Title: SAMPLING DESIGN AND PROCEDURE
1Lecture 9
- SAMPLING DESIGN AND PROCEDURE
2Population and Sample
- Population
- The entire group that the researcher wishes to
investigate - Element
- A single member of the population
3Population and Sample
- Population (Sampling) Frame
- A listing of all the elements in the population
from which the sample is drawn - Sample
- A subset of the population
- Subject
- A single member of the sample
4CENSUS
- INVESTIGATION OF ALL INDIVIDUAL ELEMENTS THAT
MAKE UP A POPULATION
5When Is A Census Appropriate?
Necessary
Feasible
6TARGET POPULATION
- RELEVANT POPULATION
- OPERATIONALLY DEFINE
- COMIC BOOK READER?
7Why Sample?
Availability of elements
Lower cost
Sampling provides
Greater accuracy
8SAMPLING FRAME
- A LIST OF ELEMENTS FROM WHICH THE SAMPLE MAY BE
DRAWN - WORKING POPULATION
- MAILING LISTS - DATA BASE MARKETERS
- SAMPLING FRAME ERROR
9Sampling
- Process of selecting a sufficient number of
elements from the population - Reasons for Sampling practicality (time and
resources), destructive sampling - Need for a representative sample
10SAMPLING UNITS
- GROUP SELECTED FOR THE SAMPLE
- PRIMARY SAMPLING UNITS (PSU)
- SECONDARY SAMPLING UNITS
- TERTIARY SAMPLING UNITS
11TWO MAJOR CATEGORIES OF SAMPLING
- PROBABILITY SAMPLING
- KNOWN, NONZERO PROBABLITY FOR EVERY ELEMENT
- NONPROBABLITY SAMPLING
- PROBABLITY OF SELECTING ANY PARTICULAR MEMBER IS
UNKNOWN
12Probability and NonprobabilitySampling
- Probability Sampling
- Elements in the population have known chance of
being chosen - Used when the representativeness of the sample is
of importance - Nonprobability Sampling
- The elements do not have a known or predetermined
chance of being selected as subjects
13Probability Sampling
- Unrestricted/Simple Random Sampling
- Every element in the population has a known and
equal chance of being selected as a subject - Has the least bias and offers the most
generalizability - Restricted/Complex Probability Sampling
- Systematic Sampling
- Stratified Random Sampling
- Cluster Sampling (USM, UM, etc)
- Area Sampling
- Double Sampling (USM and then grad students)
14PROBABLITY SAMPLING
- SIMPLE RANDOM SAMPLE
- SYSTEMATIC SAMPLE
- STRATIFIED SAMPLE
- CLUSTER SAMPLE
- MULTISTAGE AREA SAMPLE
15SIMPLE RANDOM SAMPLING
- a sampling procedure that ensures that each
element in the population will have an equal
chance of being included in the sample
16Simple Random
- Advantages
- Easy to implement with random dialing
- Disadvantages
- Requires list of population elements
- Time consuming
- Uses larger sample sizes
- Produces larger errors
- High cost
17SYSTEMATIC SAMPLING
- A simple process
- every nth name from the list will be drawn
18Systematic
- Advantages
- Simple to design
- Easier than simple random
- Easy to determine sampling distribution of mean
or proportion
- Disadvantages
- Periodicity within population may skew sample and
results - Trends in list may bias results
- Moderate cost
19STRATIFIED SAMPLING
- Probability sample
- Subsamples are drawn within different strata
- Each stratum is more or less equal on some
characteristic - Do not confuse with quota sample
20Stratified
- Advantages
- Control of sample size in strata
- Increased statistical efficiency
- Provides data to represent and analyze subgroups
- Enables use of different methods in strata
- Disadvantages
- Increased error will result if subgroups are
selected at different rates - Especially expensive if strata on population must
be created - High cost
21CLUSTER SAMPLING
- The purpose of cluster sampling is to sample
economically while retaining the characteristics
of a probability sample. - The primary sampling unit is no longer the
individual element in the population. - The primary sampling unit is a larger cluster of
elements located in proximity to one another.
