Introduction
Sampling error
Types of probability
sample
The qualities of a
probability sample
Sample size
Types of non-probability
sampling
Quantitative Sampling
Limits to generalization
7
Chapter Objectives
By the end of this chapter, students should be able to:
understand that the topic of sampling pertains to both
qualitative and quantitative research design
Chapter 11 - Interviewing in Qualitative Research ~ Sheri Adekola
understand that being able to generalize about
research findings requires representative samples
explain the difference between a probability sample
and a non-probability sample
define the different types of probability samples:
simple random, systematic, stratified random, and
stage cluster sample
understand the major issues in deciding sample sizes
describe different types of non-probability samples,
especially quota sampling
This Pho to by Unkn own Author is licensed u nder CC BY-SA identify the potential sources of sampling error
discuss theoretical sampling, widely used in
ethnographic studies
discuss sampling strategies for content analysis
discuss strategies to raise response rates
SAMPLING STRATEGIES
• To collect these data types for a study, a target
population, community, or study area must be
identified first.
• It is not possible for researchers to collect data
from everyone in a sample area or
community. Therefore, the researcher must
gather data from a sample, or subset, of the
population in the study.
• There are two strategies of sampling
Probability sampling (quantitative)
Non-probability sampling (qualitative)
Element or unit A single case in the population
Population All cases that a researcher is interested in
Sampling frame The list of elements that the sample will be selected from
Sample The elements (subset of a population) selected for investigation
Representative A sample that contains the same essential characteristics as the
sample population
Key Terms Probability
sample
A sample selected using a random process so that each element in
the population has a known likelihood of being selected
Non-probability A sample selected using a non-random method
sample
Module #4 - Sheri Adekola
Sampling error Estimation the error that occurs because of differences between
the characteristics of the sample and those of the population
Non-response When an element selected for the sample does not supply the
required data
Census Data that comes from an attempt to collect information from all
elements in the population
SAMPLE SIZE
• The absolute size of the sample matters (not the proportion of the
population that it comprises).
• As the sample size increases, the sampling error tends to decrease
• Sampling ratio
▪The sampling ratio = n/N (where sample size= n and
population size = N)
• Sampling errors
▪ Are errors of estimation that occur due to discrepancy between the sample
group and the total population
▪ Includes – non-response errors, sampling method errors, and sampling frame
errors
Probability Sampling
This Pho to by Unkn own Author is licensed u nder CC BY
TYPES OF PROBABILITY SAMPLING
• The purpose of probability
sampling aims to obtain a
sample representing the
population from which it
was drawn.
• The four common
probability sampling
techniques discussed in the
texts are
Simple Random Sampling
Systematic Sampling
Stratified Random Sampling
Multi-stage Cluster Sampling
SIMPLE RANDOM SAMPLING
• A sampling technique where a group of subjects is selected, (a sample “n”) for study
from a larger group (a population “N”)
▪ The technique takes a small, random portion of the entire population to represent the
entire data set
▪ Involves each element having the same probability of being selected
▪ Is more commonly used when the researcher knows little about the population
▪ Can be done using two methods:
▪ lottery method
▪ random number table or computer program
Strengths Weaknesses
• Unbiased representation of • Sampling error and or Sampling bias
the group • Time & Cost
SYSTEMATIC SAMPLING
• The systematic sampling technique involves choosing every ith person
from a list after randomly choosing a starting point.
The steps to create a systematic sample are
▪ Create a list of the population
▪ Select a beginning number (random start) from 1 to i
▪ Select an interval = i
▪ Generate a list of the samples based on the interval number, e.g. if you want to
select every 10th case, i = 10
▪ The case with that number is the first case selected
Strengths Weaknesses
• Accurately reflect the population • over- or under-representation of
being studied certain people
SYSTEMATIC SAMPLING PROBLEM
• Periodicity
Chapter 11 - Interviewing in Qualitative Research ~ Sheri Adekola
This occurs if the cases in the sampling frame
are arranged in some systematic order, e.g.,
in an election study: voter, non-voter, voter,
non-voter, etc.
If we were to select every 30th case starting
with case 20, we would select case 20, 50, 80,
etc.
