Chapter 6 - Primary-Data Collection

I. Data Collection Methods
example: The Gap

Primary Data	Data collected specifically for a research project Collect when secondary data are Unavailable Inappropriate can be collected through a number of different methods sometimes more than one method can apply to a single problem
Two Broad Approaches	Same basic data collection methods can be used under each. Although the formality or flexibility of the data collection process varies Nature of the sample varies Conditions under which data are collected vary

Questioning Approach	Observation Approach
Respondents play an active role Interview or a formal questionnaire Question design Can use either for exploratory, descriptive, or experimental Not all questioning or interviewing situations use formal questionnaires Questionnaire is a tool that is used in many, but not all, research projects	Passive In-person or mechanical devices Time consuming Can use either for exploratory, descriptive, or experimental

Observational Approaches example: Johnson Controls
Covert observational research	Researchers do not identify themselves. Either they mix in with the subjects undetected observe from a distance. The advantages of this approach are: It is not necessary to get the subjects’ cooperation Subjects’ behavior will not be contaminated by the presence of the researcher. Some researchers have ethical misgivings with this approach
Overt observational research	Researchers identify themselves as researchers Researchers explain the purpose of their observations. Subjects tend to modify their behavior when they know they are being watched. They portray their “ideal self” rather than their true self
Researcher Participation	The researcher participates in what they are observing They get a finer appreciation of the phenomena. Researchers that participate tend to lose their objectivity.

II. Questioning Versus Observation

Not interchangeable
Each has certain unique capabilities.
Advantages may not hold true in every situation calling for primary-data collection.
Neither approach is likely to always be better than the other along each of the following dimensions.

A.Versatility	B.Time and Cost
Observation	Observation
limited to collecting data about visible characteristics or variables may be inconclusive How does a customer feel?	Can involve large amount of inactivity
Questioning	Questioning
may not be possible. Difficult to get answers from children very versatile in the types of data it generates.	Usually less expensive Usually less time consuming A variety of avenues are available Can search for the most rich data source More flexibility in the collection process.
C.Data Accuracy	D. Respondent Convenience
Questioning	Questioning
Unable to recall reaction/purchase–Chrysler Minivan Unwilling or unable to reveal the truth Erroneous answers Survey research did not support the introduction of minivan	Answers specific questions Inaccurate Participation problems
Observing	Observing
Observation is more accurate for behavior Lack of interaction minimizes data distortion Pre-release observation of “Junior”(movie) showed support, but the movie was a box office failure Subjectivity of questioner Carelessness of an observer. Respondents' inability or unwillingness to provide accurate data	Respondents do not participate Inability to account for all variables Waiting for events to take place

Example Benetton

III.Questionnaire Format

Format is a function of
- The level of structure desired
- The degree of disguise desired during data collection.

Structured Question	Nonstructured question
presented verbatim to every respondent fixed response categories.	Not necessarily presented in exactly the same wording to every respondent Does not have fixed responses.
Nondisguised Question	Disguised Question
Direct question Purpose is obvious to respondents.	Indirect question whose True purpose is not obvious to respondents Used to examine issues for which direct questions may not elicit truthful answers
Types of Questionnaires
Structured - Non Disguised	Non - Structured - Non Disguised
Clear and direct Appropriate for large samples and descriptive research	Flexible and direct Appropriate when looking for in depth answers and exploratory research
Structured - Disguised	Non - Structured - Disguised
Clear and investigative Used to uncover people’s attitudes towards sensitive issues	Flexible and investigative Appropriate in motivation research

IV.Questionnaire Administration Methods

A. Personal Interview Method	B.Telephone Surveys
Face-to-face between interviewers and respondents. Traditionally door to door or in-home. Very flexible Greatest variety of data. Declined due to difficulties Finding adults at home Getting cooperation if they are home. Time consuming set up Mall intercept interviews conducted in shopping centers or malls Most common personal interviews More common in the (B2B) environment.	Involve only voice contact between interviewers and respondents. The most common method for reaching customers without an Internet connection. Central locations with WATS (Wide Area Telephone Service) are used
C.Mail Surveys	D.Web-based Surveys
No interviewers Survey is sent to the respondent through the mail. Popular for reaching a well-targeted customer base.	No interviewers Survey is conducted over the web. Often supplement other methods of collecting data. Quick feedback Technological advances are improving the versatility of web-based surveys.

