(Download PDF) Marketing Research An Applied Orientation 6th Edition Malhotra Solutions Manual Full Chapter

Marketing Research An Applied
Orientation 6th Edition Malhotra

Solutions Manual
Go to download the full and correct content document:
https://testbankfan.com/product/marketing-research-an-applied-orientation-6th-edition
-malhotra-solutions-manual/
More products digital (pdf, epub, mobi) instant
download maybe you interests ...
Marketing Research An Applied Orientation 6th Edition

Malhotra Test Bank
https://testbankfan.com/product/marketing-research-an-applied-
orientation-6th-edition-malhotra-test-bank/

Malhotra Solutions Manual
orientation-7th-edition-malhotra-solutions-manual/
Marketing Research An Applied Orientation Global 6th

Edition Malhotra Test Bank
orientation-global-6th-edition-malhotra-test-bank/

Malhotra Test Bank
orientation-7th-edition-malhotra-test-bank/
Essentials of Marketing Research A Hands-On Orientation
1st Edition Malhotra Solutions Manual
https://testbankfan.com/product/essentials-of-marketing-research-
a-hands-on-orientation-1st-edition-malhotra-solutions-manual/
Essentials of Marketing Research A Hands-On Orientation

1st Edition Malhotra Test Bank
a-hands-on-orientation-1st-edition-malhotra-test-bank/
Basic Marketing Research 4th Edition Malhotra Test Bank
https://testbankfan.com/product/basic-marketing-research-4th-
edition-malhotra-test-bank/
Essentials of Marketing Research Global 1st Edition

Malhotra Test Bank
global-1st-edition-malhotra-test-bank/
Marketing Research Arab World Editions 1st Edition

Malhotra Test Bank
https://testbankfan.com/product/marketing-research-arab-world-
editions-1st-edition-malhotra-test-bank/
CHAPTER 7
CAUSAL RESEARCH DESIGN:

EXPERIMENTATION
FIGURES AND TABLES
Figures
Figure 7.1 A Classification of Experimental Designs
Figure 7.2 A Concept Map for Experiments
Tables
Table 7.1 Evidence of Concomitant Variation Between Purchase of Fashion
Clothing and Education
Table 7.2 Purchase of Fashion Clothing by Income and Education
Table 7.3 Sources of Invalidity of Experimental Designs
Table 7.4 An Example of a Randomized Block Design
Table 7.5 An Example of Latin Square Design
Table 7.6 An Example of a Factorial Design
Table 7.7 Laboratory Versus Field Experiments
CHAPTER OBJECTIVES
1. Explain the concept of causality as defined in marketing research and distinguish between
the ordinary meaning and the scientific meaning of causality.
2. Define and differentiate the two types of validity: internal validity and external validity.
3. Discuss the various extraneous variables that can affect the validity of results obtained
through experimentation and explain how the researcher can control extraneous variables.
Copyright © 2010 Pearson Education, Inc. publishing as Prentice Hall
1
4. Describe and evaluate experimental designs and the differences among preexperimental,
true experimental, quasi-experimental, and statistical designs.
5. Compare and contrast the use of laboratory versus field experimentation and
experimental versus nonexperimental designs in marketing research.
6. Describe test marketing and its various forms: standard test market, controlled test
market, and simulated test market.
7. Understand why the internal and external validity of field experiments conducted
overseas is generally lower than in the United States.
8. Describe the ethical issues involved in conducting causal research and the role of
debriefing in addressing some of these issues.
AUTHOR’S NOTES: CHAPTER FOCUS
This chapter provides an overview of causal research and experimentation. The concept of
causality and the conditions for causality are described. Internal and external validity in
experimentation are discussed in detail. A classification of experimental designs is presented and
preexperimental, true experimental, quasi-experimental, and statistical designs are described.
Comparisons between laboratory versus field experiments, and experimental versus
nonexperimental designs are made. Test marketing is presented as an application of experimental
designs.
This chapter covers the material on causal research contained in competing texts. Yet, the
treatment of experimentation is more extensive than that found in competing texts.
This chapter could be taught by focusing on the chapter objectives sequentially. Discuss the
concept of causality (Chapter Objective 1), internal and external validity (Chapter Objectives 2
and 3), preexperimental and true experimental designs (Chapter Objective 4), and experimental
versus nonexperimental designs (Chapter Objective 5). Quasi-experimental designs and
statistical designs may not be covered in detail. Test marketing could be discussed in detail
(Chapter Objective 6). The material on conducting experiments internationally (Chapter
Objective 7), ethical issues (Chapter Objective 8), and the Internet and computers could also be
covered. The concept map can be used to effectively and efficiently summarize experiments
(Figure 7.2).

2
CHAPTER OUTLINE
1. Objectives
2. Overview
3. Concept of Causality
4. Conditions for Causality
(i) Concomitant Variation
(ii) Time Order of Occurrence of Variables
(iii) Absence of Other Possible Causal Factors
(iv) Role of Evidence
5. Definitions and Concepts
(i) Independent Variables
(ii) Test Units
(iii) Dependent Variables
(iv) Extraneous Variables
(v) Experiment
(vi) Experimental Design
6. Definition of Symbols
7. Validity in Experimentation
(i) Internal Validity
(ii) External Validity
8. Extraneous Variables
(i) History
(ii) Maturation
(iii) Testing Effects
(iv) Instrumentation
(v) Statistical Regression
(vi) Selection Bias
(vii) Mortality
9. Controlling Extraneous Variables
(i) Randomization
(ii) Matching
(iii) Statistical Control
3
(iv) Design Control
10. A Classification of Experimental Designs
11. Preexperimental Designs
(i) One-Shot Case Study
(ii) One-Group Pretest-Posttest Design
(iii) Static Group Design
12. True Experimental Designs
(i) Pretest-Posttest Control Group design
(ii) Posttest-Only Control Group Design
13. Quasi-Experimental Designs
(i) Time Series Design
(ii) Multiple Time Series Design
14. Statistical Designs
(i) Randomized Block Design
(ii) Latin Square Design
(iii) Factorial Design
15. Laboratory versus Field Experiments
16. Experimental versus Nonexperimental Designs
17. Limitations of Experimentation
(i) Time
(ii) Cost
(iii) Administration
18. Application: Test Marketing
(i) Standard Test Market
(ii) Controlled Test Market
(iii) Simulated Test Market
19. International Marketing Research
20. Ethics in Marketing Research
21. Summary
22. Key Terms and Concepts
23. Suggested Cases, Video Cases, and HBS Cases
24. Live Research: Conducting a Marketing Research Project
25. Acronyms
26. Exercises
4
27. Internet and Computer Exercises
28. Activities
TEACHING SUGGESTIONS
Chapter Objective 1
● Discuss the concept of causality as used in marketing.
You may want to begin the class by asking a few students what the term ‘causality’
means and writing components of their definitions on the board.
Afterwards, be sure to stress to the students that marketing effects are caused by multiple
variables and the relationships tend to be probabilistic. As such, it is not possible to
conclusively prove causality. Thus, we can only infer a cause-effect relationship between
the variables.
● Via an example, explain the three necessary conditions to infer causality.
1. Concomitant variation: is the extent to which a cause, X, and an effect, Y, occur

together or vary together in the way predicted by the hypothesis under
consideration. Evidence pertaining to concomitant variation can be obtained in a
qualitative or quantitative manner. Thus, we may hypothesize that increasing
product price will lead to an increase in profits.
2. Time order of occurrence of variables: the causing event must occur either
before or simultaneously with the effect; it cannot occur afterwards. Thus, our
profits cannot increase until after we increase the price.
3. Absence of other possible causal factors: means that we can infer causality if all
other factors affecting the subject are absent, i.e., these factors are held constant.
Thus, other factors like store penetration, expanded consumer spending, or
decreased costs must be held constant.
▪ See Table 7.1 and Table 7.2 for examples of concomitant variation.

