Professional Documents
Culture Documents
Sampling Overview
DEPARTMENT OF STATISTICS
A quote …
How I Learned to Stop Worrying and Love the Survey Cycle
- Mark Twain
DEPARTMENT OF STATISTICS
The brief
Intro/first considerations
How I Learned to Stop Worrying and Love the Survey Cycle
First considerations
Who do I need to survey?
How do I get representative samples?
Representative sampling strategies
Accuracy statements
Developing the questionnaire
Presenting the results
How do I manage this beast?
DEPARTMENT OF STATISTICS
Excellent on line resources
How I Learned to Stop Worrying and Love the Survey Cycle
www.stats.govt.nz/NR/rdonlyres/CA923AA8-BDF6-
4EAD-834F-
573F04EEF7A9/0/AGuidetoagoodSurvey.pdf
www.perseus.com/surveytips/Survey_101.htm
www.whatisasurvey.info
DEPARTMENT OF STATISTICS
The process
How I Learned to Stop Worrying and Love the Survey Cycle
STAGE 2:
RESEARCH Choose Design
PLAN/DESIGN
Determine Trade-offs Inventory Resources
Assess Feasibility
How I Learned to Stop Worrying and Love the Survey Cycle
DEPARTMENT OF STATISTICS
How I Learned to Stop Worrying and Love the Survey Cycle
DEPARTMENT OF STATISTICS
First considerations
DEPARTMENT OF STATISTICS
Motivating case study: crime & punishment
How I Learned to Stop Worrying and Love the Survey Cycle
Do I have to do a survey?
Literature search
Expert advice
DEPARTMENT OF STATISTICS
Motivating case study: crime & punishment
How I Learned to Stop Worrying and Love the Survey Cycle
Introduction 1
100%
100%
90%
90%
80%
% Voted Sark (who voted)
80%
% Voted Sark (who voted)
70%
70%
60%
60%
2
50% R = 85%
50%
40%
40%
30%
30%
20%
20%
10%
10%
0%
0%
0% 20% 40% 60% 80% 100% 120%
0% 20% 40% 60% 80% 100% 120%
% Speak Melanesian
% Speak Melanesian
DEPARTMENT OF STATISTICS
Failing this, I will need to conduct a survey
How I Learned to Stop Worrying and Love the Survey Cycle
(select)
Population Sample
(estimate)
Parameter Statistic
true proportion sample proportion
true mean sample mean
DEPARTMENT OF STATISTICS
Motivating case study: crime & punishment
How I Learned to Stop Worrying and Love the Survey Cycle
“While no nation-wide
survey focussing solely
on attitudes towards
crime and criminal
justice issues has
previously been
conducted in New
Zealand, some studies
have touched on related
topics. For example, in
1996, the National
Survey of Crime
Victims (Young et al.
How I Learned to Stop Worrying and Love the Survey Cycle
DEPARTMENT OF STATISTICS
How I Learned to Stop Worrying and Love the Survey Cycle
DEPARTMENT OF STATISTICS
Examples:
Eligible voters
Person-to-person survey
was conducted…
How do I need to survey?
DEPARTMENT OF STATISTICS
How I Learned to Stop Worrying and Love the Survey Cycle
Types of surveys:
mail/web surveys
telephone surveys
Person-to-person interviews.
Types of surveys
DEPARTMENT OF STATISTICS
How I Learned to Stop Worrying and Love the Survey Cycle
DEPARTMENT OF STATISTICS
Web survey example:
DEPARTMENT OF STATISTICS
Telephone survey example
How I Learned to Stop Worrying and Love the Survey Cycle
DEPARTMENT OF STATISTICS
How much $$$ is needed?
DEPARTMENT OF STATISTICS
How do I sample these people?
How I Learned to Stop Worrying and Love the Survey Cycle
Non-representative samples
Self-selection bias
Convenience/judgment/snowball sampling
DEPARTMENT OF STATISTICS
Non-representative samples
How I Learned to Stop Worrying and Love the Survey Cycle
4.5% responded
Population
How?
Representative samples: sample frames
DEPARTMENT OF STATISTICS
How I Learned to Stop Worrying and Love the Survey Cycle
Undercoverage
Sample frame
Duplicated units (perhaps under different spellings
or ID numbers)
White Pages
Naïve approach
E.g. Mitofsky-Waksberg
Take banks of possible phone numbers, and
select phone numbers more intensively from
banks that have larger proportions of listed
numbers
Increased hit rate to 60% in US
Pseudo-RDD methods using banks centered on
valid “seed” phone numbers are sometimes used
DEPARTMENT OF STATISTICS
Household sampling for in-home surveys
How I Learned to Stop Worrying and Love the Survey Cycle
Area sample
Household sample
Business Directory
How I Learned to Stop Worrying and Love the Survey Cycle
DEPARTMENT OF STATISTICS
DEPARTMENT OF STATISTICS
How I Learned to Stop Worrying and Love the Survey Cycle
Representative sampling
strategies
DEPARTMENT OF STATISTICS
Types of representative sampling strategies
How I Learned to Stop Worrying and Love the Survey Cycle
Sample design:
Accuracy statements
Sample
m ( population mean)
The sample mean falls here only because
Sampling error
certain randomly selected observations
were included in the sample
x ( sample mean )
DEPARTMENT OF STATISTICS
Margin of error
A margin of error of 3% means that over the long
How I Learned to Stop Worrying and Love the Survey Cycle
1
Margin of Error
n
where n is the sample size.
