Research Proposal
1
MARK977: Research for Marketing Decisions
Dr. Thomas Lee Trimester 1, 2018
2
Sampling and
Data Collection
WEEK 6 READING: CHAPTERS 9 & 10
2
Learning objectives
Sampling Design and Procedure
1. Differentiate a sample from a census and identify the conditions which favor the use of a sample versus a census.
2. Discuss the sampling design process: definition of the target population, determination of the sampling frame, selection of sampling technique(s), determination of sample size, and execution of the sampling process.
3. Classify sampling techniques as nonprobability and probability sampling techniques.
4. Identify the conditions which favour the use of nonprobability sampling versus probability sampling.
MARK977 Research for Marketing Decisions T1 20183
MARK977 Research for Marketing Decisions T1 20184
3
Selecting samples
Identify target population
MARK977 Research for Marketing Decisions T1 20185
Basic definitions
• Population. A population is the aggregate of all the elements that share some common set of characteristics, and that comprise the universe for the purpose of the marketing research problem.
• Census. A census involves a complete enumeration of all the elements of a population.
• Sample. A sample, on the other hand, is a subgroup of the population selected for participation in the study.
MARK977 Research for Marketing Decisions T1 20186
4
Sample or census? When is census appropriate?
• If cost and time permit
• Population size is quite small (e.g., industrial products)
• Information is needed from every individual in the population
• Variance or variability in characteristics of interest is large
• Costs of making an incorrect decision or sampling errors are high
– Errors resulting from the particular sample selected being an imperfect representation of the population of interest (e.g., if the sample omitted a major airline like Qantas, the results could be misleading)
MARK977 Research for Marketing Decisions T1 20187
Sample or census? When is sample appropriate? • Population size is large
• Both cost and time associated with obtaining information from the population is high
• Quick decision is needed
• To increase response quality since more time can be spent on each interview (vs. cutting time short to accommodate entire population)
• Population being dealt with is homogeneous • If census is impossible, sampling is the only alternative (e.g., consumer
response from all over the world to a new advertising theme for Coca Cola) • If costs of non-sampling errors are high
• Attributed to a variety of causes (other than sampling-related errors), including errors in problem definition, questionnaire design, survey methods, interviewing techniques, etc. (e.g., interviewing errors due to lack of supervision) (vs. making same error for entire population)
MARK977 Research for Marketing Decisions T1 20188
5
Sample vs. census
MARK977 Research for Marketing Decisions T1 20189
CONDITIONS FAVOURING THE USE OF
Sample Census
1. Budget Small Large
2. Time available Short Long
3. Population size Large Small
4. Variance in the characteristic Small Large
5. Cost of sampling error Low High
6. Cost of nonsampling errors High Low
Error in sampling Total Error
▫ Difference between the true value (in the population) and the observed value (in the sample) of a variable
• Sampling Error
▫ Error is due to sampling (i.e., value obtained from sample representing population vs. true value obtained from entire population)
▫ Errors resulting from the particular sample selected being an imperfect representation of the population of interest (i.e., mismatch)
• Non-sampling Error
▫ Errors attributed to sources other than sampling, including design, administering, response and non-response (e.g., problem definition, scaling, questionnaire design, survey methods,
interviewing techniques, data preparation and analysis)
▫ Can be observed in both census and sample – key is to ensure research is designed appropriately and with care
MARK977 Research for Marketing Decisions T1 201810
6
Error in sampling
MARK977 Research for Marketing Decisions T1 201811
Sampling design process
MARK977 Research for Marketing Decisions T1 201812
7
Define the target population The target population is the collection of elements or objects that possess the information sought by the researcher and is defined in terms of: An element is the object about which or from which the
information is desired, e.g., the respondent. A sampling unit is an element, or a unit containing the element,
that is available for selection at some stage of the sampling process (i.e., level/unit of analysis – individuals within firm vs. firms within industry).
Extent refers to the geographical boundaries. Time is the time period under consideration.
MARK977 Research for Marketing Decisions T1 201813
The target population must be defined precisely. Defining the target population involves translating the marketing research problem into a precise statement of who should or should not
be included in the sample.
