Lecture Marketing research - Chapter 7: Primary data collection: Experimentation

In this chapter, students will be able to: Understand the nature of experiments, gain insight into requirements for proving causation, learn about the experimental setting, examine experimental validity, learn the limitations of experimentation in marketing research, compare types of experimental designs, gain insight into test marketing.

Copyright © 2004 John Wiley & Sons,Inc

Primary Data Collection: Experimentation

Learning Objectives

1 To understand the nature of experiments.

2 To gain insight into requirements for proving

causation.

3 To learn about the experimental setting.

4 To examine experimental validity.

5 To learn the limitations of experimentation in

marketing research.

Learning Objectives

6 To compare types of experimental designs.

7 To gain insight into test marketing.

An Experiment:

The researcher changes an explanatory, independent,

or experimental variable to observe changes in the

dependent variable

To understand the nature of experiments.

What is an Experiment?

Dependent variable

Experimental variable

total sales

marketing mix

advertising market share

Causal Research:

The only types of research that has the potential to

demonstrate that a change in one variable causes

some predictable change in another variable

To Demonstrate Causation:

- Concomitant Variation (Correlation

- Appropriate Time Order Of Occurrence

- Elimination Of Other Possible Causal Factors

Demonstrating Causation To understand the nature of experiments.

Scientific Definition—Causation and Causality

1 X is only one of a number of determining conditions

that caused the observed change in Y

2 X can be a cause of Y if the presence of X makes the

occurrence of Y more probable or likely

3 One can never definitively prove that X is a cause of Y

but only infer that a relationship exists

4 Causal relationships are always inferred and never

demonstrated conclusively beyond a shadow of a doubt

Demonstrating Causation To understand the nature of experiments.

Concomitant Variation:

A predictable statistical relationship between two

variables

Appropriate Time Order of Occurrence:

A change in an independent variable must occur before

a change in the dependent variable

Elimination of Other Possible Causal Factors

The change in B was not caused by some factor other

than A

Demonstrating Causation To understand the nature of experiments.

Laboratory experiments:

Conducted in a controlled setting

Advantages of laboratory experiments:

•Ability to control all variables

•Greater internal validity

Disadvantages of laboratory experiments:

•External validity

Field experiments:

Tests conducted outside the laboratory

The Experimental Setting:

Laboratory or Field To learn about the experimental setting.

Internal and External Validity

Internal Validity:

The extent to which competing explanations can be ruled out

External Validity:

The extent to which causal relationships can be

generalized to outside persons, settings, and times

Experimental Notation:

X indicates exposure

O for observation

O 1 X O 2 for time periods

To examine experimental validity.

Experimental Validity

Extraneous Variables: Threats to Experimental Validity

• Regression to the Mean

To examine experimental validity.

Experimental Validity

Confounding Variables—extraneous causal factors because

they confound the treatment condition

Four Basic Approaches to Control Extraneous Factors

Experimental Design

Ex Post Facto Research—nonexperimental designs

Factors of the Experimental Design :

Researcher has control of variables and manipulates

them

1 Treatment

2 Subjects

3 Dependent variable

4 Plan for extraneous causal factors

To learn about experimental setting

Treatment, and Effects

Treatment Variable

-Independent variable that is manipulated

Experimental Groups

1 Control Group—the group in which the independent

variable is not changed during the course of the

experiment

2 Test Group—the group that is exposed to manipulation

(change) of the independent variable

Experimental Effects

The effect of the treatment variable on the dependent variable

To learn about experimental setting.

Treatment, and Effects

The High Cost of Experiments

Research

Three Pre-experimental Designs

• One-Shot Case Study—pre-experimental design with no pretest observations, no control groups, and an

aftermeasurement only

• No pretest observations

• No control group of test units

•Lacks internal validity

• One-Group Pretest-Posttest Design—pre- and

postmeasurements but no control

• Static-Group Comparison Design—pre-experinmental

To compare experimental designs.

Designs

Three Pre-experimental Designs (cont’d)

• One-Group Pretest-Posttest Design—pre- and

postmeasurements but no control group

• History

• Maturation

• Only one pretest observation

• Static-Group Comparison Design—pre-experinmental

• Absence of pretests

• Not assigned to the groups randomly

To compare experimental designs.

Designs

True Experimental Designs

• Before and After with Control Group Design

• Mortality

• History

• Solomon Four-Group Design

•Second experimental group no pretest

•Second control group only posttest measurement

• After-Only with Control Group

To compare experimental designs.

Designs

Developed to deal with external validity

Researcher lacks complete over the scheduling of treatment

or must assign treatment in a nonrandom manner

Interrupted Time-Series Designs

• The treatment interrupts repeated measurements

• Cannot control history

Multiple Time-Series Designs

• An interrupted time-series design with a control group

To compare experimental designs.

Designs

Test Markets Defined

Any research that involves:

• Testing a new product or change in an existing

marketing strategy

• The use of experimental or quasi - experimental

procedures

Test Market Usage and Objectives

• Estimate of market share

• Effect on sales of similar products

• Characteristics of consumers

• Behavior of competitors

To gain insight into test marketing.

Test Markets

Direct Costs of Test Marketing

Indirect Costs of Test Marketing

Costs include:

• Management time

• Diversion of sales activity

• Negative impact of test market failure

• Negative trade reactions to products

• Cost of letting competitors know what the firm is doing

To gain insight into test marketing.

Test Markets

Decision To Conduct Test Marketing

Benefits

• Good estimate of product’s sales potential

• Identify weaknesses of the product and the proposed

marketing strategy

Factors to Consider

• Weight the cost and risk of failure

• Likelihood and sped product can be copied

• Damage an unsuccessful new product would inflict

To gain insight into test marketing.

Test Markets

Steps in a Test Market Study

1 Define the Objective

2 Select a Basic Approach

3 Develop Detailed Procedures for the Test

4 Select Markets for the Test

5 Execute the Plan

6 Analyze the Test Results

To gain insight into test marketing.

Test Markets

Simulated Test Markets (STM)

• uses laboratory approaches and mathematical models to simulate test market results

Other Types of Test Marketing

• A rolling rollout

• Lead country strategy

To gain insight into test marketing.

Test Markets

The End

Copyright © 2002 South-Western/Thomson Learning