are unknown.
respect to the characteristics of the population.
- They should not be used for statistical
inference.

Sampling Procedure

- Identify the population.

- Determine if population is accessible.

- Select a sampling method.

- Choose a sample that is representative of
the population.

- Ask the question, can I generalize to the general Simple Random Sampling
population from the accessible population?

Sampling technique can be grouped into how

selections of items are made such as
• Systematic Random Sampling
probability sampling and non-probability
sampling. - It is obtained by selecting every kth
individual from the population.
Basic Sampling Technique of Probability
Sampling - The first individual selected corresponds to a
random number between 1 to k.
• Simple Random Sampling
 lOMoAR cPSD| 12139369

Obtaining a Systematic Random Sample When to use: This is advisable to us if the

ordering of the population is essentially
1. Decide on a method of assigning a unique random and when stratification with numerous
serial number, from 1 to N, to each one of data is used.
the elements in the population.

2. Compute for the sampling interval

N PopulationSize
k= =
n SampleSize

3. Select a number, from 1 to k, using a

randomization mechanism. The element in
the population assigned to this number is
the first element of the sample. The other
elements of the sample are those assigned
to the numbers and so on until you get a
sample of size.
Systematic Random Sampling

Example:
• Stratified Random Sampling
We want to select a sample of 50 students
- It is obtained by separating the population
from 500 students under this method kth item
into non-overlapping groups called strata and
and picked up from the sampling frame.
then obtaining a simple random sample from
Solution: each stratum.

500 - The individuals within each stratum should

k= = 10
50 be homogeneous (or similar) in some way.
We start to get a sample starting form i and for
every kth unit subsequently. Suppose the Example:
random number i is 6, then we select 15, 25,
A sample of 50 students is to be drawn from a
35, 45, .. .
population consisting of 500 students
Advantage: Drawing of the sample is easy. It belonging to two institutions A and B. The
is easy to administer in the field, and the number of students in the institution A is 200
sample is spread evenly over the population. and the institution B is 300. How will you draw
the sample using proportional allocation?
Disadvantage: May give poor precision when
unsuspected periodicity is present in the
population.

When to use: This is advisable to us if the

ordering of the population is essentially
random and when stratification with numerous
data is used.
 lOMoAR cPSD| 12139369

Solution:

There are two strata in this case.

Given:

N1 = 200 N2 = 300 N = 500 n = 50

n 50
n1 = N1 = 200 = 20
(N) ( 500 )

n 50
n2 = N2 = 300 = 30
(N) ( 500 )
The sample sizes are 20 from A and 30 fro m
B. Then the units from each institution are to
be selected by simple random sampling.

Advantage: Stratification of respondents is

advantageous in terms of precision of the
estim ates of the characteristics of the
population. Sampling designs may vary by
stratum to adjust for the differences in the
conditions across strata. It is easy to use as a
random sampling design.
Disadvantage: Values of the stratification
variable may not be easily available for all units
in the population especially if the characteristic
of interest is homogeneous. It is possible that
there are not representative in one or two Stratified Random Sampling
strata. Also, transportation costs can be high if
the population covers a wide geographic area.

When to use: If the population is such that the • Cluster Sampling

distribution of the characteristics of the
- You take the sample from naturally occurring
respondents under consideration concentrated
groups in your population.
in small and spread segment of the population.
Thus, this is preferred to use if precise - The clusters are constructed such that the
estimates are desired for stratified parts of the sampling units are heterogeneous within the
population and if sampling problems differ in cluster and homogeneous among the
the various strata of the population. clusters.
 lOMoAR cPSD| 12139369

Obtaining a Cluster Sample When to use: If the population can be

grouped into clusters where individual
1. Divide the population into non-overlapping population elements are known to be different
clusters. with respect to the characteristics under study,
this preferable to use.
2. Number the clusters in the population from 1
to N.

3. Select n distinct numbers from 1 to N using

a randomization mechanism. The selected
clusters are the clusters associated with the
selected numbers.

4. The sample will consist of all the elements in

the selected clusters.