Defining the target population
MARK977 Research for Marketing Decisions T1 201814
8
Defining the sampling frame
• A sampling frame is a representation of the elements of the target population
• Consists of a list or set of directions for identifying the target population, for example: – Telephone book – Directory listing the firms in an industry (e.g.,
manufacturing and service firms operating in 20 different two-digit Standard Industrial Classification code industries – 20, 30, & 40)
– Mailing list purchased from a commercial organisation (e.g., IncNet Business Database)
– If study on student experience/satisfaction?
MARK977 Research for Marketing Decisions T1 201815
Select a sampling technique
MARK977 Research for Marketing Decisions T1 201816
Sampling Techniques
Nonprobability Sampling
Techniques
Probability Sampling
Techniques
9
Selecting a sampling procedure
MARK977 Research for Marketing Decisions T1 201817
Probability Sampling Techniques
Simple Random Sampling
Cluster Sampling
Stratified Sampling
Systematic Sampling
All population members have a known probability of being in the sample
Simple random sampling
In simple random sampling, each element in the population has a known and equal probability of selection.
1. Obtain an accurate sampling frame
– E.g., study focuses on SMEs within specific sectors (e.g., professional services) = 1000
2. Number each case in the sampling frame with a unique number from 0 – 1000
3. Select cases using random numbers until you reach target sample size
4. Similar to a lottery system or lucky draw
MARK977 Research for Marketing Decisions T1 201818
10
Simple random sampling example
MARK977 Research for Marketing Decisions T1 201819
A B C D E
1 6 11 16 21
2 7 12 17 22
3 8 13 18 23
4 9 14 19 24
5 10 15 20 25
Select five random
numbers from 1 to 25.
The resulting sample
consists of population
elements 3, 7, 9, 16,
and 24. Note, there is
no element from
Group C.
Systematic sampling
• In systematic sampling, the sample is chosen by selecting a random starting point and then picking every i-th element in succession from the sampling frame.
– Sampling cases at regular intervals (e.g., every 5th case after selecting a random starting point – 0 to 9)
• The sampling interval, i, is determined by dividing the population size (N) by the sample size (n) and rounding to the nearest integer (i.e., total population / sample size).
• For example: – Population = 100,000 elements – Sample = 1,000 – Sampling interval = 100 – Random number = 23 – Sample consists of elements 23, 123, 223, 323, 423, 523, etc.
MARK977 Research for Marketing Decisions T1 201820
11
Systematic sampling example
MARK977 Research for Marketing Decisions T1 201821
A B C D E
1 6 11 16 21
2 7 12 17 22
3 8 13 18 23
4 9 14 19 24
5 10 15 20 25
Select a random
number between 1 to
5, say 2.
The resulting sample
consists of population
2, (2+5=) 7, (2+5x2=)
12, (2+5x3=) 17, and
(2+5x4=) 22. Note, all
the elements are
selected from a single
row.
Stratified sampling • Stratified sampling is a two-step process in which the population is
partitioned into subpopulations, or strata.
1. Partitioning population into subpopulations or strata
2. Selecting elements from each stratum using random or systematic sampling
• The stratification variables should also be closely related to the characteristic of interest (e.g., by age, by income, by ethnicity, public- vs. private-sector firms, etc.).
– If study on student experience/satisfaction?
• The elements within a stratum should be as homogeneous as possible, but the elements in different strata should be as heterogeneous as possible.
MARK977 Research for Marketing Decisions T1 201822
12
Stratified sampling example
MARK977 Research for Marketing Decisions T1 201823
A B C D E
1 6 11 16 21
2 7 12 17 22
3 8 13 18 23
4 9 14 19 24
5 10 15 20 25
Randomly select a
number from 1 to 5
for each stratum, A to
E. The resulting
sample consists of
population elements
4, 7, 13, 19, and 21.
Note, one element
is selected from each
column.
Cluster sampling • For cluster sampling, sampling frame is complete list of clusters rather than
complete list of individual cases within the population
1. Target population is divided into mutually exclusive and collectively exhaustive subpopulations, or clusters (e.g., major AUS cities – Sydney, Melbourne, Brisbane, Perth, etc.)
2. A random sample of clusters is selected, based on a probability sampling technique such as SRS.
3. For each selected cluster, either all the elements are included in the sample (one-stage) or a sample of elements is drawn probabilistically (two-stage).