5
● Review the key definitions related to experimentation.
1. Independent variable—variables or alternatives that are manipulated and whose

effects are measured and compared, such as price levels, different package
designs, and advertising themes.
2. Test units—individuals, organizations, or other entities whose response to the
independent variables or treatments is being examined, such as consumers, stores,
and geographic areas.
3. Dependent variables—variables that measure the effect of the independent
variables on the test units, such as sales, profits, and market shares.
4. Extraneous variables—all the variables other than the independent variables or
treatments that affect the response of the test units to the treatments, such as store
size, store location, and competitive effort.
5. Experiment—the process of manipulating one or more independent variables to
determine their effect on the dependent variable, controlling for the effect of
extraneous factors.
6. Experimental design—a set of procedures specifying (1) the test units and how
these units are to be divided into homogeneous subsamples, (2) independent
variables or treatments that are to be manipulated, (3) dependent variables are to
be measured, and (4) how the extraneous variables are to be dealt with.
● Introduce the symbolic notation used in marketing research.
1. X = the exposure of a group to an independent variable or treatment or event,

the effects of which are to be determined
2. O = the process of observation or measurement of the dependent variable on
the test units or group of units
3. R = the random assignment of test units or groups to separate treatments
The following conventions are associated with the symbols:

1. Movement from left to right indicates movement through time.
2. Horizontal alignment of symbols implies that all those symbols refer to a specific
treatment group.

6
3. Vertical alignment of symbols implies that those symbols refer to activities or
events that occur simultaneously.
Thus, the first example in the text, X O1 O2, indicates a treatment was given to a
sample and measurements at two different points in time were made.
▪ See Question 1.
Chapter Objective 2
● Define validity and describe the difference between internal and external validity.
Start by defining validity, in an experimental setting, as the ability to draw appropriate

conclusions about the effects of independent variables and to make reasonable
generalizations to a larger population of interest. With this definition, we can distinguish
internal and external validity. Internal validity examines whether the manipulation of the
independent variables or treatments actually caused the effects on the dependent
variables, whereas external validity examines whether the cause-and-effect relationships
found in the experiment can be generalized.
Because of the conceptual difficulty in understanding validity, some examples that depict
a research design lacking one of the two types of validity would be instructive. For
example, if we hypothesize that selling through national chains will increase profits, we
must hold all other causes of increased profits constant in order to conclude internal
validity. External validity can be seen in a study that randomly selects stores from all
markets in which a national chain operates. Assuming that the study takes into account all
realistic factors, any findings that hold for all these markets will generalize to all stores in
the national chain.
▪ See Question 2.
Chapter Objective 3
● List some of the extraneous variables that affect validity.

7
1. History (H)— refers to specific events that are external to the experiment but
occur at the same time as the experiment. These events may affect the dependent
variable.
2. Maturation (MA)—is similar to history except that it is concerned with the
changes in the test units themselves, where these changes are not due to the
impact of the independent variables or treatments but occur with the passage of
time. This may affect the test units.
3. Testing—is concerned with the effects that arise due to the process of
experimentation itself affecting the dependent variables. There are two kinds of
testing effects: (1) main testing effect (MT), and (2) interactive testing effect (IT).
4. Instrumentation (I)—are the changes in the calibration of the measuring
instrument or in the observers or scores themselves.
5. Statistical Regression (SR)—effects occur when test units with extreme scores
move closer to the average score during the course of the experiment. The
extreme test units may have been selected because of chance or by design.
6. Selection Bias (SB)—refers to the improper assignment of test units to treatment
conditions where the bias occurs when selection or assignment of test units results
in treatment groups that differ on the dependent variable before the exposure to
the treatment condition.
7. Mortality (MO)—refers to the loss of test units while the experiment is in
progress. This could be caused due to the refusal of test units to continue in the
experiment.
● Describe methods for controlling the effects of extraneous variables
1, Randomization—involves randomly assigning test units to experimental groups.

This should create representative samples free from bias.
2. Matching—test units are matched on a set of key background variables before
being assigned to the treatment conditions. This ensures that a population has
desirable traits that are to be studied.
3. Statistical Control—it is possible to statistically control for the extraneous
variables if these variables can be identified and measured, for example, in
ANCOVA the effects of the extraneous variable on the dependent variable are

8
removed by an adjustment of the dependent variable’s mean value within each
treatment condition.
4. Design Control—using specific experimental designs that differ in the kinds of
extraneous variables that can be used to control the extraneous variables.
▪ See Questions 3 and 4.
Chapter Objective 4
● Discuss the differences in the types of experimental designs.
1. Preexperimental Designs. Do not apply randomization, thus, they can be

influenced by extraneous factors.
2. True Experimental Designs. Randomization is included, thus, allowing
researchers to randomly assign test units and treatments to experimental groups.
3. Quasi-experimental Designs. Lack control over the scheduling of treatments and
the ability to randomly expose test units to treatments.
4. Statistical Designs. A series of several basic experiments that are conducted
simultaneously. These designs suffer from the same shortcomings as the actual
designs of the basic experiments.
Figure 7.1 can be used here to organize your discussion on experimental designs.
● Describe preexperimental designs and their shortcomings.
Note that preexperimental designs include the one-shot case study, the one-group pretest-
posttest design, and the static group design. Stress that the salient feature of these designs
is that they do not employ randomization procedures to control for extraneous factors.
For example, in the one-group pretest-posttest design, an observation on attitudes toward
the brand is taken before and after watching a commercial, but randomization is not used
in selecting observers, thus, the results cannot be extended to the population as a whole.
● List the significant features of a true experimental design and provide examples.