Example:

A researcher wants to survey academic

performance of high school students in Cluster Sampling
MIMAROPA.
• Multi - Stage Sampling
1. He/She can divide the entire population into
different clusters.
- Selection of the sample is done in two or
more steps or stages, with sampling units
2. Then the researcher selects a number of varying in each stage.
clusters depending on his research through
- The population is first divided into a number
simple or systematic random sampling.
of first-stage sampling units from which a
3. Then, from the selected clusters the sample is drawn. Smaller units, called the
researcher can either include all the high secondary sampling units, comprising the
school students as subject or he can select a selected first-stage units then serve as the
number of subjects from each cluster through sampling units for the next stage. If needed
simple or systematic random sampling. additional stages may be added until the
units of observation for the survey are
Advantage: There is no need to come out with clearly identified. The units comprising the
a list of units in the population; all what is samples selected from the previous stage
needed is simply a list of the clusters. It is also less constitute the frame for the stages.
costly since the elements are physically closer
together. Obtaining a Multi-Stage Sampling

Disadvantage: In actual field applications, 1. Organize the sampling process into stages
adjacent households tend to have more similar where the unit of analysis is systematically
characteristics than households distantly apart. grouped.

2. Select a sampling technique for each

 lOMoAR cPSD| 12139369

3. S y s t e m a t i c a l l y a p p l y t h e s a m p l i n g
technique to each stage until the unit of
analysis has been selected.

Example:
Suppose we wish to study the expenditure
patterns of households in NCR. We can select
a sample of households for this study using simple
three-stage sampling.

- First, divide into smaller cities/municipalities

and a random sample of these cities/
municipalities is collected. Multi-Stage Sampling

- Second, a random sample of smaller areas

such as barangays is taken from within each
of the cities/municipalities chosen in the first B a s i c S a m p l i n g Te c h n i q u e o f N o n -
stage. Probability Sampling

- Third, a random sample of even smaller • Accidental Sampling - There is no system

areas such as households is taken from of selection but only those whom the
within each of the areas chosen in the researcher or interviewer meets by chance.
second stage.
• Quota Sampling - There is specified
Advantage: It is easier to generate adequate number of persons of certain types is
sampling frames. Transportation costs are included in the sample. The researcher is
greatly reduced since there is some form of aware of categories within the population and
clustering among the ultimate or final samples; draws samples from each category. The s i z e
i.e., they are in the sample lower-stage units. of each categorical sample is
proportional to the proportion of the
Disadvantage: Its complexity in theory may be population that belongs in that category.
difficult to apply in the field. Estimation
procedures may be difficult for non-statisticians • Convenience Sampling - It is a process of
to follow. picking out people in the most convenient
and fastest way to get reactions
When to use: If no population list is available immediately. This method can be done by
and if the population covers a wide area. telephone interview to get the immediate
reactions of a certain group of sample for a
Take Note! certain issue.
Used probability sampling if the main objective
• Purposive Sampling - It is based on certain
of the sample survey is making inferences
criteria laid down by the researcher. People
about the characteristics of the population
who satisfy the criteria are interviewed. It is
under study.
used to determine the target population of
those who will be taken for the study.
 lOMoAR cPSD| 12139369

• Judgement Sampling - selects sample in

accordance with an expert’s judgment.

Cases wherein Non-Probability Sampling is

Useful

- Only few are willing to be interviewed

- Extreme difficulties in locating or identifying

subjects

- Probability sampling is more expensive to

implement

- Cannot enumerate the population elements.

Sources of Errors in Sampling

1. Non-sampling Error

- Errors that result from the survey process.

- Any errors that cannot be attributed to the

sample-to-sample variability.

Sources of Non-Sampling Error

1. Non-responses

2. Interviewer Error REFERENCES:

Statistics. Informed Decision using Data by

3. Misrepresented Answers Michael Sullivan, III,. Fifth Edition

4. Data entry errors Sampling: Design and Analysis by Sharon L. Lhr.

Second Edition

5. Questionnaire Design http://www.economicsdiscussion.net/statistics/

sampling/advantages-of-sampling-over-
completeenumeration-in-statistics/11980
6. Wording of Questions
h t t p : / / w w w. n a t c o 1 . o r g / r e s e a r c h / fi l e s
7. Selection Bias /SamplingStrategies.pdf

https://data36.com/statistical-bias-types- explained/
2. Sampling Error

- Error that results from taking one sample

instead of examining the whole population.

- Error that results from using sampling to

estimate information regarding a population.