• Elements within a cluster should be as heterogeneous as possible, but clusters themselves should be as homogeneous as possible. Ideally, each cluster should be a small-scale representation of the population.
• Very cost effective
MARK977 Research for Marketing Decisions T1 201824
13
Types of cluster sampling
MARK977 Research for Marketing Decisions T1 201825
Cluster sampling example
MARK977 Research for Marketing Decisions T1 201826
A B C D E
1 6 11 16 21
2 7 12 17 22
3 8 13 18 23
4 9 14 19 24
5 10 15 20 25
Randomly select 3
clusters, B, D, and E.
Within each cluster,
randomly select one
or two elements. The
resulting sample
consists of population
elements 7, 18, 20, 21,
and 23. Note, no
elements are selected
from clusters A and C.
14
Stratified vs. cluster sampling
MARK977 Research for Marketing Decisions T1 201827
Homogeneity within group
Heterogeneity between groups
All groups are included
A complete sampling frame for the
entire stratified subpopulations should
be drawn.
Homogeneity between groups
Heterogeneity within groups
Random selection of groups
A sampling frame is needed only for the
clusters selected for the sample.
Stratified sampling Cluster sampling
Nonprobability sampling techniques
MARK977 Research for Marketing Decisions T1 201828
- Costs and trouble of developing sampling frames are eliminated - Used in:
• The exploratory stages of a research project • Pre-testing a questionnaire • Dealing with a homogeneous population • When operational ease is required
15
Convenience sampling
Convenience sampling attempts to obtain a sample of convenient elements. Often, respondents are selected because they happen to be in the right place at the right time.
use of students and members of social organizations
mall intercept interviews without qualifying the respondents
“people on the street” interviews MBA students for organizational research?
MARK977 Research for Marketing Decisions T1 201829
Convenience sampling example
MARK977 Research for Marketing Decisions T1 201830
A B C D E
1 6 11 16 21
2 7 12 17 22
3 8 13 18 23
4 9 14 19 24
5 10 15 20 25
Group D happens to
assemble at a
convenient time and
place. So all the
elements in this
Group are selected.
The resulting sample
consists of elements
16, 17, 18, 19, and 20.
Note, no elements are
selected from group
A, B, C, and E.
16
Judgmental sampling
Judgmental sampling is a form of convenience sampling in which the population elements are selected based on the judgment of the researcher. Common examples:
purchase engineers selected in industrial marketing research because they are considered to be representative of their respective companies
Several cities might be selected to represent a country
Student samples to be representative of young consumers?
MARK977 Research for Marketing Decisions T1 201831
Judgmental sampling example
MARK977 Research for Marketing Decisions T1 201832
A B C D E
1 6 11 16 21
2 7 12 17 22
3 8 13 18 23
4 9 14 19 24
5 10 15 20 25
The researcher considers groups B, C, and E to be typical and convenient. Within each of these groups one or two elements are selected based on typicality and convenience. The resulting sample consists of elements 8, 10, 13, 22, and 24. Note, no elements are selected from groups A and D.
17
Quota sampling
Quota sampling may be viewed as two-stage restricted judgmental sampling.
The first stage consists of developing control categories, or quotas, of population elements.
In the second stage, sample elements are selected based on convenience or judgment.
MARK977 Research for Marketing Decisions T1 201833
Control characteristic
Population composition
Sample composition
Gender Percentage Percentage Number
Male 48 48 480
Female 52 52 520
Total 100 100 1000
Quota sampling example
MARK977 Research for Marketing Decisions T1 201834
A B C D E
1 6 11 16 21
2 7 12 17 22
3 8 13 18 23
4 9 14 19 24
5 10 15 20 25
A quota of one element from each group, A to E, is imposed. Within each group, one element is selected based on judgment or convenience. The resulting sample consists of elements 3, 6, 13, 20, and 22. Note, one element is selected from each column or group.
18
Snowball sampling
In snowball sampling, an initial group of respondents is selected, usually at random.
After being interviewed, these respondents are asked to identify others who belong to the target population of interest.
Subsequent respondents are selected based on the referrals.