I.e., all cases would be non-voters
STRATIFIED RANDOM SAMPLING
• A stratified random sample divides the population into smaller
groups, or strata, based on shared features
• This type of sampling ensures that subgroups in the
population are proportionally represented in the sample
Steps:
Stratify the population, i.e. divide it into subgroups
Select a simple random sample or a systematic sample from each
stratum
Strengths Weaknesses
• Accounts for the differences within • Every member of the population
the population, such as age, race or must be in a subgroup
gender.
MULTI-STAGE CLUSTER SAMPLING1
• Multi-stage cluster sampling combines two or more of the sampling
techniques in order to avoid the limitations associated with the particular
sampling techniques.
• It is useful for sampling large populations where there are no adequate
sampling frames and elements are geographically dispersed
• It involves dividing the population into groups (clusters), then, one or more
clusters are chosen at random, and everyone within the chosen cluster is
sampled.
Steps
• It involves two or more stages:
Selecting clusters (groups of elements)
Randomly select a number of subunits from each cluster (province/territory)
e.g., cities
Selecting subunits within clusters
MULTI-STAGE CLUSTER SAMPLING2
Ontario
Region of Halton
Toronto
Peel Region
North York Etobicoke Mississauga Caledon Milton Burlington
Module #4 - Sheri Adekola
20 females 20 females 20 females 20 females 20 females 20 females
20 males 20 males 20 males 20 males 20 males 20 males
Strengths Weaknesses
• Easy and convenient • members of units are different from
one another
Sampling Problems
• Error
Sampling error (addressed above)
Sampling-related error
non-response
inadequate sampling frame
• Probability samples with sufficient sample sizes minimize the
amount of sampling error, but some sampling error is bound to
occur.
Module #4 - Sheri Adekola
• This sort of sampling error is measured by a statistic called the
standard error of the mean
• About 95 per cent of all sample means lie within 1.96 standard
errors off the mean
Sample Size
• The absolute size of the sample matters
(Not the proportion of the population that it comprises)
• As sample size increases, sampling error tends to decrease
• Common sample sizes: 100, 400, 900, 1600, 2500
Each size increase cuts the sampling error by 1/2, then 1/3, then 1/4, and then
1/5 respectively
• The biggest change occurs between 100 and 400
Is an increased sample size worth the time and effort?
Often sample size is dictated by financial concerns
Module #4 - Sheri Adekola
• Issues with sample size
Non-response Heterogeneity of the Population Kind of Analysis
• Th e response rate is the percen tage of the sample that p art icipates • Generally, the great er the heterogeneity of th e popu lation o n th e • Th e sample size needed may vary depending o n w hat sort of
in the study characteristics of interest, the larger the sample size should be analysis will be done
• Is there is some particular issue common t o the non-responders • If small groups in the pop ulation are to be compared to larger
that brings them to differ in some important way from th ose wh o groups, it may be n ecessary to o versample th e smaller group in
participate order to make meaningfu l co mp arisons
• Certain statistical procedures, su ch as some multivariate an alyses,
require large sample sizes t o work properly
Non-Probability
Sampling
This Pho to by Unkn own Author is licensed u nder CC BY-SA-NC
Identifying Participants -
Sampling
• Qualitative researchers are more interested in
learning a lot about a relatively small number of
people, so random sampling is not usually used.
Lecture 2: Asking Questions and identifying Goals ~ Sheri Adekola
• Qualitative researchers:
choose people for the qualities they have—people
who can provide the greatest insight into the topic at
hand
choose participants who may help to undermine the
hierarchy of credibility
Uses non-probability sampling
Convenience sampling
Snowball sampling
Purposive sampling
Quota sampling
17
CONVENIENCE SAMPLING
• Convenience sampling provides easy access to the
participants.
• The sample is selected from elements of a population
that are easily accessible
• This sampling technique is quick and inexpensive
• Convenience samples are useful for pilot studies, testing the reliability of
measures to be used in a larger study, developing ideas, learning how do to
research, etc.
• It is also referred to as accidental or availability
sampling
Strengths Weaknesses
• Convenience and inexpensive • Generalization
PURPOSIVE SAMPLING
• Purposeful sampling is the most common sampling strategy. In
this type of sampling, participants are selected or sought after
based on pre-selected criteria based on the research question.
The participant must have first-hand experience with the topic (e.g. gang
involvement) and must be able to talk about it
• This sampling strategy is also called judgemental sampling, and
participants must meet the criteria in order to be included.