9
First, to introduce the ensuing discussion, distinguish true experimental designs by the
fact that the researcher can randomly assign test units to experimental groups and also
randomly assign treatments to experimental groups.
Examples of True Experimental Designs:

1. Pretest-Posttest Control Group Design. This design controls for most of the
extraneous variables. Selection bias is eliminated by randomization, and
interactive testing effect is not controlled due to the effect of the pretest
measurement on the reaction of units in the experimental group to the treatment.
2. Posttest-Only Control Group Design. Compared to the Solomon four-group
design, this design is fairly simple to implement because there is no
premeasurement, thus, the testing effects are eliminated. However, this design is
sensitive to selection bias and mortality.
3. Solomon Four-Group Design. The Solomon four-group design overcomes the
limitations of the pretest-posttest control group and the posttest only control group
designs in that it explicitly controls for interactive testing effect, in addition to
controlling for all extraneous variables. This design allows the researcher to
update and measure the various effects.
It will prove instructive to use a running example in explaining these designs. A standard
example is to use advertising research in the measurement of consumer attitudes toward a
commercial or the brand being advertised.
● Explain the analysis of quasiexperimental designs.
Mention that in a quasi-experimental design, the researcher can control when

measurements are taken and on whom they are taken, but the researcher is lacking control
over the scheduling of the treatments and the ability to randomly expose test units to the
treatments. Quasi-experimental designs are quicker and less expensive than true
experimentation, but should only be used when a true experimental design is not feasible.
● Explain the nature and uses of statistical designs.

10
Describe statistical designs as a series of basic experiments that enable statistical control
and analysis of external variables, thus several basic experiments are conducted
simultaneously.
Advantages:
1. The effects of more than one independent variable can be measured.
2. Specific extraneous variables can be statistically controlled.
3. Economical designs can be formulated when each test unit is measured more than
once.
Examples of a randomized block design, Latin Square design, and Factorial design can be
constructed for demonstration purposes.
▪ See Table 7.4, Table 7.5, and Table 7.6
Chapter Objective 5
● Start a class discussion on whether laboratory or field experiments are more useful in
marketing research.
Begin this discussion by simply asking students which form of experimentation is better.
You may want to note that laboratory experiments make up the bulk of consumer
research because of their ability to control extraneous variables and their relative
efficiency in gathering data. However, for certain studies, field experiments are used. For
example, Coca-Cola counts the shelf space it and its competitors receive in local grocery
stores when promotional variables are manipulated. Thus, each type of experimentation
has its role to play in marketing research, but because causality cannot be inferred from
field experiments, laboratory experiments predominate.
▪ See Table 7.7 for a summary of laboratory vs. field experimentation.
● Discuss why nonexperimental designs are limited for inferring cause-effect relationships.
Mention that descriptive studies are sometimes used to infer causality, but this may not
be appropriate. In descriptive studies, prior equivalence of the groups with respect to both
the independent and dependent variables is difficult to establish, as is time order of
11
occurrence of the variables. Finally, it offers little control in eliminating other extraneous
factors.
● Discuss the limitations of experimentation.
Start by asserting that theoretically, experimentation is a very powerful way to uncover

causal relationships. However, in practice, real world considerations prevent it from
achieving its optimal effectiveness. These considerations are:
1. Time: experiments can be time consuming; however, the experiments should be

long enough in duration so that the post-treatment measurements include most, or
all the effects of the variables.
2. Cost: the requirements of experimental group, control group, and multiple
measurements significantly add to the cost of the experiment.
3. Administration: experiments can be difficult to administer, and it is not always
feasible to control for the effects of the extraneous variables.
▪ See Questions 5, 6, 7, 8, 9, 10, 11, and 12.
Chapter Objective 6
● Define and classify test marketing.
Define test marketing as an application of a controlled experiment, done in a limited but

carefully selected part of the marketplace called test markets, which involves a
replication of the planned national marketing program for a product. In a standard test
market the product is sold through regular distribution channels. The company’s own
sales force is responsible for distributing the product, stocking the shelves, and taking
inventory at regular intervals. A controlled test marketing program is conducted by an
outside research company. The research company is responsible for all activities
associated with the test market. Simulated test markets yield mathematical estimates of
market share based on initial reaction of the consumers to the new product.
▪ See Questions 13, 14, and 15.
Chapter Objective 7
● Examine the difficulties involved with international experiments.
12
It is difficult to control for the time order of occurrence of variables and it is difficult to
control for the absence of other possible causal factors, two of the necessary conditions
for causality in an experiment.
o Control of extraneous variables is particularly problematic.
o It may not be possible to address this problem by adopting the most appropriate
experimental design as environmental constraints may make that design
infeasible.
o The internal and external validity of field experiments conducted overseas is
generally lower than it is in the United States.
EXAMPLE: M&M/Mars has set up massive manufacturing facilities in Russia and

advertises its candy bars on television there. Yet, sales have been low. Is Mars
advertising too much, too little, or just right? While the answer could be determined by
conducting a field experiment that manipulated the level of television advertising, such
causal research is not feasible given the tight control of television programming and
advertising by the Russian government. TV stations are owned and operated by the
government with severe restrictions on television advertising. This makes field
experiments manipulating advertising levels extremely difficult.
Chapter Objective 8
● Discuss the ethical responsibilities resulting from disguised experiments.
It is often necessary in experimentation to disguise the purpose of the research to produce

valid results. Disguising the purpose of the research should not lead to deception,
however. Although this seems like a paradox, one solution would be to disclose the
possible existence of deception before the start of the experiment and allow the
participants the right to redress at the conclusion of the experiment. The following four
items should be conveyed: (1) inform respondents that in an experiment of this nature a
disguise of the purpose is often required for valid results, (2) inform them of the general
nature of the experiment and what they will be asked to do, (3) make sure they know that
they can leave the experiment at any time, and (4) inform them that the study will be fully
explained after the data have been gathered and at that time they may request that their
information be withdrawn. The procedure outlined in item (4) is called debriefing.
13
One further ethical concern in experimentation involves using the appropriate
experimental design to control errors caused by extraneous variables. It is the
responsibility of the researcher to use the most applicable experimental design for the
problem. Determining the most appropriate experimental design for the problem requires
not only an initial evaluation but also continuous monitoring.
The Internet and Marketing Research

● Indicate that the Internet and computers are helpful in the analysis of experimental design
data.
Different experimental treatments can be displayed at different Web sites. Respondents

can then be recruited to visit these sites and respond to a questionnaire that obtains
information on the dependent and extraneous variables. Thus, the Internet can provide a
mechanism for controlled experimentation, although in a laboratory type of environment.
To complement the Internet, microcomputers and mainframe software can be used in the
design and analysis of experiments. The comprehensive statistical-analysis software
packages SAS and Minitab can be used to design experiments.
ACTIVE RESEARCH
It should be noted that a variety of answers are appropriate. The ones given here are merely
illustrative. DM denotes decision maker and MR denotes marketing researcher.
DM: FTC
To ensure the smooth operation of our free market system, the Federal Trade
Commission (FTC) enforces federal consumer protection laws that prevent fraud,
deception and unfair business practices. The Commission also enforces federal antitrust
laws that prohibit anticompetitive mergers and other business practices that restrict
competition and harm consumers. Whether combating telemarketing fraud, Internet
scams or price-fixing schemes, the FTC’s primary mission is to protect consumers.
14
o Information overflow, tough for customers to differentiate noise and useful
information.
o Information flow cannot be controlled or traced. This can lead to
misrepresentation of information, fraud etc.
o Dumping of products especially from foreign countries (web based selling of
drugs by Canadian and Indian companies)
o Increased possibility of collusion between companies
MR: FTC
The conditions necessary to conclude such causality are:
1. Concomitant variation- the information available has increased with increased
consumer use.
2. Time Order- Increased information lags or concurs with increased information
use.
3. Absence of other possible causes
MR: Fox News

