Marketing research

BA035IU
• Lecturer: Dr. Alang Thớ
• Email: [email protected]
• Workshops: Monday, 8.00– 10.25
• Consultation appointment: immediately before or after
class
This week 7
Summarizing main points from previous weeks

Causal research design: experimentation

• What is experimental research?
• What constitute causality?
• Issues in experimental research
• Types of experimental designs
• Laboratory and field experiments
• Guidelines for conducting experimental research
• Limitations of experimental research

Summary
 Summarizing main points from previous weeks

Research
Research objectives/aims
design Research questions/hypothesis
process

Data Secondary research-> secondary sources of data

Exploratory research-> in-depth interview, focus group, observation
collection Descriptive research-> information from respondents using survey methods (questionnaire)
methods: Causal research-> experimentation (THIS WEEK 7)
Learning objectives

1 2 3 4 5 6 7 8

Understand the Understand the Distinguish Understand the Identify and Distinguish Understand Understand the
concept of concept of between classical differences comprehend the between guidelines for limitation of
experimentation causality and the designs and between pre- advantages and laboratory and conducting experimental
and conditions statistic designs experimental, limitation of the field experiments experimental research
experimental required to infer true different types of research
research causality experimental, experimental
and quasi- designs
experimental
designs
What is experimental research?
Experiments: Studies in which conditions are controlled so that one or
more independent variable(s) can be manipulated to test a hypothesis
about a dependent variable

Experimental research: Manipulation of A treatment variable (x), followed

by observation of response variable (y)

Experiment must be designed to control for other variables to establish

causal relationship
Examples of hypothesis, independent
variables and dependent variable
• Explain what you expect to happen • H1: advertising expenditure (X1) has a
• Be clear and understandable positive association with sale of
products (y)
• Be testable
• H2: distribution (X2) has a positive
• Be measurable association with sale of products (y)
• Contain an independent and • Y= b0 + b1X1+ b2X2+ ∝
dependent variable
• Where Y is dependent variable
• X1 and X2 are independent variables
What constitutes causality?
• A change in one variable will produce a change in another (association)
• Concept of a precondition influencing a variable of interest
• The lack of association suggests the absence of causation
• An association between attitude and behavior is evidence of a causal relationship
 Determining the direction of causation/
developing hypothesis
• Draw on logic and previous theory
• Whether one of the variables is relatively fixed and unalterable
• If a time lag exists between cause and effect then the causal variable should have
a positive association with the effect variable lagged in time
 Conditions for valid causal inferences
• Condition of concomitant variation
• Evidence that a strong association exists between an action and an observed
outcome
• Condition of time order of occurrence
• Evidence that the action preceded the outcome
• Absence of competing causal explanations
• Evidence that there is no strong competing explanation for the relationship –
that a high level of internal validity exists
An example of conditions for valid causal inferences
Issues in experimental research

What type of experimental design should be used?

Should the experiment be performed in a “laboratory” setting or in the

“field”?

What are the internal and external threats to the validity of the
experiment, and how can we control for the various threats to the
experiment’s internal and external validity?
Types of experimental designs

Classical • Considers only one treatment level of an

independent variable at a time

Statistical • Allows for examining the impact of different

treatment levels of an independent variable and
the impact of two or more independent
variables
Types of experimental designs (cont’d)
True Experimental Designs
Pre-experimental Designs •Two-group, Before-After Design
•One-group, After-Only Design •Two group, After-Only Design
•One group, Before-After Design •Solomon Four Group Design
•Nonmatched Control Group Design
•Matched Control Group Design
Quasi-Experimental Designs
•Time Series Design
•Continuous Panel Design
Classical Designs

Completely Randomized Design

Statistical Randomized-Block Design
Designs Latin Square Design
Experimental
Factorial Design
Designs
Basic symbols and notations
O denotes a formal observation or measurement

X denotes exposure of test units participating in the study to the experimental manipulation of
treatment
EG denotes an experimental group of test units that are exposed to the experimental treatment.

CG denotes a control group of test units participating in the experiment but not exposed to the
experimental treatment
R denotes random assignment of test units and experimental treatments to groups. Increases
reliability
M denotes that both the experimental group and the control group are matched on the basis of
some relevant characteristics
Pre-experimental design: One-group, after-
only design
• Apply the experimental treatment to a subject or group and measure the results
EG X O
• Leaves open the possibility that the results could be explained by events external
to the design
Pre-experimental design: Nonmatched
control group design
• Introduce a control group to control for history and maturation
EG X O1
-------
CG O2
Pre-experimental design: Matched control
group design
• Matches experimental and control groups to reduce selection bias
EG M X O1
-----------
CG M O2
Pre-experimental design: One-group, before-
after design
• Improve control by adding before measure
EG O1 X O2
• Before measure adds sensitivity by adding another method to control for
confounding variables
Pre-experimental design: Threats to
experiment validity
• Before Measure Effect
• May alert respondents to the fact that they are being studied
• Results in more socially desirable behavior
• Mortality Effect
• Some subjects may stop participating in the experiment
• Instrumentation Effect
• Results from a change in the measuring instrument
True-experimental designs
• True experimental designs adopt random assignment procedure and use one or
more control groups
• Random Assignment
• For any given assignment to a treatment, every member of the universe has
an equal probability of being chosen for that assignment
True-experimental designs: Two-group,
before-after design
• Adds a control group to one-group, before - after design
• Helps control for history and maturation
• Controls for reactive effect of O1 and O2
EG R O1 X O2
-------------
CG R O3 O4
True-experimental designs: Two-group, after-
only design
• Randomization can match test and control groups on all dimensions
simultaneously, given a sufficient sample size
EG R X O1
-----------
CG R O2
• There is no interaction effect of testing as there are no pretest requirements
True-experimental designs: Solomon Four-
group design
EG R O1 X O2
---------------
CG R O3 O4

