Interviewing
allows researchers to find out about people's ideas, thoughts, opinions, attitudes, and what motivates them.
Objectives of respondent interviews
-Clarify meanings of common concepts and opinions
-Distinguish elements of an expressed opinion
-Determine what influences an attitude or behavior
-Classify complex attitude patterns
-Understand the motivations consumers attribute to their actions
Descriptive questions
provides researchers with a sample of the informant's language and understanding of some phenomenon
-EX-> "can you describe how you determine where to sit the first class period?'
Structural questions
enables the researcher to discover how informants have organized their knowledge
-ex-> "what are the different types of experiences you've had picking seats in a classroom?
Contrast questions
helps us with meanings
-ex->"whats the difference between having a lot of choices and a limited number of choices to sit?
Grand Tour questions
asked to extract a verbal description of a consumption scene through space, time events, people, activities or objects.
-ex-> "what was the first day of this class like for you?
Probing questions
in cases where responses are short or off-base, the interviewer may want to ask additional or improvised questions to get more info
-ex-> "what do you mean by that?
Key Points about interviewing
the informant is "king"
-never show your opinion
-ask more questions if you don't understand their reasons
-recognize that people sometimes hide their attitudes
-sympathy and respect are key to develop trust, self-exposition and understanding
Preparing
-create a protocol; structured.
-let informant know your area of interest
-begin with open-ended questions
Nondirection
-watch out for directive questioning
-use informant's natural language
Discovery
reveal as little of your own way of thinking as possible.
Probing
used to explore further topics that generate emotion, reasons behind attitudes and opinions, watch out for markers(verbal and non-verbal signals that there is emotion behind a topic
Listening
watch for nonverbal expressions, never imply that you know anything about the topic
Surveys
an interview with a large number of respondents using a pre-designed questionnaire.
Advantages of surveys
-standardization
-ease of administration
-ability to "tap" the unseen
-gets beneath the surface
-reveals subgroup differences
Person-administered surveys
an interviewer reads questions, either face-to-face or over the telephone, to the respondent and records his or her answers.
(+) feedback, rapport, quality control, adaptability
(-) humans make errors, slow speed, high cost, fear of interview evaluation
Computer-assisted surveys
the interviewer verbalizes questions while relying on some degree of computer technology to facilitate the interview work
(+) speed, relatively free of error, use of graphics, quick capture of data
(-) technical skills may be required, setup costs can be
Self-administered surveys
respondent completes the survey on their own with no agent-human or computer-administering the interview
(+) reduced costs, respondent control, no interview-evaluation apprehension
(-) incomplete surveys, lack of monitoring, high questionnaire requirement
computer-administered surveys
computer plays an integral role in posing the questions and recording the respondents answers
(+) breadth of user-friendly features, relatively inexpensive, reduction of interview-evaluation concern
(-) requires computer-literate and internet
Mixed-mode surveys
uses multiple data collection modes.
(+) multiple ways to achieve data
(-) survey mode may affect response, additional complexity
Data collection methods
in-home interview
-mall-intercept interview
-in-office inteview
-telephone interview
-fully automated interview
-online survey
-group self-admin. survey
-drop off survey
-mail survey-
Accuracy
shooting darts right at the target
Precision
shooting a group of darts and missing the bulls eye but the darts are clustered together
Objective Properties
observable and tangible; physically verifiable characteristics such as age, gender, # of bottles purchased
Subjective Properties
not obersevable nor tangible; cannot be directly observed because thy are mental constructs such as a person's attitudes, opinions, or intentions
Construct
something that you want to measure; satisfaction, interest, consumption rate, attitude, brand image. Must bust be carefully defined and you should know why you're measuring it.
Nominal
use only labels and possess only the characteristics of a description (race, religion, gender)
-yes or no questions, agree-disagree
-mode
Ordinal
numbers possess the property of rank order; regularly, frequently; greater than, less than.
-mode and median
-"in your opinion, would you say the prices at Walmart are __,__, or ___
Scale measures
the distance between each level is known
Interval
number possess the property rank order and the differences in scale values can be meaningful interpreted; friendly, very friendly, extremely friendly
-mode, median and mean
-"rate how enjoyable the movie was, 1-10
Ratio
a true zero exists; numbers possess the characteristics of the interval scale plus the ratios of numbers on these scales have meaningful interpretations
-mode, median, mean and standard deviation
-"how much money did you spend on food last month?
