You are on page 1of 8

PAPER – IV MANAGERIAL ECONOMICS

UNIT – I Consumer Preference

A Simple Method to Determine Consumer Preference

Introduction
Extension field trials often involve consumer preference. This may be the look of a turf grass; the feel of a
textile; the taste of a cooked, raw, or processed food product; or the smell of a product.
Statistical analysis of consumer preference often requires a trained consumer panel to show significant
results. Even then, simple statistical procedures, such as analysis of variance, can be inappropriate for this
type of data due to panelist variation: e.g., sensory preferences, personality differences, and variation in
the use of the rating scale. Use of a 1 to 10 preference scale often varies, even among trained panelists.
Some panelists use the lower range, some the higher, and some rate all choices somewhere around the
middle of the scale.
Thus, analysis of preference data often is complex, using techniques such as multiplicative mixed models
(Smith, 2003) or principle components analysis (M. McDaniel, personal communication, August 27,
2003). These advanced statistical methods make analysis more precise by factoring out much of the
panelist variation interfering with analysis of the data using a simple analysis of variance (M. McDaniel,
personal communication, August 27, 2003).
In Extension field trials, trained test panels are not available. Advanced statistical methods require help
from statisticians, often located some distance from the field site. A simple, practical consumer preference
technique is needed to evaluate field data.
Consumers at field tours, local Master Gardeners, farmers' market shoppers, 4-H members, parents and
leaders, and commodity producers are available to extension personnel, and willingly volunteer their
services to rate products. Using these consumers, statistically valid tests for preferences can be conducted
using the method described here.
Collection of Data
Prepare and present samples to be evaluated in an identical manner. Provide evaluation forms and pencils
for the consumers to record their preferences. Tables and chairs arranged around the central distribution
area can make the evaluation process comfortable for the consumers.
Collection Example
An example uses specialty potato cultivars sliced and boiled in an identical manner. Cultivars were
identified by number and placed on paper plates for sampling by consumers (shoppers at a local farmers'
market). Evaluation form instructions read, "On a scale from 1 to 10 (10 being the best, 1 being the worst),
rate the following potato cultivars. Please take a sip of water between samples." Paper cups and cold water
were provided.
Analysis of Data
This procedure uses the SAS 1999 statistical software for analysis. This is easily installed on an Extension
office computer.
Enter raw rating data into a spreadsheet such as Excel. Number each consumer (replication), and record
the rating for each product attribute (texture, flavor, and appearance in the potato example) for each
treatment (each cultivar in the potato example). This data must be saved as a text file to be read by the
SAS program.
Use a nonparametric statistical technique to analyze the mean ratings for each treatment. The rank of each
rating is computed. By ranking the 1 to 10 ratings of the evaluators, the variation due to differences in use
of the rating scale is minimized.
Next, employ a signed rank test to assess statistical differences between treatments. A chi-square test will
indicate the level of significance of the data. This will tell you if the mean ranks for each attribute of the
treatments are significantly different.
To perform mean comparisons on significantly different attributes, use the standard error of the mean
ranks for each attribute. The mean rank, plus or minus two standard errors, approximates a 95%
confidence interval. Therefore, any two means differing by more than two standard errors are implied to
be significantly different. You can then state which treatments are statistically significantly different. In
the potato example, after data analysis, such statements as the following can be made:
• "At the Twin Falls (Idaho) Farmers' Market, consumers preferred the texture of 'Caribe' and
'Huckleberry' potatoes over all other cultivars tested."
• "Taste test results indicate that 'Caribe,' 'German Butterball,' "Yukon Gold,' 'Viking Red,' and
'NorDonna' rank high"(Olsen, 2003).
Analysis Example
Using SAS, the following nonparametric procedure was applied to the specialty potato data. Where:
• Location is either 1 or 2 since the test was performed at two separate farmers' markets.
• Cultivar is the specialty potato type (these are the treatments)
• Texture is the mouth feel of the boiled sample
• Flavor is how the boiled sample tasted
• Appearance is how the boiled sample looked
• Rep is each individual consumer completing the entire evaluation
• A:\Potatotaste00.txt is the location and the name of the text data file
• The procedure NPAR1WAY calculates the mean ranks
The SAS program is as follows.
Data Pottaste2;
Infile'A:\Potatotaste00.txt' delimiter='09'x;
Input location rep cultivar texture flavor appearance;
Proc sort;
by location cultivar texture flavor appearance rep