Information on consumers’ preferences for network news channels can be obtained from
sources such as http://www.rateitall.com/t-8-tv_news_shows.aspx.
A preexperimental design would not be appropriate as there are three experimental

groups. A statistical design is called for.
DM: Fox News

o The popularity ratings for channels can be used to assess the attributes that
audiences look for in Network News Channels.
o Based on experimentation causality can be assigned to factors that make the news
more attractive.
o Improve the attributes preferred by audience
o Convey the change in form and content to audience through appropriate PR and
Advertising channels
EXPERIENTIAL LEARNING
15
1. Students should be encouraged to visit www.bestbuys.com and identify the relevant
information.
2. Students should be encouraged to search the Internet and identify the relevant
information on consumers’ price sensitivity for digital cameras.
3. A factorial design is appropriate. The price of digital cameras could be varied and
consumers’ willingness to buy measured. It would be important to control for income
and digital camera usage.
4. It is likely that the market is segmented with respect to price sensitivity. Different
prices can be charged to the different segments with some differentiation in the
cameras offered.

16
DECISION RESEARCH
It should be noted that a variety of answers are appropriate. The ones given here are merely
illustrative.
The Marketing Research Decision
1. It would be useful to conduct exploratory research in form of secondary data analysis and
focus groups followed by causal research in the form of an experiment.
2. A lot of secondary data about apparel industry is available from online as well as
traditional third party databases. This can be used initially to gather information about the
success of private labels and in-house brands. The focus groups are helpful in gaining
further understanding of the conclusions drawn from the analysis of secondary data,
understanding consumer priorities, perceptions and preferences. The specific causal
design that is recommended is a factorial design. The factor, brand name can be varied at
three levels: Levi’s, Gap, and Arizona. Respondents can be randomly assigned to one of
these brands and asked to express preference for the brand rate its power. Current usage
of these brands should be controlled.
3. The causal design, as specified, will provide a direct relative measure of the power of the
three brands when the mean levels are compared.
The Marketing Management Decision
1. He should introduce another brand of lower priced jeans and sell Levi’s through discount
stores like Wal-Mart and Target.
2. Pricing appears to be one of the reasons why Levi’s is loosing the battle for market share.
It would be a good idea to launch a cheaper line of jeans to appeal to the cost conscious
market segment. To reach the new target segment, the company would want to increase
advertising spending in targeted marketing efforts. The new line of jeans should be
distributed through different channels than that of the existing high priced segment. This
will ensure the necessary reach.

17
PROJECT ACTIVITIES
1. The posttest-only control group design should be used. A sample of respondents would
be selected at random. The sample would be randomly split, with half the subjects
forming the experimental group and the other half constituting the control group. Only
the respondents in the experimental group would be exposed to the TV program
containing the test (Sears) commercial. Then, a questionnaire would be administered to
both groups to obtain posttest measures on attitudes toward the department store (Sears).
The difference in the attitudes of the experimental group and the control group would be
used as a measure of the effectiveness of the test commercial.
2. Only causal designs are truly appropriate for inferring cause-and-effect relationships.
Although descriptive survey data are often used to provide evidence of “causal”
relationships, these studies do not meet all the conditions required for causality. Also,
descriptive research offers little control over other possible causal factors.
Descriptive research constitutes the most popular research design in marketing research,
and we do not want to imply that it should never be used to examine causal relationships.
Indeed, some authors have suggested procedures for drawing causal inferences from
descriptive (nonexperimental) data. However given the limitations of descriptive
research, extreme caution should be exercised when using it for examining causal
relationships.
EXERCISES
Questions
1. There are three requirements or conditions that must be satisfied before a causal
relationship can be inferred. The three conditions are:
(a) Concomitant variation of the two variables.
(b) Time order of occurrence of variables.
(c) Elimination of other possible causal factors.
2. The difference between internal and external validity is that internal validity is concerned
with the question of whether the observed effects on the dependent variable have been
caused by variables other than the treatment, and control of extraneous variables is
necessary for establishing internal validity. External validity, on the other hand, is

18
concerned with whether the cause-effect relationship can be generalized. More often than
not, a tradeoff is required between internal and external validity. While internal validity
can be raised in an artificial environment, this reduces the generalizability of the results
and consequently, the external validity.
3. Examples of extraneous variables that can reduce validity are:
(a) History (H): A firm is testing a new price level when a rival firm starts a
promotional campaign.
(b) Testing: A pretreatment questionnaire biases responses on the posttreatment
questionnaire.
(c) Selection Bias (SB): While assessing the market size for a new soft drink, the
sample was drawn only from households in the upper 50 percent income bracket.
(d) Mortality: 20 percent of the respondents failed to respond to the posttreatment
questionnaire.
(e) Instrumentation: In the case of a pretest-posttest control group design,
questionnaires with different formats were used to measure pretreatment and
posttreatment attitude.
(f) Statistical Regression: In an experiment, suppose two measurements are made of
a consumer’s attitude toward a test product, one before tasting it and one
afterwards. If the extreme scores move towards the average, regression has
occurred.
4. The various methods for controlling extraneous sources of variation are:
(a) Randomization. This involves randomly assigning test-units to experimental
groups by using random numbers. Treatment levels are also randomly assigned.
Such random assignment usually results in an equal representation of extraneous
variables in each treatment condition.
(b) Matching. In this case, the test units are matched on a set of key characteristics
before being assigned to the treatment conditions.
(c) Statistical Control. This involves the use of statistical methods such as
ANCOVA, which removes the effect of extraneous variables by adjusting the
mean values of dependent variables within each treatment condition.
(d) Design Control. Extraneous variables can also be controlled by using specific
experimental designs.
5. The distinguishing feature of the true experimental design, as compared to the
preexperimental design, is randomization. In true experimental designs, the researcher
19
can randomly assign test units to experimental groups and also randomly assign
treatments to experimental groups.
6. The steps involved in implementing the posttest-only control group design are:
(a) Select a sample of respondents at random.
(b) Randomly assign the respondents to two groups (i.e. experimental group and
control group).
(c) Respondents in the experimental group would then be exposed to a treatment.
(d) Posttreatment measurements are obtained from both groups using a measuring
instrument like a questionnaire.
The design is described symbolically as follows:
EG: R X 01
CG: R 02
Treatment effect is given by:
TE = 01 – 02
7. A time series experiment is a quasi-experimental design. It involves periodic
measurement on the dependent variable for a group of test units. Then the treatment is
administered by the researcher or occurs naturally. After the treatment, periodic
measurements are continued in order to determine the treatment effect. A time series
experiment may be symbolically described as:
01 02 03 04 05 X 06 07 08 09 010
This design is used in cases where the researcher lacks control over the scheduling of the
treatment and the ability to randomly expose test units to the treatment but can control
when measurements are taken and on whom they are taken.
8. A multiple time series design is different from the basic time series in that a multiple time
series design has an additional group of test units added to serve as a control group.
9. The advantages statistical designs have over basic designs are:
(a) In the case of basic designs, the effects of only one independent variable or
treatment can be measured while in case of a statistical design, the effects of more
than one independent variable can be measured.
(b) In the case of statistical designs, specific extraneous variables can be statistically
controlled.