EG R X O5
---------------
CG R O6
• This design is often prohibitively expensive
• Provides power to control for before measure effect of O1 on both X and O2
Quasi- experimental designs
• Offer some degree of control but there is no random assignment of variables
• Provide more measurements and more information than pre-experimental design
Quasi- experimental designs: Time series
design
• Series of measurements are employed during which an experimental treatment
occurs
EG O1 O2 O3 O4 X O5 O6 O7 O8
Quasi- experimental designs: trend studies,
and continuous panel studies
• Trend Studies: Measures over time come from succession of separate random
samples from the same population
• Continuous Panel Studies: Collect a series of measurements on the same sample
of test units over an extended period of time
Statistical designs: Completely randomized
design
• Any number of treatments can be assigned to test units on a random basis
EG1 R X1 O1
----------------
EG2 R X2 O2
----------------
EG3 R X3 O3
Statistical designs: Randomized block design
• Employs the randomization process for all variables
• Matching ensures that there are no differences between test samples on matched variables
• Matching and randomization are combined in randomized block design
EG1 R X O1
--------------
CG1 R O2
-------------------------
EG2 R X O3
---------------
CG2 R O4
Statistical design: Latin square design
• Reduces number of groups involved when interaction between the treatment
levels and control variables are unimportant
• Requires same number of rows, columns, and treatment levels
• Cannot be used to determine interaction effects
Statistical designs: Factorial designs
• Two or more experimental variables are considered simultaneously
• Each combination of the experimental treatment levels applies to randomly selected groups
EG1 X1 O1
EG2 X2 O2
…
EGn Xn On
• Provides the ability to determine interactive effects of pairs of experimental variables and the
main effect
Laboratory experiments
• Experiments in which the experimental treatment is introduced in an artificial or
laboratory setting
• Laboratory experiments tend to be artificial
• Testing effect exists as respondents are aware of being in a test and may not
respond naturally
• Results may not have external validity
• Least costly and allow experimenter greater control over the experiment
• Alternative explanations of results are reduced, increasing internal validity
Field experiments
• Research study in which one or more independent variables are manipulated by the
experimenter under carefully controlled conditions as the situation will permit
• Experimental treatment or intervention introduced in a completely natural setting
• Response tends to be natural
• Tend to have much greater external validity
• Difficult to control
• Competing explanations for results exist
Threats to experimental internal validity
• History
• Maturation
• Testing
• Instrumentation
• Statistical Regression
• Selection Bias
• Mortality
• Selection - Maturation Interaction
Threats to experimental external validity
• Reactive or interaction effect of testing
• Interaction effect of selection bias and experimental variable
• Reactive effects of experimental arrangements
• Multiple treatment interference
Guidelines for conducting experimental
research
Recognition of and statement of the problem

Choice of factors and levels

Must provide useful information about

Selection of the response variable process under study
Guidelines for conducting experimental
research (cont’d)
Selection of suitable order for experimentation trials
Choice of Experimental Design Determination of whether blocking or other
randomization restrictions are involved

Performing the Experiment

Data Analysis

Conclusion and Recommendations

Limitations of experimental research

Cost Involved Time Considerations Security

Field experiment exposes
marketing program in the
marketplace
Difficult to hide from competitors
Limitations of experimental research (cont’d)
• Implementation Problems
• Difficult to gain cooperation within the organization
• Contamination may occur in experiments involving market areas due to
inability to confine the treatment to designated experimental area
• Variability in behavior across test units can be so large that it is difficult to
detect experimental effects
Summary
• The principle work of experimental research is manipulation of a treatment of variable (X) followed by
observation of response variable (Y). A change in X causes Y to change in the hypothesized way. To
establish this causality between two variables, types of evidences are required such as condition of
concomitant variation, condition of time order of occurrence, and absence of competing causal
explanation.
• Experimental designs can be categorized into two groups: classical and statistic designs. The classical
ones consider the impact of only one treatment level of an independent variable at a time. The statistic
ones allow for examining the impact of different treatment levels of an independent variable and also
the impact of two or more independent variables.
• Experimental research can be divided into two categories: laboratory experiments and field
experiments.
• The experimental research also has its limitations in relation to time, cost, security, and
implementation.