Introduction to Sampling

Methods
By
Dr. Jimoh Olawale Ajadi
Outline
• Population and Sample
• Statistic and Parameter
• Sampling Frame
• Probability and Non-probability Sampling
• Sampling and Non-sampling Errors
• Questionnaire Design
Population and Sample
• Population is the entire group of individuals or objects (elements) about which
we want information.
• Sample is the part (subset) of the population we actually collect information
from.
• If a sample is equal to the population, then we have a census which contains all
information one wants. However, census is rarely conducted for several
reasons:
1. Cost (money is limited)
2. Time (time is limited)
3. Utility (testing a product can be destructive)
4. Accessibility (nonresponse)
In those cases, sampling is the only alternative
Statistic and Parameter
•  Parameters are fixed, unknown numbers important to the population
(e.g. population mean (, variance (, proportion (), etc).
• Statistic is a characteristic of a sample, e.g. sample mean (, sample
variance (), sample proportion (), etc.)
• Examples:
1. The average age of KFUPM students is 27 years
2. The proportion of Male Students that registered for STAT 565 is 0.888
3. The mean age for randomly selected 100 students at KFUPM is 25.
 Sampling Units and Sampling Frame
• Sampling unit Before selecting the sample, the population must be divided into
parts that are called Sampling units. These units must cover the whole of the
population and not overlap. That is, every element in the population belongs
one and only one unit. We may want to study individuals, but do not have a list
of all individuals in the target population. Instead, households serve as the
sampling units, and the observation units are the individuals living in the
households.
• Sampling frame A list, map, or other specification of sampling units in the
population from which a sample may be selected. For a telephone survey, the
sampling frame might be a list of all residential telephone numbers in the city.
For a survey using in-person interviews, the sampling frame might be a list of all
street addresses. For an agricultural survey, a sampling frame might be a list of
all farms, or a map of areas containing farms.
 Sample Survey Design
• Sample Survey Design The procedure for selecting the sample is called
the sample survey design.

• The general aim of sample survey is to obtain data(samples). Data have

to be “representative” of the whole population. Broadly speaking, we
have two kinds of sampling schemes

Probability Sampling
 Non-probability Sampling
Probability Sampling
• Probability Sampling Sampling designs whereby particular samples
are numerated and each has a non-zero probability of being selected.

a. Simple random sampling

b. Stratified random sampling
c. Cluster sampling
d. Systematic sampling
We will concentrate on probability sampling in this course
Non-Probability Sampling
• Non-Probability Sampling  is a sampling procedure that uses non-
random ways to select samples.

• Volunteer sampling: medical volunteers for research

• Subjective sampling: we choose samples that we consider to be
typical or representative of the population
• Quota sampling: One keep sampling until certain quota is filled
Methods of Data Collection
• Personal Interview
• Telephone Interview
• Self-administered questionnaires
• Direct observation, e.g. assign a person to count the number of cars
passing a specified point on the road during the 4-6 pm rush hours.
Sampling and Non-sampling Errors
• Nonsampling error: An error from any source other than sampling
error. Examples include nonresponse and measurement error.

• Sampling error: Error in estimation due to taking a sample instead of

measuring every unit in the population.

• Selection bias and measurement error are examples of nonsampling

errors, which are any errors that cannot be attributed to the sample-
to-sample variability.
Questionnaire Design
• Questionnaire design is the most important and perhaps the most difficult
part of the survey sampling problem.
• Some general guidelines include:
1. Decide what you want to find out. This is the most important step in
writing a questionnaire.
2. Always test your questions before taking survey. Ideally, the question will
be tested on a small sample of members of target population. Try
different versions of the questions and ask the respondents in your
pretest on how they interpret the questions.
3. Keep the questions simple and clear. Questions that seems clear to you,
may not be clear to someone listening to the whole questions over the
telephone or to a person of different native language
Questionnaire Design
4. Use specific questions instead of general ones, if possible.
5. Relate your questions to the concept of interest
6. Decide whether to use open or closed questions. An open question
allows respondents to form their own response categories; in a closed
question (multiple choice), the respondent chooses from a set of
categories read or displayed.
7. Avoid questions that prompt or motivate the respondent to say what you
would like to hear. These are often called leading, or loaded, questions.
8. Report the actual question asked. Public opinion is complex, and you
inevitably leave a distorted impression of it when you compress the
results of your careful research into a summary statement “x% of
Americans favor affirmative action.”
 Questionnaire Design
9. Use forced-choice, rather than agree/disagree questions. Some persons will agree with almost any
statement. Schuman and Presser (1981, p. 223) report the following differences from an experiment
comparing agree/disagree with forced-choice versions:
Q1: Do you agree or disagree with this statement: Most men are better suited emotionally for politics
than are most women.
Q2: Would you say that most men are better suited emotionally for politics than are most women, that
men and women are equally suited, or that women are better suited than men in this area?

10. Ask only one concept per question. In particular, avoid what are sometimes called double-barreled
questions, so named because if one barrel of the shotgun does not get you, the other one will.
11. Pay attention to question order effects. If you ask more than one question on a topic, it is usually
(but not always) better to ask the more general question first and follow it by the specific questions.