Complete Statistics Homework (PETT)

1. Nominal-numbers serve as descriptors (e.g., SSN, numbers assigned to marathon runners, firstnames, colors of jerseys)
How to describe statistically:
Percentages, frequencies
Mode
(not average-mean)
Transformations: (what changes can be made to the data without losing its qualities?) one-to-one
transformations (renaming)
2. Ordinal-numbers denote relative ranking (e.g., sales rankings, occupation level in a hierarchy,
scale-strongly agree to strongly disagree)
Differences in numbers have no meaning other than relative position
How to describe statistically:
Anything from nominal scale
Median, quartiles, percentiles
(still no average)
Some rank-order statistics
Transformations: rename and keep order
3. Interval-distances are equal (e.g., temperature in F, attitude scales)
Distance between 1 to 2 is the same as 4 to 5
How to describe statistically:
Anything from nominal and ordinal scale
Averages (means), but consider problem with average answer on a scale
(not ratios-consider a ratio of temperatures)
Most statistics
Transformations: any linear transformation (y=a + bx)
4. Ratio-includes logical zero (e.g., temperature in Kelvin, sales in $, Age)
Note: 1 to 2 is the same as 4 to 5, but also 6 is 3 times 2
How to describe statistically: all statistics permitted
Transformations: exponential transformations permitted (y=b*)
W5 Scale
Hide Assignment Information
Instructions
We’ve seen examples of a number of different types of
scales in class and discussed the measurement
process. Come up with a 10 (or more) item scale
intended to measure a psychological variable of your
choice. You might use a Likert scale or a semantic
differential scale, but try to be creative. Consider
questions that might relate to various elements of your
variable.
Due Date
310
JOURNAL OF CONSUMER RESEARCH
TABLE 3
EXPLORATORY FACTOR ANAYLSIS OF MATERIALISM ITEMS
Factor
Item
1
2
3
.70
.69
-.68
.58
-56
Reliability
Coefficient alpha was calculated separately for the
items comprising the three factors and for the 18 items
as a single scale. The seven centrality items produced
alpha coefficients between .71 and 75 in the latter three
surveys. For the six-item success subscale alpha ranged
from 74 to.78, and for the five happiness items, alpha
was between .73 and .83. When combined into a single
scale, alpha for the 18 items varied between .80 to.88.
Test-retest reliability (three-week interval) was cal-
culated on data from a sample of 58 students at an urban
university. The reliability correlations were 82,.86, and
.82 for the centrality, happiness, and success subscales,
respectively, and .87 for the combined scale.
Social Desirability
While materialism may be more socially acceptable
today than in some past eras, because of recent media
attention to the negative aspects of materialism we con-
sidered it important to test the measure for susceptibility
to social desirability bias. Social desirability was mea-
sured in the first consumer data collection with 10 items
from the Marlowe-Crowne scale (Crowne and Marlowe
1960). These items were chosen from the larger scale
because they have been shown to possess greater sen-
sitivity than other items and are appropriately keyed
for current standards of desirable behavior (Ballard,
Crino, and Rubenfeld 1988). Correlations with the so-
cial desirability measure were -12,-.03, and -.06 for
the centrality, happiness, and success subscales, re-
spectively, and -.09 for the combined scale. The low
correlations suggest that social desirability bias was not
a problem for these measures.
-.43
-.78
Success:
I admire people who own expensive homes,
cars, and clothes.
Some of the most important achievements
in ife include acquiring material
possessions.
I don’t place much emphasis on the amount
of material objects people own as a sign
of success.
The things I own say a lot about how well
I’m doing in life.
I like to own things that impress people.
I don’t pay much attention to the material
objects other people own
Centrality:
I usually buy only the things I need.
I try to keep my life simple, as far as
possessions are concerned.”
The things I own aren’t all that important to
me.
I enjoy spending money on things that
aren’t practical
Buying things gives me a lot of pleasure.
I like a lot of luxury in my life.
I put less emphasis on material things than
most people I know.”
Happiness:
I have all the things I really need to enjoy
life.”
My life would be better if I owned certain
things I don’t have.
I wouldn’t be any happier if I owned nicer
things.
I’d be happier if I could afford to buy more
things.
It sometimes bothers me quite a bit that I
can’t afford to buy all the things I’d like.
-.62
-.60
.60
.54
.52
-.49
-.80
.65
-.58
.58
.37
.55
Descriptive Statistics
The distributions for the overall materialism measure
and its three components were approximately normal
NOTE.-Only loadings greater than.35 are shown. An asterisk indicates reverse
scored items. A five-point Likert scale response format was used.
was significant in tests of all three data sets, indicating
that the three-factor model is superior in fitting the
data.
