SAMPLING

Presented by: Jarah Victoria R. Dayag

BASIC TERMS
The identification and selection of elements that will
make up the sample is at the heart of all sampling
techniques.
There are two kinds of data of interest to social
scientists: individual data and cultural data.
Individual data are about attributes of individuals in
a population.
BASIC TERMS
If the idea in collecting data is to estimate the
average age, income or preference in a larger
population-that is, to estimate some population
parameters-then a scientifically drawn unbiased
sample is a must.
BASIC TERMS
A population is the set of all cases of interest.
In order to select a subset of a certain population,
we need to develop a specific list of the members of
the population; this specific list is called a sampling
frame and is, in a sense, an operational definition of
the population of interest.
BASIC TERMS
The subset of the population actually drawn from
the sampling frame is called sample.
Each member of the population is called an
element.
Populations, not samples, are of primary interest.
BASIC TERMS
The ability to generalize from a sample to the
population depends critically on the
representativeness of the sample.
A sample is representative of the population to the
extent that it exhibits the same distribution of
characteristics as the population.
BASIC TERMS
There are two basic approaches to
sampling-nonprobability sampling and probability
sampling.
PROBABILITY SAMPLING
Simple Random Sampling
is the basic technique of probability sampling.
every element has an equal chance of being
included in the sample.
Most packages for statistical analysis have built in
random-number generators, and you can create
random samples by using one of the
random-number generators on the internet.
PROBABILITY SAMPLING
Systematic Random Sampling
For this, you need a random start and a sampling
interval, N.
You enter the sampling frame at the random start
and take every Nth person (or item) in the frame.
PROBABILITY SAMPLING
Stratified Sampling
the population is divided into subpopulations called
strata and random samples are drawn from each of
these strata.
ensures that key subpopulations are included in
your sample.
You divide a population into subpopulations, based
on key independent variables and then take a
random sample from each of those subpopulations.
PROBABILITY SAMPLING
Cluster Sampling
It lets you sample populations for which there are
no convenient frames or lists.
By sampling from these clusters, we narrow the
sampling field from large, heterogeneous chunks to
small, homogenous ones that are relatively easy to
find.
PROBABILITY SAMPLING
For example, there are no lists of school children
from in large cities, but children cluster in schools.
There are lists of schools, so you can take a sample
of them, and then sample children within each
school selected.
HOW BIG SHOULD A SAMPLE BE?

There are two things you can do to get good

samples.
1) Ensure sample accuracy by making sure that
every element in the population has an equal
chance of being selected- that is, you can make
sure the sample is unbiased.
2) Ensure sample precision by increasing the size
of unbiased samples.
HOW BIG SHOULD A SAMPLE BE?

The next step is to decide how big a sample needs

to be.
Sample size depends on:
1) the heterogeneity of the population or chunks
of population (strata or clusters) from which you
choose the elements.
2) how many population subgroups (that is,
independent variables) you want to deal with
simultaneously in your analysis.
HOW BIG SHOULD A SAMPLE BE?

3) the size of the phenomenon that you are trying to

detect.
4) how precise you want your sample statistics (or
parameter estimators) to be.
CONT…
The major threat to representativeness is bias. A
biased sample is one in which the distribution of
characteristics in the sample is systematically
different from the target population.
NONPROBABILITY SAMPLING
Nonprobability samples are always appropriate for
labor-intensive, in-depth studies of a few cases.
Every case has to count and this means choosing
cases on purpose, not randomly.
In depth research on sensitive topics requires
nonprobability sampling.
NONPROBABILITY SAMPLING
Example: It can take months of participant
observation fieldwork before you can collect
narratives about topics like sexual and reproductive
histories or bad experiences with mental illness or
use of illegal drugs.
Really in depth research requires informed
informants, not just responsive respondents.
NONPROBABILITY SAMPLING
Nonprobability samples are also appropriate for
large surveys when, despite our best efforts, we just
can’t get a probability sample.
NONPROBABILITY SAMPLING
Nonprobability sampling methods include quota
sampling, purposive or judgement sampling,
convenience or haphazard sampling, chain referral
or network sampling (snowball sampling and
respondent driven sampling).
NONPROBABILITY SAMPLING
Quota Sampling
is stratified sampling without random selection. It is
used widely in studies that rely on qualitative data,
like in-depth interviews.
The key to quota sampling is the development of a
sampling design, or sampling grid.
Example:
Suppose you are studying the lived experiences of
Mexican labor migrants to the United States. You want to
compare the experiences of people up to 30 years of age
and those over 30; of mestizos and Indians; and of men
and women. That’s three binary independent variables.
QUOTA SAMPLING GRID WITH THREE
BINARY INDEPENDENT VARIABLES

