2Focusing You
Research Design
Your company has decided to create a smartphone app and the vice president has asked you to be the
team leader. Your team’s assignment is to nurture the concept. When you meet with your VP next week,
you will specify the kind of apps your company might develop, determine what the different apps might
do, and focus on your target audience for each possible app.
As your project matures, you understand how important it is to have a research design. Such a plan will
guide your team and your company’s decision makers. It will lay out the methods and procedures you
need to employ as you collect information.
To develop a research design, you will rely on three types of studies: exploratory studies, descriptive
studies, and causal studies. Each depends on different information that will help you. No matter how
large or small your project, conducting surveys and establishing a research design is vital to your success.
If you don’t know where your project is going, you won’t know if it’s succeeding.
EXPLORATORY STUDIES
First, you need to do an exploratory study. This is the problem finding phase. An exploratory study forces
you to focus the scope of your project. It helps you anticipate the problems and variables that might arise
in your project.
Perhaps the most common problem is size. Your project must be kept focused. If the scope of a project is
too big, it will not get off the ground. Too much information is overwhelming. An important objective
of an exploratory study is keeping your project manageable. The larger your project’s scope, the more
difficult it is to control. This process will help you weed out problems.
In the case of developing an app, for example, an exploratory study would help your research team take
an abstract idea and develop it into a focused plan. The specific app would be market-driven. This process
takes legwork, but the results are worth the effort.
16 | RESEARCH DESIgN
Exploratory studies generally encompass three distinct methods:
1. Literature search
2. Expert interviews
3. Case studies
LITERATURE SEARCH
A literary search means you go to secondary sources of information: the internet, the public li
ary,
company or government records. These sources are usually easy and inexpensive to access.
For example, your development team would search online. They would look at other kinds of apps on the
market, the prefe
ed phone to develop an app, the pricing of similar products, and any other information
necessary to set parameters on their project.
EXPERT INTERVIEWS
After a literature search, your team would have a useful background for the project. They know what
questions to ask and how to set up their project. After the literary search, the next step is to interview
experts. These experts might include company executives or consumers. They would also talk to people
who used similar products. Your team would seek out professionals who have careers relating to the
esearch project.
Your team knows that one effective way to gain information from experts is through focus groups. A
focus group includes 6-8 individuals who share a common background (software development, market
analysis, administration, dog
eeding, fly fishing) who participate in a joint interview. The secret to a
successful focus group is ignoring the traditional question/answer format. Instead, you encourage the free
flow of ideas and discussion.
CASE STUDIES
Every research project will have pitfalls. Thus, case studies become a vital tool because they allow you to
examine another business’s managerial problems and solutions. If another study deals with similar issues,
you can avoid these pitfalls by learning from its mistakes. Case studies include histories of other projects
and simulations of possible alternatives. A good “What if?” can save a lot of time and resources.
DESCRIPTIVE STUDIES
Who are you selling to? An exploratory study helped you establish what you are selling, but the
descriptive study will help you find your market and understand your customer. Since you will not be able
to sell to everyone, a descriptive study is necessary to focus your project and resources.
RESEARCH DESIgN | 17
There are different kinds of studies you can implement to better understand your market. Consider the
following descriptive studies:
• Market potential: description of the number of potential customers of a product.
• Market-share: identification of the share of the market received by your product, company and
your competitors.
• Sales analysis: description of sales by te
itory, type of account, size or model of product.
• Product research: identification and comparison of functional features and specifications of com-
petitive products.
• Promotion research: description of the demographic characteristics of the audience being
reached by the cu
ent advertising program.
• Distribution research: determining the number and location of retailers handling the company’s
products. These are supplied by wholesalers and distributed by the company.
• Pricing research: identifying competitors’ prices by geographic area.
These studies will help you formulate solutions. At the same time, they indicate how potential customers
might react.
CAUSAL STUDIES
Even though descriptive studies describe and sometimes predict relationships, results, or events, you may
want to know why. If you can discover the reasons behind your solutions, then you can assemble your own
predictive models. Such models can be used in the future. As a marketing researcher, knowing why will
make your job easier. Causal studies try to find out the relationship between a specific cause and a specific
effect.