20
(c) Economical designs can be formulated when each test unit is measured more than
once.
10. The limitations of the Latin Square design are:
(a) They require an equal number of rows, columns, and treatment levels.
(b) Only two external variables can be controlled simultaneously.
(c) They do no allow interactions of the external variables with each other or with the
independent variable.
11. A laboratory experiment is one where the researcher creates an artificial environment for
the purpose of experiment. Thus, he has a great degree of control over extraneous
variables. On the other hand, a field environment is one where the experiment is
conducted under actual conditions.
Laboratory experiments have some advantages and some disadvantages vis-à-vis field
experiments. The advantages are that there is a greater control over extraneous variables,
internal validity is high, and time required is short. It is also economical. The
disadvantages are that the environment is artificial and external validity is low. Therefore,
the results cannot be safely generalized. Also, the reactive error is high, due to
artificiality of the environment which may cause the respondent to react to the situation
itself, rather than to the independent variable.
12. Descriptive research should not be used for establishing causal relationships for the
following reasons:
(a) It is difficult to establish the prior equivalence of the groups with respect to both
the independent and dependent variables in descriptive research.
(b) It is difficult to establish time order of occurrence.
(c) It provides little control in eliminating other possible causes.
13. Test marketing is an application of a controlled experiment done in a limited but carefully
selected part of the marketplace called test markets. It involves a replication of a planned
national marketing program for a product in the test markets. The three types of test
markets are:
(a) Standard test market: The product is sold through regular distribution channels
and, typically, the company’s own sales force is responsible for distributing the
product. It involves a one-shot case study.
(b) Controlled test market: The entire test marketing program is conducted by an
outside research company, which also handles distribution and field sales
operations in the test market.
21
(c) Simulated test market: These are also called laboratory tests and yield
mathematical estimates of market share based on initial reaction of consumers to
the new product.
14. The main difference between a standard test market and a controlled test market is that in
a standard test market the company’s own employees are responsible for the distribution
of the product; whereas in a controlled test market, the entire marketing program is
conducted by an outside research company.
15. In a simulated test market, respondents are intercepted in high-traffic locations such as
shopping malls and prescreened for product usage. The selected individuals are exposed
to the proposed new product concept and given an opportunity to buy the new product in
a real-life or laboratory environment. Those who purchase the new product are
interviewed at a later date to determine their evaluation of the product and repeat
purchase intentions. The trial and repeat-purchase estimates so generated are combined
with data on proposed promotion and distribution levels to obtain a projected share of the
market.
Problems
1. (a) Independent Variable - The commercial

Dependent Variable - Attitude towards abortion
(b) Posttest-only control group design
(c) The posttest-only control group design controls for the various sources of
invalidity, however, internal validity may be affected by the samples chosen.
Since a pretest was not conducted to measure attitudes, attitudes towards abortion
before seeing the commercial are not known, although it is hoped that
randomization has adjusted for this effect.
External validity may be affected because this was a lab experiment, not an actual
field experiment, thus, the results may not be generalizable to those obtained
when the commercial is actually viewed in home.
2. If the respondents had been selected by convenience, a static group design would result.
Any experimental effect could also be attributed to selection or mortality.
3. (a) There is a tendency towards concomitant variation in the data, as can be seen in
computing percentages.
22
Product Use Income
High Medium Low
High 40 20 16
Medium 35 46 24
Low 25 34 60
TOTAL 100 100 100
(b) Low income consumers exhibit low product use.

4. (a) This is an example of the one-shot case study. The internal validity is threatened
by history, maturation, selection, and mortality.
(b) This is an example of the posttest-only control group design. Internal validity is
not hampered by extraneous variables.
5. Many answers are possible for each design. One solution is provided as an example.
(a) Measuring the attitude towards a new advertisement or new product.
(b) Evaluating the effectiveness of a change in a product attribute or the effectiveness
(c) Evaluating the attitude toward a new advertisement or product when time and cost
are not significant factors, forcing researchers to reduce sample size, quickly
determine results, and/or keep costs down.
(d) When great precision is needed and the effectiveness of an advertising program
needs to be monitored over time to show the process of change in the population.
(e) A new marketing program is being initiated which must be evaluated to determine
its effectiveness. The goal is to determine which of the components of the
program (price, promotion, channels, etc.) are the most important factors leading
to sales and to assess the interaction of these components on sales.
Internet and Computer Exercises
1. Computer controlled experiments are becoming increasingly popular in marketing

research. They ensure that proper technique is followed when conducting an experiment.
As such, the validity of the results is improved.
2. Several of the designs can be implemented. A two factor design where factor one denotes
the value of coupon (none, low, medium, and high) and factor two denotes product use
(none, low, medium, and high) seems to be very appropriate. Students should select a
specific product and also define the levels (low, medium, and high) for each factor.

23
3. The existing and the three new packages can be displayed, one at each specific location
on the Internet. Respondents can be recruited and randomly assigned to each package
location (URL), asked to view the package and answer several attitudinal and behavioral
intent questions. The package with the most favorable attitude and/or the highest
behavioral intent can then be identified.
4. The previous (existing) and the new version of EXCEL can be made available, one at
each specific location on the Internet. Respondents can be recruited and randomly
assigned to each EXCEL version, and then asked to do a specific task using that version.
Then they answer several questions relating to ease of use, performance, features, and
overall preference. The most favorable version can then be identified.
5. Respondents would be randomly recruited and randomly assigned to one of two Internet
locations (URLs). The experimental group of respondents would first see the print ad for
Toyota Camry and then respond to a battery of attitudinal and behavioral intent questions.
The control group respondents would not see the print ad but respond to the same battery
of attitudinal and behavioral intent questions. The effectiveness of the print ad can be
determined by comparing the responses of the two groups.

24
ACTIVITIES: QUESTIONS AND ANSWERS
Role Playing
Q1. You are a marketing research manager for the Coca-Cola Company. The company would
like to determine whether it should increase, decrease, or maintain the current level of
advertising dollars spent on Coke Classic. Design a field experiment to address this issue.
A1. One of several designs can be used for this field experiment. A pretest-posttest control
group design is outlined below:
(a) Select three sets of test markets with similar demographic profiles, competitive
environments and sales volume of Coke Classic.
(b) Randomly increase ad budgets in one set of markets, decrease them in a second
set and maintain them in the third set of markets.
(c) Track sales volumes for three months in each set of markets.
(d) Analyze the sales results to determine differences in performance.
Q2. What potential difficulties do you see in conducting the experiment just described? What
assistance would you require from the Coca-Cola management to overcome these
difficulties?
A2. Potential difficulties include access to sales data, selecting three similar markets to test,
changing competitive dynamics and objections from bottlers in the test market where ad
expenditures will decrease.
Management can assist by ensuring corporate compliance for gathering data, allocating
the necessary funds, pacifying affected bottlers.
Fieldwork
Q1. Select two different perfume advertisements for any brand of perfume. Design and
conduct an experiment to determine which ad is more effective. Use a student sample
with 10 students being exposed to each ad (treatment condition). Develop your own
measures of advertising effectiveness in this context.

