Marketing 360 Exam 1

marketing research
-refers to the process of designing, gathering, analyzing, and reporting information that may be used to solve a specific marketing problem
-helps to uncover information managers need to make important business decisions
Way marketing research can be used
o Identify marketing opportunities and problems
o Generate, refine, and evaluate potential marketing actions
o Monitor marketing performance
o Improve marketing as a process
1. Establish the need for marketing research
Value of info vs. Cost of info
2. Define the problem
-situations that require managers to make choices among decision alternatives
-Most important step in research process
3. Establish research objectives
Research objs. specify what researcher must do to obtain info the manager needs to choose b/w decision alternatives
4. Determine research design
Overall approach used to obtain info needed
Exploratory Research Design
-little is known about question, involves collecting info in an unstructured/informal manner, usually qualitative techniques or analysis of secondary data
Descriptive Research Design
-question is well defined, focuses on describing phenomena of interest (satisfaction) and/or relationship b/w two variables of interest (satisfaction & repeat purchasing)
Causal Design
-question is well defined, usually experiments and objective is to establish cause-and-effect relationships (does running an ad increase sales?)
5. Identify information types and sources
-Primary info – info collected specifically for the problem at hand
-Secondary info – info already collected for some other purpose
6. Determine methods of accessing data
-Primary data – observe, actively gather
-Secondary data – already exists
7. Design data collection forms
Two types of forms – Questionnaires & Observation forms
8. Determine the sample plan and size
-Sample plan
-Sample size
Sample plan
impacts representativeness
Sample size
impacts accuracy
9. Collect data
Challenging and subject to non-sampling errors
10. Analyze data
Enter data into computer files, inspect data for errors, run tabulations & stat tests
11. Prepare and present the final research report
Communicate results to client
Nominal scales
-Use descriptors (labels) to place objects into categories
-Serve for classification and identification purposes
-Enable researchers to describe objects
-Ex: What is your gender?, what is your relationship status?, which
categories describes your household income? (check one)
Ordinal scales
-Permit researchers to rank order respondents on their responses
-Identify ORDERED relationships among objects
-Indicate only RELATIVE size differences: DO NOT know what the
distance between descriptors is
-Ex: Please rank the following cereals according to your degree of liking (1=you like most, 6=you like the least)
Interval scales
-Identify ordered relationships just like an ordinal scale BUT distances
between the descriptors (or labels) are known
-Descriptors are equal distances apart
-The distance between descriptors is usually one unit
-Interval scales include the modified likert scale and the sematic differential scale
Ratio scales
-Have a true zero point
-Enables researcher to make statements such as the following:
Individuals that are likely to patronize the restaurant are TWICE as old as those who are unlikely to patronize the restaurant
-Ex: How old are you?, What is your approximate weight in pounds?
Simple Random Sampling
Lottery Method – write the names or codes on a piece of paper, put them in a container, then randomly select the desired number of samples. Sometimes it is referred to as the fishbowl technique.
Systematic Sampling
choose a starting point then select every kth element of the population using
Cluster Sampling
first off, divide the population area into sections (or clusters), randomly select a few of those sections to form a sample.
Stratified random sampling
the population is subdivided into at least two different subpopulations that share the same characteristics (such as gender), then draw a sample from each stratum.
Convenience sampling
samples drawn at the convenience of the interviewer.
Purpose sampling
requires a judgment or an “educated guess” as to who should represent the population
Chain referral sampling
require respondents to provide the names of prospective respondents
Quota sampling
specified percentages of the total sample for various types of individuals to be surveyed
refers to how close a sample’s statistic is to the true value in the population. In other words, whether a sample well represents the target.