Proc MEANS;
by location cultivar;

Proc NPAR1WAY WILCOXON;


by location;
Class cultivar;
OUTPUT OUT=DataT Wilcoxon;
VAR texture flavor appearance;

Proc rank out=rankdata data=pottaste2;


var texture flavor appearance;
rankst f a;
by location;

Proc sort data=rankdata;


by location cultivar;

Proc means mean stderr;


var t f a;
by location cultivar;

run;
The results of this SAS program provide, for each attribute at each location for each treatment:
1. The rating mean--the raw score averaged for each attribute
2. The rank mean--the rank scores averaged for each attribute
Also provided are:
1. The chi-square for the ranked means. This will tell you if there are significant differences between
the rank means.
2. The standard error for the rank means. If the chi-square shows significance, the standard error will
tell you which rank means are different from each other.
This consumer preference technique and statistical method allows Extension professionals in remote field
situations to measure sensory attributes of products using available consumer clientele and statistical
analysis possible on an office computer.
Acknowledgement
Thanks to William Price, Statistician, Statistical Programs, College of Agriculture and Life Sciences,
University of Idaho, Moscow, Idaho for help with SAS programming and interpretation.
---------------------------------------------------------------------------------------------------------------------
Research in advertising has become a crucial element in all aspects of planning, assessment and
evaluation. One of the main objectives of advertising research is to understand the correlation between
advertising and its effects on the consumer.
The purpose of this study was to analyze the change in brand preferences in three brands of anti-aging
foundations before and after exposure to advertisements. Specifically, Lancome Renergie Lift Makeup,
Shiseido The Makeup and Clinique Repairwear were examined for this study.
Methodology of the study, results and analysis will be discussed in the following pages. The actual
questionnaire as well as frequency outputs are also included.

Executive Summary
The purpose of this study was to analyze the change in brand preferences in three brands of anti-aging foundations before and after
exposure to advertisements. Specifically, Lancome Renergie Lift Makeup, Shiseido The Makeup and Clinique Repairwear were
examined for this study.
Due to time and budget constraints, this study used a non-random (convenience) sampling. People who were considered as samples
were asked to complete the survey online. An email was sent to the "target audience" to request participation for this study.Out of
70 questionnaires returned, 60 were used for this study. The data was then transferred into SPSS for analysis.
Overall, Lancome is the brand liked the most followed by Shiseido and Clinique. However, many of the results are non-consistent
and are not statistically significant enough. One of the reasons may be because of the small sample size of 60 people. Moreover,
these people were selected as convenience samples rather than random samples. Also, no control group was included in the study
and randomization was not used in the questionnaire to lessen order biases.
Although having some limitations and not indicating large differences between each brand, it still provides some interesting
information and can serve as a basis for future analysis and discussion.
Structure
There are four main sections in the survey.
The first section asks questions related to the study and allows the respondent to grow familiar with the questionnaire.
The following section measures favorability change after ad exposure on pre-post constant sum scale. The respondents are asked to
indicate favorability for all three anti-aging foundation brands by dividing 10 points according to their liking toward each brand.
Then, three anti-aging foundation print ads were presented. The respondents were asked again to indicate brand preference for each
brand in the same manner as described above.
The third section determines respondents' attitudes toward the three brands and advertisements. Ten Likert items were used to assess
attributes pertaining to each individual anti-aging foundation brand. The Likert items gave the respondents an option to categorize
how they felt about each brand. Each Likert item was provided a value from 1-5, labled from strongly agree to strongly disagree.
Respondents' attitudes toward each ad were also measured in this section.
The respondents' demographic information was collected in the final section. The questions included gender, age, educational level,
income, and the frequency they purchase foundations. The purpose of this section is to explain if any demographic information is
related to how the respondents react to the ad. All the responses were provided anonymously and were assured to the respondent at
the beginning of the questionnaire in order to protect the respondents' privacy.
Top

