Beruflich Dokumente
Kultur Dokumente
Pedro S. Coelho
Susana P. Esteves
New University of Lisbon
Introduction
In marketing research, and particularly in the framework of customer
satisfaction measurement, we often try to measure attitudes and human
perceptions. This task raises a number of questions regarding
questionnaire design and particularly about the appropriate response
scales to use. Among the usual decisions is the choice between a verbal or
numerical scale, along with the number of response alternatives.
314
Coelho.qxp 26/04/2007 14:56 Page 315
In spite of these well-known ideas very little work has been done in
trying to validate them. Particularly in the context of customer satisfaction
measurement many authors have proposed the ten-point numerical scale
(anchored in the extremes). This is the usual approach in the European
Customer Satisfaction Index (ECSI) (ECSI 1998; Ball et al. 2004) and in
the framework of the American Customer Satisfaction Index (ACSI)
(Fornell et al. 1996, 1998; Johnson et al. 2001). Nevertheless, some
practitioners have criticised this scale, arguing that respondents have
difficulty discriminating answers using more than five points (particularly
in a telephone survey) and that an odd number of points may be preferable
in order to account for neutrality. According to these arguments a standard
five-point scale would be a preferable choice over a ten-point scale.
This paper aims to compare a five-point and a ten-point numerical scale
in the context of customer satisfaction measurement. The analysis includes
the evaluation of non-response rates, response distribution, the ability to
discriminate between attributes being measured, the ability to model
customer satisfaction, as well as convergent, discriminant and nomological
validity of constructs used in the ECSI model. Moreover, we investigate the
effects of social-demographic characteristics on the ability of respondents
to use each scale. The social-demographic analysis includes both the effects
on response profile and the probability of non-response.
The structure of the paper is organised as follows. The Introduction
presents the problem and the goals of the paper. In the next section we
introduce the use of scales in attitude measurement, and approach the
problem of choosing the number of response alternatives, referring to
previous work in this context. The organisation of the empirical study is
shown in the subsequent section. This presentation includes the ECSI
model as well as the study design. The fourth section presents and analyses
the main results obtained in the study. The final section discusses the main
findings.
315
Coelho.qxp 26/04/2007 14:56 Page 316
316
Coelho.qxp 26/04/2007 14:56 Page 317
they have not found any increase in reliability from using a number of
categories above five, and detected a significant decrease in reliability
when using more than seven points. Cicchetti et al. (1985), using a Monte
Carlo simulation to access the extent to which the interrater reliability is
affected by the number of scale points, concluded that, although reliability
increases up to seven scale points, no substantial increases occur beyond
that point. Nevertheless, conclusions are necessarily limited to the
simulation parameters. Haley and Case (1979) have tested 13 attitude
scales for agreement, discrimination among brands and response pattern,
but their study did not offer much insight into the choice of the number of
response alternatives within a same scale type. Givon and Shapira (1984)
use a stochastic model to investigate the conjoint effect of the number of
items and number of response alternatives on the sampling error of a
composite scale estimator. They conclude that sampling error may be
reduced, increasing the number of response alternatives up to five, seven
or nine, depending on the number of items used. A review of the work
done up until the beginning of the 1980s, regarding the optimal number of
response alternatives, can be found in Cox (1980). The author concludes
that there is no single number of response alternatives for a scale that is
appropriate under all circumstances. Also, he concludes that no formula
can be given to indicate what this number should be, even in a particular
set of circumstances. Nevertheless, he establishes that scales with two or
three response alternatives are generally inadequate and that the marginal
return from using more than nine response alternatives is minimal.
Consequently, he proposes that the optimal number of response
alternatives is normally situated between five and nine. One exception is
Alwin’s (1997) work, which compares seven- and eleven-category rating
scales. His conclusions favour the eleven-point scale in terms of
measurement precision, and reject the idea that the eleven-point scale is
more vulnerable to measurement errors.
317
Coelho.qxp 26/04/2007 14:56 Page 318
(ECSI 1998; Cassel & Eklof 2001; Vilares & Coelho 2004). It has been
validated across a number of European countries and many industries,
such as insurance, mobile phones, fixed phones, carbonated soft drinks,
public transportation, retail banking, cable TV, supermarkets, postal
services, food products and public service.
The ECSI model is composed of two sub-models: the structural model
and the measurement model. The structural model defines the
relationships between the latent variables and is represented in Figure 1.
Customer satisfaction is the central variable of this model, having as
antecedents the image of the company, customer expectations, perceived
quality of products and services, and perceived value (where the relation
between quality and price is measured). As consequences of customer
satisfaction there are two variables: complaints and loyalty.
The measurement model includes the relations between the latent or
non-observable variables and the observed indicators that correspond to
survey questions (Table 1). Within this model we assume that the
relationships between the latent variables and the observed indicators are
all of the reflective nature (i.e. the indicators are assumed to be reflex of
the latent variables).
Image
Loyalty
Satisfaction
(ECSI)
Expectations
Perceived
value
Perceived
Complaints
quality
318
Coelho.qxp 26/04/2007 14:56 Page 319
PLS (Partial Least Squares) was used to estimate this model using two
data sets obtained as explained in the next section. The methodology PLS
applied to ECSI is presented in detail by several authors (e.g. ECSI 1998;
Cassel et al. 2000).