25
A1. The purpose of this exercise is to have the student actually design and conduct a simple
experiment in order to apply the material discussed in the chapter. They should also gain
an appreciation for the rigor of statistical testing and the assumptions a researcher must
make when conducting an experiment. Because quantitative analysis has not been
covered in the text so far, it should be interesting to see what measures students devise to
measure the advertising effectiveness. Whatever measure they choose, it should be
justifiable and valid in this setting.
Group Discussion
Q1. “Whereas one cannot prove a causal relationship by conducting an experiment,

experimentation is unscientific for examining cause-and-effect relationships.” Discuss
this statement as a small group.
A1. Issues which can be discussed include the role of inference in drawing conclusions, the
difficulty of isolating all possible sources of variation in social science experimentation,
the historic value of experimentation in deriving theories and inferring relationships, and
the nature or definition of science, (i.e., is science only limited to proofs which account
for all sources of variation?).
Note: Answers to the Running Case on Dell are provided in the case solutions

26
Another random document with
no related content on Scribd:
Fig. 11
The Swing is Made upon One Ski Instead of Using Both as in the
Christiania Swing
Closely akin to side-slipping is the Christiania swing with the stick,

which is accomplished by pressing with both heels at the same time,
while the stick digs well into the snow above. This variation of the
side slip is easily done, and the skier is turned sharply uphill to come
to a quick stop. When a sharp hill is met with, that is considered a bit
too steep to take straight, this swing with the stick may be made by
taking a zigzag course down grade steering clear of any obstacles
by snowplowing, stemming, or side-slipping; and turning the corners,
or “tacking,” by making use of the Christiania swing and the stick, as
shown in Fig. 10.
The “S”-turn may likewise be used for turning corners, without the
necessity for stopping to make the ordinary kick turn. A good way to
learn this useful movement is to run straight downhill in a snowplow
position, reduce the speed to a comfortable walking pace with the
stick, and stem with the ski. If this is done with the right ski, the “S”-
turn is made by throwing practically the whole weight of the body on
the right ski, at the heel, and pressing it outward while the stick is
carried ahead and below the skier. If the heels are kept well apart,
and the toes close together, the skier will have no trouble about
swinging around in a curve and be off on the other tack. About the
only difficulty in making the “S”-turn is the position of the body, which
must be thrown somewhat out and away from the hill. To the novice
this at first seems to invite a fall, but a few trials will soon prove that
the weight of the body must be thrown on the foot which circles on
the outside of the curve, hence the apparently unnatural position of
the body is essential for a good turn. By bringing the stick well
forward and downhill, the skier uses his staff as a pivot upon which
the turn is made.
The Christiania swing, made without the stick, is a favorite with
expert ski runners when running on rough and steep ground and is a
good way of stopping. The swing may be made both to the right and
left. To make it to the right, keep the skis close together, the right a
trifle in advance, with the weight of the body equally on both feet and
with knees slightly bent. Now throw the weight more forward and
upon the toes, while the heels are carried forward and outward to the
left. The body must lean to the right—the direction in which the swing
is made—and twisted somewhat at the waist; and the sharper the
turn, the more the body must lean sideways to keep the balance.
The swing to the left is made in the, same fashion, only the left ski
should be a trifle advanced and the body thrown to the left.
Fig. 12
To Make the Jump the Skier Assumes the Easy Position Required for
Coasting Downhill
The Telemark swing is more difficult to master than the Christiania

swing, because it is done on one foot, or ski, instead of using both,
and as it is less powerful than the latter, it is of far less use for
stopping. To make the Telemark swing to the right, assume the
regular position for downhill coasting, and, advancing the left foot,
turn the ski so that it rests on its edge as when making the
snowplow, throw the body to the right and lean in toward the slope to
keep the balance. To make the swing to the left, advance the right
foot, turn the body to the left and lean as before. This is shown in
Fig. 11. The Telemark turn is, in fact, made in the same manner as
stemming, and the sharpness of the swing rests altogether upon the
quickness with which the heel is thrown outward and the body turned
in the direction the skier desires to swing. The swing is made upon
one ski, and the key to the whole swing is the knack of raising the
heel of the other foot off its ski until it rests upon the toes. That this is
hard to do goes with the telling, and the novice should first acquire
the knack of balancing by running straight downhill with the weight
thrown on one foot. When this can be done, and not before then, the
skier is ready to practice the turn. The Telemark swing, like all other
turns, is easily acquired at slow and moderate speeds, and becomes
more and more difficult to make as the speed is increased and the
turn is made more sharply and quickly.
Jumping on skis is one of the most exhilarating winter sports, and
it is a pity that it is not more popular wherever a medium-heavy fall of
snow occurs. While touring on skis across a hilly country, there will
be many natural jumps to encounter, for drifts, stumps, rocks, and
other rises in the ground, when well covered and padded with snow,
make good jumping-off places. While but a few skiers may have
attempted such high leaps as the famous Holmenkollen,
Fiskertorpet, or Foldberg, all who have done much ski running have
done a little jumping, since, when running downhill, an unexpected
dip is often encountered, and a rise in the ground causes the skier to
leave the ground for a short distance and alight several feet below.
Doubtless the skier has enjoyed the flying-like sensation of this brief
moment, and very likely he has climbed the hill to repeat the jump.
Moreover, this has very likely demonstrated that the distance of the
jump depends upon the height of the dip, the speed of the skier
passing over it, and likewise upon the spring of the body on the take-
off. In making a jump of any height, the take-off may be level,
pointing up or even downhill, and constructed with framework
extending out from the hillside, or consist merely of a large boulder,
or a pile of logs, well padded with snow. The height of the slope
chosen will, of course, regulate the distance of the jump, and the
place where the jumper alights should be fairly steep, since, if the
skier lands upon a level place great difficulty will be experienced in
keeping the balance, therefore the usual jumping hill, where jumping
competitions are held, is provided with a 30°, or steeper, landing
place, and this merges gradually into the outrun, or slope,
connecting the hill with the level ground below.
Fig. 13
Each Member of the Party should be Provided with a Ruck Sack of Good
Capacity
For the safety of the skier, the snow should be firm but not icy or
hard, and this is easily done by packing the snow down well by
means of the skis. A good, thick padding of snow is of course
essential, and a thickness of 2 ft. is really needed at the landing
place and at the take-off. In our more northerly sections, plenty of
snow usually falls, but wherever a few sportsmen get together, it is
an easy matter to shovel sufficient snow to prepare a good and safe
jumping hill.
To gain confidence and acquire some useful experience in
jumping, the novice should practice leaping from a 2-ft. rise and
gradually increase the height of the take-off by piling more snow
upon it to increase its height. One or two packing cases firmly placed
upon a smooth, steep hillside, and well padded with 2 ft. of well-
trodden snow, will make a nice take-off. For the beginning the take-
off may point slightly downhill or be fashioned level, and as the skier
becomes more proficient, snow may be added to the edge so that
the take-off will send the jumper well up into the air.
The knack of jumping is nothing more than balancing the body
upon alighting, and the steeper the landing place the easier it is to
keep the balance. To make the jump in good form, the skier assumes
the easy position required for coasting downhill, as shown in Fig. 12.
When within a dozen yards of the take-off the body is lowered until
the skier is in a crouching position with the arms extending back as
in the act of jumping. Arriving within a couple of yards of the dip the
body and arms are thrown forward, which transfers the weight of the
body upon the toes, and the body is straightened up and the arms
are raised not unlike the wings of a bird, to keep the perfect balance
of the body. The straightening up of the body, known to skiers as “the
sats,” is the leap proper and must be timed so that the body
assumes an erect position when the jumper is not less than 12 ft.
from the edge of the take-off. The beginner will invariably jump too
late, but after a little practice, and profiting by numerous mistakes,
the take-off will be timed correctly. Alighting after a jump is best done
by advancing one ski a trifle to keep the balance, and bending the
knees a bit to lessen the impact. The jumper ends with the Telemark
or Christiania swing.
When taking tours of any length on skis, each member of the party
should be provided with a ruck sack of good capacity. That of the
expanding type, made with two outside pockets, and with gores at
the sides, is a good, sensible pack. It should be made of 8-oz.
waterproof khaki and fitted with shoulder straps of good width, to
prevent chafing the shoulders. Leather ruck sacks are sometimes
used, but are heavier in weight and more expensive but no better.
One member of the party should carry some kind of repairing outfit,
consisting of an awl, a length of leather thong, a few spare straps
and a stout cord, or string. These sacks are shown in Fig. 13.
Knife, Fork, and Spoon Holder
The Holder Keeps the Cutlery in a Position for Easy Selection and Grasping
The holder is made of a piece of sheet copper of sufficient