FIGURING OUT CAUSAL RELATIONSHIPS
Cause and effect have to be related. Before a cause and effect can be established, a logical implication (or
theoretical justification) has to be found.
There are three types of evidence that can be used to establish causal relationships:
1. Associative variation
2. Sequence of events
3. Absence of other possible causal factors
18 | RESEARCH DESIgN
Associative Variation
Associative variation involves taking two variables and seeing how often they are associated. The more
they show up in studies, the more likely they are related. Associative variation can be
oken down into
two distinctions: association by presence and association by change.
Association by presence measures how closely presence of one variable is associated with presence of
another. However, association by change measures the extent to which a change in the level of one
variable is associated with a change in the level of the other.
For example, if you wanted to find a causal relationship between a salesperson’s success in sales and
training, you would have to establish a relationship between the two variables. Do sales only increase
after training? Can sales increase before training? If you find that one variable is affected by another, you
know which variable to adjust.
Sequence of Events
In order to establish a cause/effect relationship, you must first establish that the causal factor occu
ed
first. For example, in order for salesperson training to result in increased sales, the training must have
taken place prior to the sales increase. If the cause does not precede the effect, then there is no causal
elationship.
Absence of Other Possible Causal Factors
You must also demonstrate that other factors did not cause the effect. Once you have proved this, you can
logically conclude that the remaining factor is the cause. For example, if we can control all other factors
affecting the sales item, then we have to conclude that the increase in sales comes from training.
SOURCES OF MARKETING INFORMATION
The app development team knows it must do careful market research before it can begin development.
But where do they start?
There are four major sources for finding marketing information. We’ll
iefly describe each in this
section. However, we will discuss these in-depth in later chapters. These four sources include:
1. Secondary sources
2. Respondents
3. Natural and controlled experiments
4. Simulation
RESEARCH DESIgN | 19
Secondary Sources
Secondary information is information that someone else researched for a solution to a problem other
than yours. Even though this information wasn’t intended for your project, it could provide valuable
insights. For example, PetMD conducted a study and found that sixty-nine percent of dog owners need
help understanding their dog’s nutritional needs. Meanwhile, Hill’s®ScienceDiet is developing a new
chicken and whole grain dog food that meets the full spectrum of nutritional needs. While the purpose
of PetMD’s study had a different purpose, Hill’s can use PetMD’s research to better its own market
products.
Respondents
Information from respondents plays a huge role in research. Customers’ ve
al and behavioral responses
provide useful information. Later in this book, we’ll look at how both asking questions and observing
ehavior come together to form a complete response.
Natural and Controlled Experiments
Natural experiments are just what they would seem. The investigator only measures results, having
no control over the elements of the experiment. For example, if Nielson wanted to research a TV
audience’s response to a specific television commercial, a natural experiment would involve the researcher
monitoring viewership and interviewing the audience. The results would then be compared to a control
group who had not watched the commercial. Natural experiments are useful when you want to gauge
general results.
Controlled experiments measure specific variables and require the researcher to be more involved.
Experimental results are then compared to a control group in order to measure the chosen variable.
Two kinds of intervention are required in controlled experiments:
1. Manipulating at least one causal variable.
2. Random assignment of subjects to experimental and control groups.
Controlled experiments work best when the researcher controls all but one causal variable. The researcher
assigns subjects to an experimental group where the causal variable is manipulated or to a control group
where no causal variables are manipulated. The researcher measures the dependent variable in both
situations and then tests for differences between the groups. This strict control allows differences between
the groups, if present, to be attributed to the manipulated variable.
Qualtrics.com online will be invaluable when you do field experiments. This tool is quick, easy to use,
and cost effective. Qualtrics provides a rich assortment of tools for conducting experiments. They include:
advanced
anching logic, randomization, question block presentation, question response timing, and
JavaScripting capabilities.
20 | RESEARCH DESIgN
Simulation
Experimentation can be expensive and time-consuming. It might be more cost effective to create a
simulation model instead of doing real-world experiments.
Simulations are effective when the project has a scope larger than regular experiments can cover.
