Session 7

Field Work: Data Collection & Preparation

SPSS Basic Operation
 Marketing Research Process
Step 1&2 :
Step 1: Defining the Problem Management decision
problem/Marketing Research
problem
Step 2: Developing an Approach to the Problem
Step 3:
Research Design
- Exploratory/Descriptive/Causal
Step 3: Formulating a Research Design
Research
Source of data
Step 4: Doing Field Work or Collecting Data - Primary and secondary data
Data Collection Method
- Focus group
Step 5: Preparing and Analyzing Data - In-depth interview
- Projective techniques
- Survey
- Observation
Step 6: Preparing and Presenting the Report - Experiment
Questionnaire Design
Sampling Design
 Step 3: Field work / Data Collection

• Those who design the research rarely

collect marketing research data.
• All work should be streamlined and
well controlled.
• All field work involves selection,
training, and supervision of those who
collect the data
 Training Field-Workers
Making the initial contact
• Ask permission e.g. “May I have some of your valuable time?”

Asking questions
• Should ask every question exactly as worded on the questionnaire. Repeat the
question if necessary.

Probing
• “Any others?”, “Could you tell me more?”

Recording answers
• Use the same format and conventions to record the interview
• Record the responses verbatim for unstructured questions

Terminating the interview

• Should let with a positive feeling about the interview
 Supervising Field-Workers

Supervision
of field-
workers

Quality
Sampling Control of Central office
control and
control cheating control
editing
 Validation and Evaluation
• Validation of fieldwork • Evaluation of field-workers
• - to evaluate field-workers to
– i.e. to check if field provide them with feedback on
workers submit the their performance.
authentic interviews
– Supervisors call 10 to 25%
of the respondents Evaluation
Criteria

• Ask about the length and

quality of the interview, Quantity Quality
reaction to the
interviewer, and basic
Cost and Response Quality of Quality of
demographic data for time rates interviewing data

cross-checking
Step 4: Preparing and Analyzing Data

Questionnaire Checking

Editing

Coding

Transcribing (i.e. data entry)

Data Cleaning

Selecting a Data Analysis Strategy

 Step 4: Preparing and Analyzing Data
Questionnaire checking
• Checking for completeness
• Missing pages
• The questionnaire is answered by someone
who does not qualify for participation
 Step 4: Preparing and Analyzing Data
Editing
• Reviewing questionnaires to increase accuracy
and precision
• Identify illegible, incomplete, inconsistent, or
ambiguous responses
– Returning to the field to get better data
– Assigning missing values
– Discarding unsatisfactory respondents
 A survey on consumer complaints
Research Report
In a U.S. study examining consumer complaints, 800
questionnaires were mailed to households during the summer
period of 2013 in each of two service categories: medical care and
banking services. 493 filled-in questionnaires were received with
61.6% response rate. Among them, 320 were from the medical
care while 173 were from the banking services. The returned
questionnaires were carefully checked and edited. Those
respondents who did not meet the qualifying criteria being
unable to recall a recent dissatisfying experience) and those with
a large number of missing values or missing values on key
variables were discard. Only 453 usable samples that remained
(285 for medical care while 168 for banking services).
 Step 4: Preparing and Analyzing Data
Coding
• Use codebook containing coding instructions and the
necessary information about variables in the data
set.

• Assigning a code, usually a number, to each possible

response to each question.

• Editing and Coding are always doing at the same time!

 Code book Example (short version)
Question Variable name Coding Instruction
ID Questionnaire no. 1-1000
Q1 First_visit 1:Yes
2:No
9: missing

Q1b Visit_time 000-100 time

999: missing
Q2 Purpose_visit 1: vacation
2: business/meeting
3: visiting friends/relatives
4: other (study)
5: other
9: missing

Q3 Nights 000-100 nights

999: missing
Q4 Done_today 1: Stanley Market
2: Ocean Park
3: Peak
Open-ended 4: shopping at Mongkok
question 5: other
9: missing

Q5 Sat_venue 5:very satisfactory

Sat_info 4:satisfactory
Sat_facilities 3:average
Sat_atmosphere 2:unsatisfactory
Sat_welcome 1:very unsatisfactory
Sat_overall 9: NA or missing
Code book
 Step 4: Preparing and Analyzing Data
Transcribing

• Transcribing – data entry

 Code Book for Super Sandwiches Comment Card
Question Variable name Coding Instruction
Questionnaire ID 1-100
Date mm/dd/yyyy
Store_time hh:mm
Store_location 1. HK
2. KLN
3. NT
9: missing

Q1 Overall_exp 1. Below your expectation

Product 2. Ok but not that great
Price 3. Met your expectation
Service 4. Surpassed your expectation
Attitude 9: missing
Ambience
Q2 Time 1. First visit
2. Once a month or less
3. Bi-weekly
4. Once a week
5. Twice a week
6. 3 times a week or more
9: missing
Q3 Revisit 1. Yes
2. No
9: missing
Q3b Not_visit String with 30 width
 Fill in the form
Data Collection
• Assume you are invited to fill in “Super
sandwiches” comment card
– Date:
– Time:
– Location:
– Q1-Q3:
 Editing and Data Entry
• Based on Codebook, use red ball pen to edit
your questionnaire.
 Data Entry

• Input your data into SPSS by

– 1) define variable view
– 2) input your data (ONE respondent)
 Internet Survey Platform

https://www.cityu.edu.hk/questionpro/

DON’T use Google Survey!

21
 Step 4: Preparing and Analyzing Data
Data cleaning
• Data cleaning - Consistency checks
– Out-of-range data values
• E.g. Satisfaction rate from 1-to-5 scale; 9 is assigned for
missing  0, 6, 7 and 8 are out-of-range data

Use Analyze/descriptive statistics/frequencies

Example: Research Proposal for
KMB Bus Survey
Example: Research Proposal for
KMB Bus Survey(Con’t)
Step 5: Preparing and Analyzing Data

Questionnaire Checking

Editing

Coding

Transcribing

Data Cleaning

Selecting a Data Analysis Strategy

 Step 5: Preparing and Analyzing Data
Selecting a Data Analysis

Review research objectives, problems and design

Characteristic of data (i.e. the measurement scales used exert a strong

influence of the choice of statistical techniques)

Properties of statistical techniques

Background and philosophy of the researcher

Data analysis strategy

Example: Proposal for KMB Bus Survey
Example: Proposal for KMB Bus Survey
• The End!