While confirmatory factor analysis served to explicate
the three hypothesized manifestations of the underlying
construct, the three factors were summed for purposes
of validation. This approach was followed because
analyses showed that the three factors normally act in
concert with respect to external variables. Carver (1989)
has noted that, in these situations, using the summed
index instead of subscales is appropriate and advanta-
geous in terms of parsimony and clarity of communi-
construct and notes that, in doing so, researchers have assumed either
that the underlying construct is assessed indirectly by measures of its
various manifestations (the latent variable approach) or that the con-
struct is something more than the sum of its component parts (the
synergistic approach). For purposes of the materialism measure, we
make the former assumption that the three subscales are manifes-
tations of materialism and the latent variable approach is thus ap-
propriate. Carver describes the advantages of summing the compo-
nents in such a case and discusses the patterns of results that justify
summed vs. separate component analysis. In the research reported
here, all hypotheses were investigated using both the summed scale
and the component scales. On average, the summed multidimensional
index relates to the diverse constructs in the hypothesis tests better
than does any one component dimension. In such cases, the higher
level information (i.e., the consistent relation of the multifaceted
(summed) construct to many outcome variables) is more important
than the lower level (individual subscale) information,” and the uso
of the summed construct measure instead of individual subscales is
preferred (Carver 1989, p. 580). For this reason, summed scale results
are presented here. Results of hypothesis tests at the subscale level
are available from the authors.
cation.2
*Carver (1989) has discussed at length the appropriateness of com-
bining component scores into a summed measure representing a latent
Price Consciousness #315
to
ey
wrenc\a=
Dickerson, Mary D. and James W. Gentry (1983), “Characteristics of Adopters and Non-Adopters of Home
Computers,” UCR, 10 (Sept.), 225-235
Darthu. Naveen and Adriana Garcia (1999), “The Internet Shopper, “JAR, 39 (May/June), 52-58,
ponthu, Naveen and David Gilliland (1996), “The Infomercial Shopper,” JAR, 36 (March/April), 69-76.
Tieslop, Louise A., Lori Moran, and Amy Cousineau (1981), “Consciousness in Energy Conservation Beha-
vior: An Exploratory Study,” JAMS, 8 (Dec.), 299 305.
Korgaonkar
, Pradeep K. (1984), “Consumer Shopping Orientations, Non-Store Retailers, and Consumers’
Patronage Intentions: A Multivariate Investigation,” JAMS, 12 (Winter), 11-22
Mittal, Banwari (1994). “An Integrated Framework for Relating Diverse Consumer Characteristics to Super-
market Coupon Redemption,” IMR, 31 (November), 533-544.
Schhaars, Steven P. and Leon G. Schiffman (1984), “An Application of a Segmetation Design Based on the
Hybrid of Canonical Correlation and Simple Cross-Tabulation,” JAMS, 12 (Fall), 177-189.
Tat, Peter K. and David Bejou (1994), “Examining Black Consumer Motives For Coupon Usage,” JAR, 34
(March/April), 29-35.
Wells, William D. and Douglas Tigert (1971), “Activities, Interests, and Opinions, “JAR, 11 (Aug.), 27-35.
lo
ly
ed
SCALE ITEMS:
36)
nd
L)
1. Ishop a lot for “specials.”
2. I find myself checking the prices in the grocery store even for small items
ere
3. I usually watch the advertisements for announcements of sales.
are
4. A person can save a lot of money by shopping around for bargains.
sts
5. I check the prices even for inexpensive items,
he
fy
#15
6. I pay attention to sales and specials.
7. Clothing, furniture, appliances, … whatever I buy, I shop around to get the best prices.
on
8. I usually purchase the cheapest item.
De
9. I usually purchase items on sale only.
Barak and Stern (1985/1986): 1, 2, 3, 4 6-point
Dickerson and Gentry (1983): 1, 2, 3, 46-point
Donthu and Garcia (1999): 2*, 4,8,9 5-point
Donthu and Gilliland (1996):2*, 4,8,9 5-point
Mittal (1994): 1,2,75-point
Tat and Bejou (1994): 1, 5, 6 5-point
Asterisks indicate that a scale item used in a study was similar to one shown but varied somewhat in phras-
In
us. Analytics/Data
тәлә1/eәлу
Spring Semest
nd analysts predict and inform business decisions based on past and present busin
pal is to help you develop business data capability that can be applied to all business contexts.
our business analytics minor, students will move beyond reviewing statistics to understandig
2019-2020
Minor in Business
Course
Attitude Toward the Product/Brand (Semantic Differential) #59
SCALE ITEMS: 1
1. good / bad
2. like / dislike
3. pleasant/unpleasant
4. high quality / poor quality
5. agreeable / disagreeable
3
6. satisfactory / dissatisfactory
7. wise / foolish
2
1
8. beneficial / harmful
f
9. favorable / unfavorable
f
10. distinctive / common
11. likable / dislikable
>
12. positive / negative
1,
13. buy / would not buy
),
14. attractive / unattractive
39
”
15. enjoyable/unenjoyable
16. useful / useless
17. desirable / undesirable
i-
18. nice / awful
-C
19. important/ unimportant
od
20. harmless / harmful
21. valuable / worthless
22. appetizing/unappetizing
23. unique / not unique
Marketing Scales Handbook
83