Useful for estimating characteristics that are rare in the population (e.g., locating marketing research interviewers)
MARK977 Research for Marketing Decisions T1 201835
Snowball sampling example
MARK977 Research for Marketing Decisions T1 201836
A B C D E
1 6 11 16 21
2 7 12 17 22
3 8 13 18 23
4 9 14 19 24
5 10 15 20 25
Elements 2 and 9 are selected randomly from groups A and B. Element 2 refers elements 12 and 13. Element 9 refers element 18. The resulting sample consists of elements 2, 9, 12, 13, and 18. Note, there is no element from group E.
Random Selection Referrals
19
Nonprobability or probability sampling?
• Non-probability sampling if: – Conducting exploratory research given that findings are
treated as preliminary – Non-sampling errors are an important factor because the
use of judgment may allow greater control over the sampling process
• Probability sampling if: – Conducting conclusive research because results are
projected to the target population – Sampling errors are an important factor because results are
projected to the target population (see disadvantages associated with non-probability techniques)
MARK977 Research for Marketing Decisions T1 201837
Nonprobability or probability sampling?
MARK977 Research for Marketing Decisions T1 201838
CONDITIONS FAVOURING THE USE OF
Factors Nonprobability
Sampling Probability Sampling
Nature of research Exploratory Conclusive
Relative magnitude of sampling and
nonsampling errors
Nonsampling errors
are larger
Sampling errors are
larger
Variability in the population Homogeneous
(low)
Heterogeneous
(high)
Statistical considerations Unfavorable Favorable
Operational considerations
(e.g., cost and time) Favorable Unfavorable
20
Non-response problems • Respondents may:
– Refuse to respond – Respond partially – Lack the ability to respond – Be inaccessible
• Non-response bias = bias that arises when actual respondents differ from those who refuse to participate (in terms of characteristics, ways of thinking, etc.) in ways that affect survey results.
• Sample size has to be large enough to allow for non- response
• Common in mail surveys
MARK977 Research for Marketing Decisions T1 201839
Solutions to non-response problems
• Improve research design to reduce the number of non- responses (e.g., include incentives)
• Repeat the contact one or more times (call back or remind) to try to reduce non-responses
MARK977 Research for Marketing Decisions T1 201840
21
Determine the sample size
• Importance of decision and accuracy level required in results – For important decisions, more information is necessary and the
information should be obtained more precisely • Nature of the research
– Exploratory vs. conclusive • Nature of the analysis
– Level/unit of analysis (e.g., firm vs. group/team vs. individual) – Advanced statistical techniques (e.g., AMOS SEM)
• Sample sizes used in similar studies – And the response rates common of a specific method in literature
• Resource constraints • Variability and size of the population
MARK977 Research for Marketing Decisions T1 201841
Sample sizes for different population sizes
MARK977 Research for Marketing Decisions T1 201842
Population 5% (95% accuracy) 1% (99% accuracy)
50 44 50
100 79 99
250 151 244
500 217 475
1,000 278 906
2,000 322 1655
5,000 357 3288
10,000 370 4899
100, 000 383 8762
1,000,000 384 9513
Confidence level
22
Sampling decisions
• Exam stress example • Important issues to consider:
– Who – How – What – Threat of potential biases and errors
MARK977 Research for Marketing Decisions T1 201843
MARK977 Research for Marketing Decisions T1 201844
23
Learning objectives
Data Collection Procedures
1. Describe the field work or data collection process and explain the selection, training, and supervision of field workers, the validation of field work, and the evaluation of field workers.
2. Discuss the training of field workers in making the initial contact, asking the questions, probing, recording the answers, and terminating the interview.
3. Discuss the supervision of field workers in terms of quality control and editing, sampling control, control of cheating, and central office control.
4. Describe the evaluation of field workers in areas of cost and time, response rates, quality of interviewing, and the quality of data.
MARK977 Research for Marketing Decisions T1 201845
Data collection
• Field work (or data collection) – Field workers make contact with respondents, administer
questionnaire, record data, and turn in completed questionnaires for processing
– May occur in the field (e.g., personal in home, mall intercept) or from an office (e.g., telephone, mail)
• Field workers – Personnel involved in the data collection process, including: – A personal interviewer administering questionnaires door to door – An interviewer intercepting shoppers in a mall – A telephone interviewer calling from a central location – A worker mailing questionnaires from an office or posting them
on a website
MARK977 Research for Marketing Decisions T1 201846
24
The field work/data collection process
MARK977 Research for Marketing Decisions T1 201847
Selection of field workers
The selection of field workers requires the researcher to:
• Develop job specifications for the project, taking into account the mode of data collection.