thickness to support the number of pieces of cutlery used. The piece
is notched to admit the different pieces, and its back edge is bent at
right angles to provide means of fastening it to a support, a wall or
the back of the kitchen cabinet. It will save space, as well as time,
since it is much easier to grasp one of the articles when wanted than
if they are kept in a drawer.—Contributed by L. E. Turner, New York
City.
Making Round Rods for Fish Poles
In looking forward to the enjoyment that may be had in the spring,
it is well to prepare and overhaul the fishing apparatus or the
shooting equipment. In doing so, it may be necessary to make a joint
for the fish rod or perhaps a rod for the gun. These can be easily cut
if they are sized and run through holes made in a piece of thin metal
as follows: Make several holes of the desired sizes in a steel plate,
and ream them out with a rather dull taper reamer, so as to leave a
bur on one side. This bur should be filed down almost level with the
surface of the metal, leaving the edges flat and sharp. If a rod of
wood from which the article is to be made is put in a hole and drawn
through from the opposite side to the bur, a nice round rod will result.
As the rod becomes smaller, use a smaller hole until the required
diameter is obtained. A saw plate that is not too thin is about the
proper thing to use for the steel plate. It will be necessary to draw the
temper to make the holes, but it is not necessary to retemper it after
the holes are made.
¶Celery keeps well in a small box of dry sand.

A Ski Sled
By GEORGE J. EGELBERG
T he sled is built low and wide so that it will not tip easily. The skis, or
runners, are cut 10 ft. long and 6 in. wide, from 1-in. ash boards
that are straight-grained. At the points where the curve is to be
formed, plane off about ¹⁄₄ in. on the upper side, but do not plane off
any at the very tip end. This will allow the skis to be more easily
bent. If it is not handy to steam the skis, put them in boiling water,
and be sure that at least 1¹⁄₂ ft. of the points are covered. Provide a
cover for the vessel, so that only very little steam may escape. Let
them boil for at least one hour. A good method of bending the points
is shown. When the skis are taken from the water, put them as
quickly as possible in the bending blocks, side by side, and bend
them with a slow, even pressure. Weight the extending ends and
leave the skis in the blocks 8 or 10 hours to dry. Sharpen the points
after they are bent.
The Runners are Shaped Like a Ski and are Joined Together with Knees for
the Top Board
The sled will run easier if the skis have a slight rocker curve. To
make this curve, have the center block 6 in. while the two end blocks
are 5¹⁄₂ in. high. A ¹⁄₄-in. flat-head bolt is run through the ski, the
block, and the cross strip. The holes are countersunk in the surface
for the heads of the bolts. The top is made of three 6-in. boards,
fastened to the crosspieces. It is a good plan to brace the tips of the
skis with a 2-in. strip.
Clocks for the Craftsman
An Ordinary Alarm Clock Mounted in a Wood Base Made in Elaborate

Designs to Resemble a Timepiece of High Value; yet Inexpensive to Make
Three designs of clocks are shown, which can be easily made in

oak, or other wood, that will match other furniture. The sizes of the
pieces required are given by the dimensions in the drawings.
The clock is a matter of choice. Prices in most stores range from
75 cents up and the works are of the ordinary alarm-clock variety.
After selecting the clock the small legs as well as the back plate are
removed. The hole cut in the wood for the clock must be a snug fit,
and after placing it in position, the back plate is replaced.
The finish may be a wax or gloss, as desired, and directions for
applying it will be found on the can containing the material.
A Compact Galvanometer
A small portable galvanometer is one of the most useful
instruments to the electrical experimenter. There are continually
arising instances where it is necessary to test through and identify
certain wires, for which purpose a small galvanometer and a dry cell
are quite sufficient. For comparing the resistances by the well-known
Wheatstone-bridge method, a galvanometer is, of course,
indispensable. If the winding is made suitable, or by placing a shunt
across the terminals to reduce the deflection, a small galvanometer
will roughly indicate the current passing and thus enable one to
compare his dry cells and eliminate the weak ones. Rough voltage
comparisons may also be made by placing a resistance in series
with the galvanometer.
For constructing this instrument, a good pocket compass, of about
2-in. diameter, must be procured. Prepare a neat little box with the
four edges accurately beveled off. On the under side of this, carefully
cut a channel, about ¹⁄₂ in. wide and 2¹⁄₂ in. long, to a depth that will
bring the bottom of the slot within ¹⁄₈ in. of the top of the base block.
Place two binding posts on the base, as indicated, and secure the
compass in place with cement, or by two very small nails put through
the bottom. If the glass cannot be removed, it will be necessary to
solder the nail heads to the bottom of the compass box, after having
carefully removed the lacquer.
The correct wiring will depend on the strength of the current
handled. It is, however, very easy to get an idea of what the
deflection will be under certain conditions by merely making a
preliminary trial, after winding a few turns of any magnet or bell wire
at hand around a small piece of wood, and slipping the coil so
formed into the slot on the under side of the base block. The winding
may be from two or three turns of heavy wire up to several hundred
turns of fine magnet wire, but after one or two trials, the maker will
have no trouble in determining his particular requirements.
Galvanometer Made of a Compass Set on a Wood Base, with Coil and Wire
Connections
The final coil should be wound lengthwise on a wood core, and the
whole packed neatly into the slot. Connect up the ends to the binding
posts, and then glue in a thin piece to hold the coil in place.
By drilling a small horizontal hole through the base, as indicated
by the two dotted lines in the top view of the working drawings, and
inserting a small bar magnet, ¹⁄₈ in. in diameter, or less, the
instrument may be rendered independent of the earth’s magnetism
and used without reference to the north point. Such a controlling
magnet reduces the time required to bring the needle to rest after it
has been violently reflected.
¶Woodwork about a house, when primed with white lead made quite
thin in raw linseed oil, will never blister unless moisture gets back of
it. Yellow-ocher priming will cause blistering at any time up to 20
years.
A Perpetual Calendar
It is Only Necessary to Change the Sliding Pieces to Set the Calendar for
Each Month
It is only necessary to set this calendar the first of each month, by