Design
This research is based on a survey designed specifically to collect initial and post advertising exposure brand opinions. By
subtracting pre-exposure purchase intention from post-exposure purchase intention, the constant sum scale is intended to measure
the effects of advertising. In this survey, there was no control group. Every ad was seen in the same order by each participant.
Top

Sampling
Due to time and budget constraints, this study used a non-random (convenience) sampling. People who were considered as samples
were asked to complete the survey online. An email was sent to the "target audience" to request participation for this study. It was
decided that a sample size of at least 60 would be decent enough for statistical analysis of this study. This sample size was
considered to allow enough representation, so that if statistical significance is found, projection can be made in 85 or more samples
of the 100 samples within the same population as these 60 were drawn that we would find results of the same magnitude. Out of 70
questionnaires returned, 60 were used for this study.
Top
Data Collection
Respondents were asked to complete the questionnaire electronically. The data would be then sent to a database where it was
collected. The program Cold Fusion was used to submit the data once the survey was completed. Microsoft Access was used to
transfer the survey results to an electronic database. Finally, SPSS (Statistical Package for the Social Sciences), was used to
calculate statistics and recode data.

Basic Statistics
In 85 or more samples from every 100 people drawn from the same population of th is sample of the 60 people,
it is expected to find the same mean scores for Brand A and Brand B as found in this sample (0.12 < 0.15). The
same can be expected for the pair for Brand A and Brand C (0.02 < 0.15) as well. However, in 85 or more
samples from every 100 people drawn from the same population of the 60 people, we would not expect to find
the same mean scores for Brand B and Brand C as found in this sample (0.16 > 0.15).
While brand preference toward Clinique between up-movers and down-movers were almost the same, ad
preference were significantly higher in those who showed increased favorability. Therefore, we could conclude
that respondents liked the ad for Clinique but that did not necessarily lead to brand favorability.
In 85 or more samples from every 100 people drawn from the same population of th is sample of the 6 0 people,
it is expected to find the same mean Ad Index S cores for up-movers and down-movers as found in this sample
(0. 01 < 0.15). However, we cannot expect that for Brand Index Scores for these groups.
From the chi-square significance test, we can conclude that the ad for Clinique should be improved since the
salience of dislike in Clinique among those who had negative attitudes toward the brand before are more likely
to grow stronger, while it did not have any effect on those with above-median brand preferences and improved
attitudes toward the brand.
The correlation between Lancome and Clinique is very weak ( correlation coefficient = 0.02, significance =
0.44). Therefore, we cannot say that favorability toward Lancome and Clinique have any effect on each other.
Lancome and Clinique showed decreased favorability by about 40%. Thus, Shiseido's advertisement seems to
have had more positive influence on the viewers toward the product than the others.
Shiseido showed more women not changing their attitudes toward the product and less negative outcomes.
Therefore, we can conclude that the ad for Shiseido did not necessarily contribute to more positive attitudes of
female respondents, but had the most influence preventing favorability diminish.
Regression Analysis
The regression analysis showed that there is very little relationship between change in brand favorability and ad
favorability. Clinique had the closest relationship between all factors in question, meaning that these factors did
relate to how they favored the advertisement shown.
The multiple regression analysis for Lancome shows a low coefficient of multiple determinants (R Square) of
2.6%, indicating that there is very little relationship between how respondents rated the Lancome brand on the
ten Likert items and their favorability of the Lancome ad derived from their score changes before and after
exposure to the ads. The F-ration (0.13) indicates that in 85 or more samples of every 100 samples drawn from
the same population as this sample of 60 people, we would not expect to find the same multiple regression
coefficient for Lancome.
Shiseido shows an even lower coefficient of multiple determinants (R Square) than Lancome with 1.1%,
indicating that there is very little relationship between brand favorability and ad favorability. The F-ration
(0.05) indicates that in 85 or more samples of every 100 samples drawn from the same population as this
sample, we would not expect to find the same multiple regression coefficient for Shiseido. The only attribute
that respondents thought important of Shiseido was brand credibility. Unstandardized coefficients (b) suggest
that the more respondents trust Shiseido, the more they favored the ad.
Clinique shows a coefficient of multiple determinants (R Square) of 24.4%, showing some relationship between
brand and ad favorability. in 85 or more samples of every 100 samples drawn from the same population as this
sample, we would expect to find the same multiple regression coefficient for Clinique.