• Decide what characteristics the field workers should have (to match respondents’ characteristics and nature of the problem being addressed).
• Recruit appropriate individuals.
MARK977 Research for Marketing Decisions T1 201848
25
General qualifications of field workers
• Healthy. Field workers must have the stamina required to do the job.
• Outgoing. The interviewers should be able to establish rapport with the respondents.
• Communicative. Effective speaking and listening skills are a great asset.
• Pleasant appearance. If the field worker's physical appearance is unpleasant or unusual, the data collected may be biased.
• Educated. Interviewers must have good reading and writing skills. • Experienced. Experienced interviewers are likely to do a better
job.
MARK977 Research for Marketing Decisions T1 201849
Training field workers
MARK977 Research for Marketing Decisions T1 201850
26
Training field workers
• Making the Initial Contact. Interviewers should be trained to make opening remarks that will convince potential respondents that their participation is important. When rejected due to inconvenience, ask for a rescheduling.
• Asking the Questions 1. Be familiar with the questionnaire. 2. Ask the questions in the order in which they appear in the
questionnaire. 3. Use the exact wording given in the questionnaire. 4. Read each question slowly. 5. Repeat questions that are not understood. (even a slight change in the wording, sequence, or manner in which the question is asked can distort its meaning and bias the response)
MARK977 Research for Marketing Decisions T1 201851
Training field workers (cont.)
• Probing. Motivating respondents to enlarge on, clarify, or explain their answers. Some commonly used probing techniques are:
1. Repeating the question.
2. Repeating the respondent's reply.
3. Using a pause or silent probe.
4. Eliciting clarification
MARK977 Research for Marketing Decisions T1 201852
27
Training field workers (cont.)
• Recording the Answers. Guidelines for recording answers to unstructured questions are:
1. Record responses during the interview. 2. Use the respondent's own words (verbatim). 3. Do not summarize or paraphrase the respondent's answers. 4. Include everything that pertains to the question objectives. 5. Include all probes and comments. 6. Repeat the response as it is written down.
• Terminating the Interview. The respondent should be left with a positive feeling about the interview. Thank the respondent and express appreciation.
MARK977 Research for Marketing Decisions T1 201853
Supervision of field workers Quality Control. This requires checking to see if the field
procedures are being properly implemented. If problems are detected, supervisors should discuss them with interviewers and provide additional training where necessary.
Sampling Control. The supervisor attempts to ensure that the interviewers are strictly following the sampling plan rather than selecting sampling units based on convenience or accessibility.
Control of Cheating. Occurs when interviewers fill in fake answers without contacting respondents. Cheating can be minimized through proper training, supervision, and validation.
Central Office Control. Supervisors provide quality and cost- control information to the central office in the form of an overall progress report.
MARK977 Research for Marketing Decisions T1 201854
28
Validation of field work
• In the validation of field work, the supervisors call 10 - 25% of the respondents to inquire whether the field workers actually conducted the interviews.
• The supervisors ask about the length and quality of the interview, reaction to the interviewer, and basic demographic data.
• The demographic information is cross-checked against the information reported by the interviewers on the questionnaires.
MARK977 Research for Marketing Decisions T1 201855
Evaluation of field workers
• Cost and Time. The interviewers can be compared in terms of the total cost (salary and expenses) per completed interview (e.g., high completes and low travel/food expenditure).
• Response Rates. It is important to monitor response rates on a timely basis so that corrective action can be taken if these rates are too low (e.g., problems with introductions or the way they conduct the interview).
MARK977 Research for Marketing Decisions T1 201856
29
Evaluation of field workers
• Quality of Interviewing. To evaluate interviewers on the quality of interviewing, the supervisor must directly observe the interviewing process (e.g., making appropriate initial contact, asking questions in order and as worded, interpersonal skills during the interview, manner in which interview is terminated).
• Quality of Data. The completed questionnaires of each interviewer should be evaluated for the quality of data (e.g., legible recorded data, little incompletes, answers to unstructured questions are recorded verbatim and complete).
MARK977 Research for Marketing Decisions T1 201857