DEPARTMENT OF STATISTICS
Sampling errors
How I Learned to Stop Worrying and Love the Survey Cycle
Process errors:
Examples include measurement error,
interviewer error, and processing error.
It can be minimised by proper interviewer
training, good questionnaire design, pre-testing,
and careful management of the data recording
process.
The problem is most serious when a bias is created.
DEPARTMENT OF STATISTICS
Non-sampling errors…
How I Learned to Stop Worrying and Love the Survey Cycle
Selection bias
Non-response errors
Population
Training of interviewers
Pilot questionnaire
DEPARTMENT OF STATISTICS
Be as short as possible
DEPARTMENT OF STATISTICS
A good questionnaire must:
How I Learned to Stop Worrying and Love the Survey Cycle
Think about the way you intend to use the collected data when
preparing the questionnaire
Questions will also depend on how you are getting the data e.g.
CATI, person to person, mail/web
DEPARTMENT OF STATISTICS
Using focus groups
How I Learned to Stop Worrying and Love the Survey Cycle
Motivation
Why is respondent going to/not participate
Political polls
Do I need incentives $$$$
DEPARTMENT OF STATISTICS
Some types of questions
How I Learned to Stop Worrying and Love the Survey Cycle
Open-ended questions
Disadvantages:
Advantages:
Obtains unanticipated
Flexibility in responsesanswers
difficult to code and
analyse
May better reflect respondent’s thoughts/beliefs
Provides incomplete
Appropriate when listorofunintelligible answers
possible answers is
excessive
DEPARTMENT OF STATISTICS
Close-ended questions
How I Learned to Stop Worrying and Love the Survey Cycle
Types of Exercises:
Aerobics
Basketball
Swimming
Weightlifting
DEPARTMENT OF STATISTICS
Two-way forced choice
How I Learned to Stop Worrying and Love the Survey Cycle
Yes No
Ranked
DEPARTMENT OF STATISTICS
How I Learned to Stop Worrying and Love the Survey Cycle
Strongly Strongly
Agree Agree Neutral Disagree Disagree
1 2 3 4 5
DEPARTMENT OF STATISTICS
Closed-ended questions
How I Learned to Stop Worrying and Love the Survey Cycle
Advantages:
Disadvantages:
Answers
Obtains more
relative
reliable
to response
answersscale provided
Respondent's
Meaning of responses
choice not
more
among
meaningful
listed alternatives
to researcher
Choices
Straightforward
listed communicate
analysis kind of response wanted
DEPARTMENT OF STATISTICS
Writing good survey questions
How I Learned to Stop Worrying and Love the Survey Cycle
No double negatives
It is not the case that I have never cheated on my
tax returns
Eliminate vagueness or poorly-defined terms
How many times in the past year have you talked
with a doctor about your health?
Objectionable/Irrelevant question
How old are you?
DEPARTMENT OF STATISTICS
Discrete questions/responses
How I Learned to Stop Worrying and Love the Survey Cycle
DEPARTMENT OF STATISTICS
Discrete questions/responses
DEPARTMENT OF STATISTICS
Limit response format (7±2)
Quality (Poor-Excellent)
Party Support
“Under MMP you get two votes.
One is for a political party and is called a party vote.
The other is for your local M.P. and is called an
electorate vote.”
DEPARTMENT OF STATISTICS
Example: One News Colmar Brunton poll
How I Learned to Stop Worrying and Love the Survey Cycle
Party Vote*
“Firstly thinking about the Party Vote which is for
a political party.
Which political party would you vote for?”
IF DON’T KNOW –
“Which one would you be most likely to vote for?”
DEPARTMENT OF STATISTICS
Always seek others’ advice
How I Learned to Stop Worrying and Love the Survey Cycle
Pre-test on colleagues
30
25
20
%
15
10
0
<=10% 10-19 20-29 30-39 40-49 50-59 60-69 79-79 80-89
Violent crime/100 incidents
60
50
40
Crime
30
20
10
0
ty l e e e e al
es cia nc ag us tiv u
n s o l e m b tr a ex
o ti io A S
ish an V Da rty in
is
D d rty p e m
an e o d
gs o p Pr A
ru Pr
D
%
DEPARTMENT OF STATISTICS
Lessons
How I Learned to Stop Worrying and Love the Survey Cycle
DEPARTMENT OF STATISTICS
You don’t have to be boring
DEPARTMENT OF STATISTICS
Graphical excellence
How I Learned to Stop Worrying and Love the Survey Cycle
Avoid distortion
Encourage comparisons
Round drastically
DEPARTMENT OF STATISTICS
The clearer you see the target, the more easily you can
see if you hit it or not.
DEPARTMENT OF STATISTICS
Always communicate
How I Learned to Stop Worrying and Love the Survey Cycle
Always discuss:
Your goals
Be honest
Assume nothing
STAGE 2:
RESEARCH Choose Design
PLAN/DESIGN
Determine Trade-offs Inventory Resources
Assess Feasibility
DEPARTMENT OF STATISTICS
Is it worth all the effort?
How I Learned to Stop Worrying and Love the Survey Cycle
- Mark Twain
How I Learned to Stop Worrying and Love the Survey Cycle
DEPARTMENT OF STATISTICS
Fini
How I Learned to Stop Worrying and Love the Survey Cycle
DEPARTMENT OF STATISTICS
Presentation
How I Learned to Stop Worrying and Love the Survey Cycle
DEPARTMENT OF STATISTICS
DEPARTMENT OF STATISTICS
Statistics NZ’s
A Guide To Good Survey Design