Ranking the methods

Each method has advantages and limitations Advantages and Limitations vary with the specifics of the situation.
Criteria	1	2	3	4
	Best			Worst
Versatility
Number of Questions	Personal	Mail	Web	Phone
Amount/variety of information	Personal	Phone	Web	Mail
Presentation Stimuli	Personal	Web	Phone	Mail
Time	Web	Phone	Personal	Mail
Cost	Web	Mail	Phone	Personal
Accuracy
Sampling Control	Personal	Phone	Mail	Web
Supervisory Control	Web	Mail	Phone	Personal
Opportunity for Clarification	Personal	Phone	Web	Mail
Respondent Convenience	Web	Mail	Phone	Personal

V.Types of Observation Techniques

A.Natural versus Contrived Observation

Natural Observation	Reactions and behavior observed as they occur naturally in real-life situations A wide variety of companies are sending researchers to the field to observe consumers in their natural environment. Natural observation (ethnographic research) is more suited than traditional qualitative research for studying non-Western cultures.
Contrived Observation	Contrived setting Environment artificially set up by the researcher. Researchers are increasingly relying on computers to conduct simulated market testing. Offers a greater degree of control Speedy Efficient Less expensive Would this data have resulted from a real-life setting??

B.Disguised versus Nondisguised Observation

Disguised Observation

Respondents are unaware they are being observed
Respondents do change their behavior as a function of the observational technique.
Allows for monitoring of the true reactions of individuals.
Unethical if disguised observation monitors
- Normally private behaviors
- Behaviors that may not be voluntarily revealed to researchers.
Mystery shopping
- popular disguised observational technique
- Mystery shopper
  - Unknown to the retail establishment
  - Visits the store
  - Uses a structured script
  - Observes and records the shopping experience.

Nondisguised observation

Data may be contaminated by respondent-induced errors.
Data gathered through using disguised observation might not be as rich as those from nondisguised observation.

C.Human versus Mechanical Observation

Human observation	people taking observations observing products in use to detect usage patterns and problems observing license plates in store parking lots determining the socio-economic status of shoppers determining the level of package scrutiny determining the time it takes to make a purchase decision
Eye-Tracking	Tacks eye movements Measures which sections Attract customers' attention how much time they spend looking at those sections Used for ads product packaging promotional displays websites Oculometers - what the subject is looking at Pupilometers - how interested is the viewer
Response Latency	The speed with which a respondent provides an answer Measured to determine the ad effectiveness on brand preferences. Assumes that a quick expression of brand preference indicates a stronger preference.
Voice Pitch Analysis (VOPAN) -	Used to determine how strongly a respondent feels about an answer how much emotional commitment is attached to an answer. Variations from normal voice pitch is considered a measure of emotional commitment to the question's answer.
People Meter	Electronic device to monitor television viewing behavior who is watching what shows are being watched. used by AC Nielsen Company
Psychogalvanometer	measures galvanic skin response

D.Web-Based Observational Techniques

HTTP cookie	Well-known mechanism for storing information about Internet users on their own computers Often stores identification for subsequent recognition of a Website visitor. Cookies and their use generally does not hide from users Considered ethical if the user gives permission
Spyware	Computer software that gathers and reports information about a computer user without the user's knowledge or consent. Considered unethical

E.Direct versus Indirect Observation

Direct observation	Captures actual behavior or phenomenon of interest
Indirect observation	Consists of examining the results or consequences of the phenomenon. can give only relatively crude or imprecise indications of a phenomenon More efficient use of time More efficient fund usage May be the only way to get data from situations impractical to observe directly.

F.Structured versus Nonstructured Observation

Structured observation	Study's data requirements are well established and can be broken into a set of discrete, clearly defined categories Generally easier to record and analyze Limited in the depth and richness of data. More suitable for conclusive research projects
Non-structured observation	Study's data requirements Not well established cannot be broken into a set of discrete, clearly defined categories More suitable for exploratory research projects.

G Other Types of Observational Techniques

Audits

retail audits to determine the quality of service in stores
inventory audits to determine product acceptance
shelf space audits

Trace Analysis

credit card records
computer cookie records
garbology - looking for traces of purchase patterns in garbage
detecting store traffic patterns by observing the wear in the floor (long term) or the dirt on the floor (short term)
exposure to advertisements

Content Analysis

observe either articles, programs, or advertising content of
- magazines
- television broadcasts
- radio broadcasts
- newspapers

Web Links

Gallop Leading research organization
Harris Interactive Leading research organization
Netratings.com rates websites
Doubleclick.com check out the privacy statements