22EXAMPLES OF CLUSTERS
Population Element Possible Clusters in Malaysia
Malaysian adult population States Districts
Metropolitan Statistical Area Census
tracts Blocks Households
23EXAMPLES OF CLUSTERS
Population Element Possible Clusters in Malaysia
College seniors Colleges Manufacturing
firms Districts Metropolitan Statistical
Areas Localities Plants
24EXAMPLES OF CLUSTERS
Population Element Possible Clusters in Malaysia
Airline travelers Airports Planes Sports
fans Football stadia Basketball
arenas Baseball parks
25Cluster
- Advantages
- Provides an unbiased estimate of population
parameters if properly done - Economically more efficient than simple random
- Lowest cost per sample
- Easy to do without list
- Disadvantages
- Often lower statistical efficiency due to
subgroups being homogeneous rather than
heterogeneous - Moderate cost
26Stratified and Cluster Sampling
- Stratified
- Population divided into few subgroups
- Homogeneity within subgroups
- Heterogeneity between subgroups
- Choice of elements from within each subgroup
- Cluster
- Population divided into many subgroups
- Heterogeneity within subgroups
- Homogeneity between subgroups
- Random choice of subgroups
27Double
- Advantages
- May reduce costs if first stage results in enough
data to stratify or cluster the population
- Disadvantages
- Increased costs if discriminately used
28Nonprobability Samples
No need to generalize
Feasibility
Limited objectives
Issues
Cost
29Nonprobability Sampling Methods
Convenience
Judgment
Quota
Snowball
30NONPROBABLITY SAMPLING
- CONVENIENCE
- JUDGMENT
- QUOTA
- SNOWBALL
31Nonprobability Sampling
- Convenience Sampling
- Based on availability, e.g. students in a
classroom - Purposive Sampling
- Specific targets, because they posses the desired
info - Judgement sampling
- Quota sampling
32CONVENIENCE SAMPLING
- also called haphazard or accidental sampling
- the sampling procedure of obtaining the people or
units that are most conveniently available
33QUOTA SAMPLING
- ensures that the various subgroups in a
population are represented on pertinent sample
characteristics - to the exact extent that the investigators desire
- it should not be confused with stratified sampling
34JUDGMENT SAMPLING
- also called purposive sampling
- an experienced individual selects the sample
based on his or her judgment about some
appropriate characteristics required of the
sample member
35SNOWBALL SAMPLING
- a variety of procedures
- initial respondents are selected by probability
methods - additional respondents are obtained from
information provided by the initial respondents
36Area Sampling
37Sample Size
- Factors Determining Sample Size
- Homogeneity of population
- Level of confidence
- Precision
- Cost, Time and Resources
38Larger Sample Sizes
Population variance
Number of subgroups
Desired precision
When
Small error range
39Roscoes Rule of Thumb
- gt30 and lt500 appropriate for most research
- Not less than 30 for each sub-sample
- In multivariate analysis, 10 times or more the
number of variables - Simple experiment with tight controls, 10-20
quite sufficient
40WHAT IS THE APPROPRIATE SAMPLE DESIGN
- DEGREE OF ACCURACY
- RESOURCES
- TIME
- ADVANCED KNOWLEDGE OF THE POPULATION
- NATIONAL VERSUS LOCAL
- NEED FOR STATISTICAL ANALYSIS
41What Is A Good Sample?
Precise
Accurate
42AFTER THE SAMPLE DESIGN IS SELECTED
- DETERMINE SAMPLE SIZE
- SELECT ACTUAL SAMPLE UNITS
- CONDUCT FIELDWORK
43SYSTEMATIC ERRORS
- NONSAMPLING ERRORS
- UNREPRESENTATIVE SAMPLE RESULTS
- NOT DUE TO CHANCE
- DUE TO STUDY DESIGN OR IMPERFECTIONS IN EXECUTION
44ERRORS ASSOCIATED WITH SAMPLING
- SAMPLING FRAME ERROR
- RANDOM SAMPLING ERROR
- NONRESPONSE ERROR
45RANDOM SAMPLING ERROR
- THE DIFFERENCE BETWEEN THE SAMPLE RESULTS AND THE
RESULT OF A CENSUS CONDUCTED USING IDENTICAL
PROCEDURES - STATISTICAL FLUCTUATION DUE TO CHANCE VARIATIONS
46Stages in the Selection of a Sample
Define the target population
Select a sampling frame
Determine if a probability or nonprobability
sampling method will be chosen
Plan procedure for selecting sampling units
Determine sample size
Select actual sampling units
Conduct fieldwork
47End of lesson