Labor Migrants in the US

Up to 30 yrs of age Over 30 yrs of

age
Mestizo Indian Mestizo Indian

Male Femal Male Femal Male Femal Male Femal

e e e e
CONT…
The figure shows the eight cells in this design. If
you want at least five informants in each cell, you’ll
need to do 40 interviews.
When it’s done right, quota samples often do a
good job of reflecting the population parameters of
interest.
CONT…
Quota samples are biased toward people you can
find easily hence, quota sampling is dangerous
when estimating any population parameter, for that
matter, if you need precise results.
On the other hand, quota sampling is appropriate in
the study of cultural domains.
NONPROBABILITY SAMPLING
Purposive, or Judgement Sampling
In purposive sampling, you decide the purpose you
want informants to serve, and you go out to find
some.
It’s like quota sampling, except that there is no
overall sampling design that tells you how many of
each type of informant you need for a study.
NONPROBABILITY SAMPLING
There are at least five good reasons for using
purposive samples. They are used widely in:
1) Pilot studies
2) intensive case studies
3) critical case studies
4) hard-to-find population studies
5) studies of anything where no other method of
sampling is available.
NONPROBABILITY SAMPLING
Convenience or Haphazard Sampling
is a glorified term for grabbing whoever will stand
still long enough to answer your questions.
It is useful for exploratory research, to get a feel for
“what’s going on out there,” and for pretesting
questionnaires to make sure that the items are
unambiguous and not too threatening.
NONPROBABILITY SAMPLING
Chain referral, or Network sampling: The snowball
and RDS methods
Also known, generically, as chain referral sampling
and network sampling, are two network sampling
methods for studying hard-to-find or hard-to-study
populations.
NONPROBABILITY SAMPLING
Populations can be hard to find and study for at least
four reasons:
1) They contain very few members who are scattered
over a large area, and/or:
2) They are stigmatized or reclusive, and/or:
NONPROBABILITY SAMPLING
3) They are people who really have something to
hide, and/or:
4) They are members of an elite group (surgeons,
professional athletes) and don’t care about your
need for data.
NONPROBABILITY SAMPLING
Snowball Sampling
using key informants and/or documents, you locate
one or two people in a population. Then ask those
people to:
1) list other in the population; and
2) recommend someone from the list whom you might
interview.
NONPROBABILITY SAMPLING
Ostrander (1980) used snowball sampling in her
study of class consciousness among upper-class
women in a Midwestern U.S city. She selected her
first informant by looking for someone who had
graduated from an elite women’s college, was listed
in the social register, was active in upper-class
clubs-and who would talk to her. At the end of the
interview, she asked the informant to “suggest
another woman of your social group, with a
background like yours, who might be willing to talk
to me.”
NONPROBABILITY SAMPLING
Respondent-Driven Sampling
RDS begins with a few people who acts as seeds.
The respondents are paid for being interviewed and
then asked to recruit up to three members of their
networks into their study.
In RDS, the initial members of the sample are
volunteers as are the people they recruit.
NONPROBABILITY SAMPLING
⚪ When it’s done right, the RDS method
produces samples that are less biased
than are traditional snowball samples.
SAMPLE SIZE IN NONPROBABILITY
SAMPLING

There is growing evidence that 10-20

knowledgeable people are enough to understand
the core categories in any well-defined cultural
domain or study of lived experience.
Morse (1994) recommended a minimum of six
interviews for phenomenological studies and 30-50
interviews for ethnographic studies and grounded
theory studies.
REFERENCES
Bernard, H. R. (2013). Nonprobability Sampling. In
H. R. Bernard, Social Research Method: Qualitative
and Quantitative Approaches (pp. 162-176). Los
Angeles: Sage Publications.
Bernard, H. R. (2013). Sampling The Basics. In H.
R. Bernard, Social Research Method: Qualitative
and Quantitative Approaches (pp. 127-142). Los
Angeles: Sage Publications.
John J. Shaughnessy, E. B. (2012). Sampling in
Survey Research. In E. B. John J. Shaughnessy,
Research Methods in Psychology (pp. 140-148).
New York: McGraw-Hill.