Questionnaire design
systematic process in which the researcher contemplates various question formats, considers a number of factors characterizing the survey at hand, words the questions carefully, and organizes the layout
Question development
practice of selecting appropriate response formats and wording questions that are understandable, unambiguous and unbiased
Question bias
ability of a question's wording or format to influence respondent's answers
Do's of question wording
1. focused on one topic, "When you are on family vacation, what type of hotel do you typically use?"
2. Brief questions, "If your ice maker was not working right, how would you correct the problem?"
3. Gramatically simple questions, " Would you and your s
Don'ts of question wordinng
1. Do not "lead" to a particular answer, "Don't you worry when using your cc for online purchases?"
2. Do not use "loaded" wording, "Should people be allowed to protect themselves from harm by using a taser in self-defense?"
3. do not use a "double-barrel
Questionnaire organization
pertains to the sequence of statements and questions that make up a questionnaire.
Question flow
pertains to the sequencing of questions or blocks of questions, including any instructions on the questionnaire.
Screening questions
used to cut out respondents who do not meet qualifications necessary to take part in the research study.
Warm-up questions
simple and easy to answer questions that are used to get the respondent;s interest and to demonstrate the ease of answering
"how often do you go shopping for clothes?
Transition questions
prior to major sections of questions or changes in question format; notifies respondent that the subject of the following questions will change
Complicated and difficult-to-answer questions
middle, close to the end; told that there aren't many questions left, committed the respondent.
"how likely are you to purchase in the next 3 months?
Classification and demographic questions
last section; personal and possibly offensive. " what is the highest level of education you've received?
Skip logic
lets the questionnaire designer direct the online survey to ask questions based on previous answers
"If yes,
Display logic
similar to skip logic, survey displays or asks questions that are appropriate based on the respondent's prior answers.
Pretesting
dry run of a questionnaire to find and repair difficulties that respondent's encounter while taking the survey. should be representative of the target population
probability sampling
an objective procedure in which the probability of selection is known in advance for each population unit; researcher remains objective
-randomly selecting people from a population
-simple random, stratified random, cluster, systematic,
non-probability sampling
subjective procedure in which the probability of selection is unknown beforehand.
-the people are chosen for a reason
-convienence, judgement, quota
sampling study
inferences are drawn simply from a portion or sample of the population, costs less than census
census study
decision makers draw inferences or conclusions from the entire population of interest. must be feasible and necessary.
simple random sampling
every possible sample of a certain size within a population has a known and equal probability of being chosen as the study sample
stratified random sampling
the chosen sample is forced to contain units from each of the segments or strata of the population
Cluster sampling
clusters of population units are selected at random and then all or some of the units in the chosen are studied. Best for naturally occurring groups like households
systematic sampling
first unit is selected randomly, then the remaining are selected systematically using the sampling interval.
K-means sampling
# of units in population/ # units desired in sample
Convenience sampling
the researcher's convenience forms the basis for selecting a sample of units
Judgement sampling
the researcher exerts some effort in selecting a sample deemed to be the most appropriate for the study
Quota sampling
a pre-specified quota of units is selected from each population segment, or cell, based on the judgement of the researchers or decision makers.
sampling error
The difference between a statistic value, which is generated through a sampling procedure and the parameter value, which can be determined only through a census study. involves sample selection and sample size
parameter
The actual, or true, population mean value or population proportion for any variable (income, product ownership, etc.)
� = 4.5
statistic
An estimate of a parameter from sample data
Sampling distribution
A representation of the sample statistic values obtained from every conceivable sample of a certain size, chosen from a population by using a specified sampling procedure, along with the relative frequency of occurrence of those statistic values
Standard error
Represents the standard deviation of the different sample statistic values that will be obtained through repeated selection of samples from the same population
It is interpreted as the average amount of sampling error associated with the sampling procedur
non-sampling error
pertains to all sources of error other than sample selection method and sample size
sample accuracy
refers to how close a random sample's statistic is to the true population's value it represents
variability
refers to how similar or dissimilar responses are to a given question
confidence interval approach
applies the concepts of accuracy, variability, and confidence interval to create a "correct" sample size or estimate a "likely" level of error
margin of sample error formula
P= estimated percent of our target measure in the population
Q=1-P
N= # of people in our sample
standard sample size formula
n=sample size
z=standard error (typically 1.96)
p=estimated percent in the population
q=1-p
e=acceptable sample error expressed as a percent
sample size for estimating a mean
S2*Z2/e2
how to estimate s:
-standard deviation from a previous study on target population
-conduct a pilot study
-range/6