Discriminant Analysis
From the standardized discriminant coefficients, respondents considered the attributes that “Clinique is a good
anti-aging foundation” and “would prefer Clinique over other brands” important. The unstandardized
discriminant coefficients suggest the relationship between the brand attributes and ad favorability as follows:
• The more the respondents considered Clinique a good anti-aging foundation, the more they liked the ad.
• The more the respondents preferred Clinique over other brands, the less they liked the ad.
The Chi-square value of 8.21 indicates that there is little relationship between those with changed favorabilities
and brand attributes. In 85 or more samples of every 100 samples drawn from the same population as this
sample of 60 people, we would not expect to find the relationship and Chi-square score for Clinique (0.30 ≥
0.15).
The group centroid for those with increased favorability was -0.6 and that for those with decreased favorability
was 0.4. However, we cannot project the same results of this sample to the population since the Wilks' Lambda
score (0.78) is not statistically significant. In other words, in 85 or more samples of every 100 samples drawn
from the same population as this sample of 60 people, we would not expect to find the same group centroids for
Clinique (0.30≥0.15).
The outcome of this study was not successful which is made clear by the low percentage of respondents that
were accurately classified. This is a mere 60 percent of the respondents which are not much better than the 50
percent that could be achieved by random selection. The scores show that the percentage of persons studied was
not significant enough to make the data collected successful.
ANOVA/MANOVA
The sample shows obvious differences in favorability toward the brand by age, indicating that older women
were more skeptical that the product would make them look younger. The difference of preference by age was
more prominent especially for those who had changed favorability toward the brand after exposure to the ad.
We can conclude that in 85 or more samples of every 100 samples drawn from the same population as this
sample, we would expect to find the same mean scores by age. However, the results for change scores and their
relationship to age is not statistically significant; thus, in 85 or more samples of every 100 samples drawn from
the same population as this sample, we would not expect to find the same means for neither change scores nor
their relationship with age.
The relationship between the change in brand preference and age was statistically significant. Therefore, in 85
or more samples of every 100 samples drawn from the same population as this sample, we would expect to find
the same mean in change scores by age. However, we cannot project the same results to the population for each
independent variables; change of favorability and age.
When factoring in both age and the movement upwards and downwards in favor of Clinique, there is a positive
interaction between the two making it an important factor. This relays the idea that when considering whether
or not Clinique is a good brand, respondents' age played a part in the way they favored the ad and moved up or
down in this favor.

Factor Analysis
The Factor Analysis revealed those Likert items that were evaluative in nature and related to the most
unambiguous Likert item of each group: the “good” item. These items were then taken to compute an attitude
score for each respective test brand. These attitude scores did reveal that in this sample, Lancome is the brand
liked the most followed by Shiseido and Clinique. Lancome is favored more than the other brands in this study
and in the population as is the advertising for this brand.
Based on the results from a paired t-test to observe the significance of the difference between the three mean
attitude scores, we can conclude that that in 85 or more samples of every 100 samples drawn from the same
population as this sample, we would expect to find the same difference between mean scores for pairs
Lancome-Shiseido and Lancome-Clinique . However, in 85 or more samples of every 100 samples drawn from
the same population as this sample, we would not expect to find the same mean score difference s for pair
Shiseido-Clinique.

Top