Environmentally rich models (containing complex interactions and nonlinear relationships) are usually
too difficult to solve by standard analytical methods such as calculus or other mathematical programming
techniques. Rather, the analyst views a simulation model as a limited imitation of the process or system
under study and attempts to run the system on a computer to see what would happen if a particular set of
conditions were put into effect.
Simulations are often developed for marketing systems, and include marketing-mix elements (new-
product, price, advertising, and sales-force variables).
TYPES OF ERRORS AFFECTING RESEARCH RESULTS
Information gained from research projects should be as accurate as possible. Any research project is
subject to e
ors, so a research designer must do everything he/she can to minimize them. As shown in
Table 2.1, two general e
ors have important implications in research designs:
1. E
ors related to improper selection of respondents
2. E
ors related to accuracy of responses
RESPONDENT SELECTION ERRORS ACCURACY OF RESPONSE ERRORS
1. Population Specification E
o
2. Sampling E
ors
3. Selection E
ors
4. Frame E
ors
5. Survey Non-Response E
ors
1. Non-Response E
ors
2. Su
ogate Information E
ors
3. Measurement E
ors from Interviewers
4. Measurement e
ors from questions
5. Measurement e
ors from respondents
TABLE 2.1
COMMON ERROR TYPES
RESEARCH DESIgN | 21
The next discussion considers some strategies that can be employed to make your
esearch project relatively e
or-free.
Understanding the possible e
ors that can taint the accuracy of information in your
study is key to avoiding and co
ecting sampling e
ors. Below is a
ief explanation of
possible e
ors.
RESPONDENT SELECTION ERRORS
POPULATION SPECIFICATION ERROR
This type of e
or occurs when the researcher selects an inappropriate population or
universe from which to obtain data.
Example: Packaged goods manufacturers, for example, frequently survey
housewives because they are an easy contact. Also, it is assumed housewives
decide what is to be purchased and do the actual purchasing for a household.
However, in this situation, there often is population specification e
or. In-
creasingly, husbands may purchase a significant share of the packaged goods
and have significant influence over what is bought.
SAMPLING ERROR
Sampling e
or occurs when a sample does not accurately represent the population.
Example: Suppose that we used tweets (Twitter) to recruit a random sample
of 500 people from the general adult population. After an analysis, though,
we find our study was composed only of people aged 18 to 35. Because the
sampling pool shares so many age group specific traits, the data isn’t accurate
in representing the general population.
The more homogeneous the population (meaning people who are similar), the smaller
the sampling e
or; and as sample size increases, sampling e
or decreases. If a census
were conducted (i.e., all elements of the population were included) there would be no
sampling e
or.
22 | RESEARCH DESIgN
SELECTION ERROR
Selection e
or is the sampling e
or that occurs when a sample is selected by a
nonprobability method.
Example: Interviewers conducting a mall intercept study have a natural
tendency to select those respondents who are the most accessible and
agreeable. Such samples often comprise friends and associates who are rarely
representative of the desired population.
Selection e
or often reflects people who are easily reached, are better dressed, have
etter kept homes, or are more pleasant. These types of samples rarely represent
the desired population. Having clear, written procedures that specify how to select
espondents can help to reduce selection e
or.
FRAME ERROR
A sampling frame supposedly represents all the members of the population. It is
usually a listing of the respondents you want to sample.
Example: The sample frame for a study at a shopping mall includes all
shoppers in the mall during the time of data collection. In years past, a
commonly used frame for consumer research was the telephone directory.
Over time, this frame has increasingly introduced e
or because many
elements of the population (households, singles, students) are no longer
included in the directory. There are also unlisted phone numbers, move-ins,
and cell phones to consider. Some elements are listed more than once, and
non-population elements are also included (businesses and people who have
left the area).
A perfect frame identifies each member of the targeted population once, but only once,
and does not include members outside of that specific population.
SURVEY NON-RESPONSE ERROR
Non-response e
or occurs when respondents and non-respondents are too different.
Your respondents should accurately represent the population you want to sample. If
non-respondents are not equally distributed across the population, you will not have an
accurate sample.
There