sliding the insertions up or down, to get the proper month or week.
The calendar, as it is shown, is set for January, 1916. Saturday is the
first day and Friday the seventh, and so on. It is not confusing and
can be read either by the day or date. If the day is known it will show
the date, and if the date is known it will show the day. The illustration
clearly shows the parts, which can be cut from heavy paper or
cardboard.
Heater for the Experimenter
A convenient small heater for heating liquids in experimental work,
and even in making a hot drink where there is no gas, can be readily
made from an ordinary oil lamp and a small round can, having a
crimped-on head or bottom. The can should be of such diameter that
the prongs of the lamp burner will hold it firmly in place. A hole
should be made in the bottom of the can. It is then placed, upside
down, on the lamp burner. If the top comes too far from the flame,
cut off a strip around the edge.—Contributed by Clarence S. H.
Anderson, Worcester, Massachusetts.
A Camp Chair Constitutes the Body of the Sled and the Legs are Equipped
with Runners
A Folding Ice Sled

On a smooth ice surface, or on hard snow, the sled shown will run
easily, and a skater can push another with surprising speed by a light
push on the shoulders while the rider rests his feet on the front of the
runners. The sled is light, and it can be folded up and carried under
the arm. It is also handy for putting on the skates, or for use in a
crowded car.
Any camp stool will do for the main part of the sled. Holes are
bored in the ends of the legs to receive the lugs on the runners
snugly. If the builder is not equipped with a forge, a blacksmith will
make the runners cheaply. The sliding surfaces of the runners are
smoothed with a file.—Contributed by Thomas Lappin, Portland,
Ore.
¶A column of water 27.6 in. will have a pressure of 1 lb. per square
inch.
Cleaning Tinware with Milk
Some housewives advise a system of dry-cleaning for tinware for
the reason that it insures a surface free from rust which is less liable
to burn. Where washing is preferred, however, a little milk added to
the water proves more satisfactory than either soap or soda, its
peculiarly solvent effect upon grease obviating all necessity for hard
scouring, which latter will wear the tin coating and gradually cause
the article to become useless for holding food and more apt to rust
into holes.—Contributed by J. E. Pouliot, Ottawa, Can.

(Download PDF) Marketing Research An Applied Orientation 6th Edition Malhotra Solutions Manual Full Chapter

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

(Download PDF) Marketing Research An Applied Orientation 6th Edition Malhotra Solutions Manual Full Chapter

Uploaded by

Copyright:

Available Formats

Marketing Research An Applied

Orientation 6th Edition Malhotra

Marketing Research An Applied Orientation 6th Edition

Marketing Research An Applied Orientation 7th Edition

Marketing Research An Applied Orientation Global 6th

Marketing Research An Applied Orientation 7th Edition

Essentials of Marketing Research A Hands-On Orientation

Basic Marketing Research 4th Edition Malhotra Test Bank

Essentials of Marketing Research Global 1st Edition

Marketing Research Arab World Editions 1st Edition

CAUSAL RESEARCH DESIGN:

FIGURES AND TABLES

AUTHOR’S NOTES: CHAPTER FOCUS

Copyright © 2010 Pearson Education, Inc. publishing as Prentice Hall

● Via an example, explain the three necessary conditions to infer causality.

1. Concomitant variation: is the extent to which a cause, X, and an effect, Y, occur

Copyright © 2010 Pearson Education, Inc. publishing as Prentice Hall

1. Independent variable—variables or alternatives that are manipulated and whose

● Introduce the symbolic notation used in marketing research.

1. X = the exposure of a group to an independent variable or treatment or event,

The following conventions are associated with the symbols:

Copyright © 2010 Pearson Education, Inc. publishing as Prentice Hall

Start by defining validity, in an experimental setting, as the ability to draw appropriate

Copyright © 2010 Pearson Education, Inc. publishing as Prentice Hall

● Describe methods for controlling the effects of extraneous variables

1, Randomization—involves randomly assigning test units to experimental groups.

Copyright © 2010 Pearson Education, Inc. publishing as Prentice Hall

1. Preexperimental Designs. Do not apply randomization, thus, they can be

● Describe preexperimental designs and their shortcomings.

Copyright © 2010 Pearson Education, Inc. publishing as Prentice Hall

Examples of True Experimental Designs:

● Explain the analysis of quasiexperimental designs.

Mention that in a quasi-experimental design, the researcher can control when

● Explain the nature and uses of statistical designs.

Copyright © 2010 Pearson Education, Inc. publishing as Prentice Hall

● Discuss the limitations of experimentation.

Start by asserting that theoretically, experimentation is a very powerful way to uncover

1. Time: experiments can be time consuming; however, the experiments should be

Define test marketing as an application of a controlled experiment, done in a limited but

EXAMPLE: M&M/Mars has set up massive manufacturing facilities in Russia and

It is often necessary in experimentation to disguise the purpose of the research to produce

The Internet and Marketing Research

Different experimental treatments can be displayed at different Web sites. Respondents

MR: Fox News

A preexperimental design would not be appropriate as there are three experimental

DM: Fox News

Copyright © 2010 Pearson Education, Inc. publishing as Prentice Hall

The Marketing Research Decision

The Marketing Management Decision

Copyright © 2010 Pearson Education, Inc. publishing as Prentice Hall

Copyright © 2010 Pearson Education, Inc. publishing as Prentice Hall

Copyright © 2010 Pearson Education, Inc. publishing as Prentice Hall

1. (a) Independent Variable - The commercial

(b) Low income consumers exhibit low product use.

Internet and Computer Exercises

1. Computer controlled experiments are becoming increasingly popular in marketing

Copyright © 2010 Pearson Education, Inc. publishing as Prentice Hall

Copyright © 2010 Pearson Education, Inc. publishing as Prentice Hall

Copyright © 2010 Pearson Education, Inc. publishing as Prentice Hall

Q1. “Whereas one cannot prove a causal relationship by conducting an experiment,

Copyright © 2010 Pearson Education, Inc. publishing as Prentice Hall

Closely akin to side-slipping is the Christiania swing with the stick,

The Telemark swing is more difficult to master than the Christiania