Strengths Weaknesses
• The ability to target niche • Open to selection bias and error
demographics in order to obtain
specific data points
QUOTA SAMPLING
• Quota sampling is a sampling technique whereby participant
quotas are pre-set prior to sampling.
• Typically, the researcher attempts to gather data from a certain
number of participants that have certain characteristics such as
age, gender, ethnicity, class, marital status, HIV status, etc.
Strengths of quota sampling
▪ Cheaper and easier to manage compared to random sampling
▪ Can be conducted much faster than random sampling
▪ Good for pilot tests, and exploratory research
Weakness of quota sampling
▪ Is not likely to be representative of the population
▪ Judgements about eligibility may be incorrect (e.g. a
researcher may misjudge a person’s age and mistakenly
disregard the person)
SNOWBALL SAMPLING
• In this method, the participants refer the researcher to others
who may be able to potentially contribute or participate in the
study.
• This method often helps researchers find and recruit
participants that may otherwise be hard to reach
• Snowball sampling is also known as chain referral sampling.
Strengths of Snowball Sampling
▪ The chain referral process allows the researcher to reach populations
that are difficult to sample when using other sampling methods.
▪ The process is cheap, simple and cost-efficient.
▪ This sampling technique needs little planning and less work compared to
other methods
Other Types of Sampling
Lecture 2: Asking Questions and identifying Goals ~ Sheri Adekola
22
Structured Observation
and Sampling
• Often, no sampling frame
E.g., a list of all people who were admitted to the
emergency room at a particular hospital
• May involve time sampling
E.g., an emergency room may be observed at random
times throughout the day
• May include place sampling
E.g, a study of student activities on campus may
Module #4 - Sheri Adekola
involve sampling places such as dining halls, pubs,
classrooms, etc.
• May include behaviour sampling
E.g., a researcher may want to observe every fifth
interaction between students and librarians at a
particular reference desk
Content Analysis
Sampling
Sampling Sampling
• Sampling media • Sampling dates
• For example, a study of • For example, if researching
newspaper articles may involve media portrayals of sex
sampling of different papers, of workers, one could use a
articles on a given topic, etc. random method to select the
years for which the media are
Module #4 - Sheri Adekola
to be analyzed
Review: Theoretical Sampling
Theoretical Sampling is meant to be an alternative strategy,
used “in order to discover categories and their properties
and to suggest the interrelationships into a theory”
• Theoretical sampling can involve people, settings, events,
time, and contexts
• In theoretical sampling, the researcher:
simultaneously collects and analyzes the data
decides what data to collect next and where to find them
Chapter 10 - Ethnography - Sheri Adekola
develops a theory in the process
• data collection (observing, interviewing, and collecting
documents) continues until the point of theoretical
saturation is reached:
No new or relevant data seem to be emerging regarding a
category
The relationships among categories are well established
and validated
Chapter 11 - Interviewing in Qualitative Research ~ Sheri Adekola
This Pho to by Unkn own Author is licensed u nder CC BY-SA-NC
Issues in Sampling
Reducing Non-Response
Call backs are useful—sometimes several are
necessary
For telephone interviews: Reassure prospective participants that you are not
out for material gain
Dress appropriately
For face-to-face contact: Be flexible to accommodate participants
Write a good covering letter explaining the reasons
Module #4 - Sheri Adekola
for the research
Make it personal by including the respondent’s name
and address in the covering letter and personally
signed
Mailed questionnaires should always be
For mailed questionnaires: accompanied by a stamped return envelope
Don’t allow the questionnaire to appear
unnecessarily bulky
Follow up individuals who do not reply at first,
possibly with two or three further mailings
Monetary incentives increase the response rate but
can be deemed unethical
Virtual Sampling Issues
• A major limitation of online surveys is that not
everyone is online and has the technical ability
to handle these kinds of questionnaires
• Many people have more than one email
address
• Some households have one computer but
several users
• Internet users are a biased sample of the
population
Module #4 - Sheri Adekola
Tend to be better educated, wealthier,
younger, more urban
• Few sampling frames exist for the general
online population
Chapter 11 - Interviewing in Qualitative Research ~ Sheri
Adekola
• ReadChapter 8 – Quantitative
Data Analysis
Chapter 11 - Interviewing in Qualitative Research ~ Sheri Adekola
This Photo by Unknown Author is licensed under CC BY-
SA