Data
Data came from a survey corresponding to the 2004 wave of ECSI-
Portugal (the Portuguese Customer Satisfaction Index). The selection of
respondents follows the criteria defined in ECSI (1998). Data collection
took place in November and December 2004, through telephone
interviews supported by a CATI system. The same questionnaire was
administered to both samples, but for one sample we used a five-point
319
Coelho.qxp 26/04/2007 14:56 Page 320
scale and for the other a ten-point scale (anchored in the extremes).1 The
two scales are both numerical, with the same labels on the extreme points.
Therefore, the only difference between them is the number of response
alternatives. The questionnaire is the standard questionnaire used in ECSI-
Portugal for the mobile telecommunications industry. The questionnaire
includes a set of questions regarding the seven constructs of a structural
satisfaction model (image, expectations, perceived quality, perceived value,
satisfaction, complaints, and loyalty), plus a set of socio-demographic
questions. The sample size was 252 for the five-point scale and 253 for the
ten-point scale. Both data sets were collected among customers of the same
mobile telecommunications operator. The sampling design includes a
random selection of households using random-digit dialling. In each
household one resident is selected randomly and qualified as a member of
the target population.
Results
Descriptive analysis
Table 2 shows the frequency of non-response and the frequency of
response on the middle points of each scale. Results are shown by
indicator and organised in seven groups corresponding to the seven latent
variables in the satisfaction model. From the results presented in Table 2 it
can be seen that, in general, the five-point scale has a higher proportion of
non-responses when compared to the ten-point scale. Among the 25
indicators considered, only four show higher non-response rates for the
ten-point scale.
When we formally test the difference between the proportions of non-
response measured with the two scales, using the hypotheses
1 The labelling varies with the specific attributes but is generally stated as ‘very low’ to ‘very high’.
320
Coelho.qxp 26/04/2007 14:56 Page 321
Table 2 Non-response rates and proportion of responses in the middle points of the scale
% of middle points
NR (%) % of 3 % of 5 and 6
Latent variable 1 to 5 1 to 10 Difference 1 to 5 1 to 10 Difference
Image
Q4A 4.0 0.8 3.2* 20.2 21.1 –0.9
Q4B 2.8 1.2 1.6 7.8 10.8 –3.0
Q4C 4.8 2.4 2.4 27.1 21.9 5.2
Q4D 4.4 2.4 2.0 29.0 28.3 0.7
Q4E 4.0 1.2 2.8* 16.9 15.6 1.3
Expectations
Q5A 6.0 4.3 1.7 27.0 24.4 2.6
Q5B 6.7 7.1 –0.4 35.7 25.5 10.2*
Q5C 6.3 6.7 –0.4 40.3 25.8 14.5*
Perceived quality
Q6 0.4 0.0 0.4 19.9 18.2 1.7
Q7A 1.2 0.0 1.2 25.7 16.6 9.1*
Q7B 8.3 4.7 3.6 20.3 13.3 7.0*
Q7C 13.1 10.3 2.8 20.5 17.2 3.3
Q7D 12.7 7.5 5.2 28.6 17.9 10.7*
Q7E 7.1 4.0 3.1 25.2 21.4 3.8
Q7F 6.0 3.2 2.8 26.6 17.1 9.5*
Q7G 0.8 0.4 0.4 32.8 21.0 11.8*
Perceived value
Q10 2.0 1.6 0.4 42.1 44.2 –2.1
Q11 2.8 1.2 1.6 44.1 41.6 2.5
Satisfaction
Q3 0.4 0.8 –0.4 25.5 25.1 0.4
Q9 2.4 2.4 0.0 20.2 27.5 –7.3
Q18 4.4 4.0 0.4 7.8 21.0 –13.2
Complaints
Q15 0.0 0.0 0.0 34.6 12.5 22.1*
Q16 11.1 11.4 –0.3 31.8 27.6 4.2
Loyalty
Q12 3.2 2.0 1.2 10.7 18.1 –7.4
Q17 3.2 2.8 0.4 17.2 15.0 2.2
* Significant at 5% level
321
Coelho.qxp 26/04/2007 14:56 Page 322
If the response effort were too high using the ten-point scale we would
expect to find a higher frequency of non-response in the group using this
scale. Results do not confirm this hypothesis, and we may conclude that
the use of a five-point or ten-point scale does not tend to affect
significantly the non-response rate.
The concentration of response in the middle points of the scale can also
be seen in Table 2. This table exhibits the proportion of response in
category 3 for the five-point scale and the proportion of response in
categories 5 and 6 for the ten-point scale. It can be observed that in general
the concentration of response in the middle points is higher for the five-
point scale, when compared to the ten-point one. In fact, only six
indicators (among 25) show a higher concentration of response in middle
points for the ten-point scale.
When we formally test the difference between the proportions of
responses in middle points with the two scales, using the hypotheses
322
Coelho.qxp 26/04/2007 14:56 Page 323
Table 3 Means by indicator using the original and the transformed scale
1 to 5 1 to 10
Indicator Mean Transformed mean Mean Transformed mean Difference
Image
Q4A 4.0 0.76 7.7 0.75 0.01
Q4B 4.4 0.84 8.3 0.82 0.02
Q4C 3.9 0.72 7.6 0.73 –0.01
Q4D 3.7 0.68 7.2 0.69 –0.01
Q4E 4.1 0.77 7.9 0.77 0.00
Expectations
Q5A 3.8 0.70 7.4 0.71 –0.01
Q5B 3.7 0.68 7.3 0.70 –0.02
Q5C 3.6 0.66 6.9 0.65 0.01
Perceived quality
Q6 4.0 0.75 7.8 0.76 –0.01
Q7A 3.9 0.72 7.6 0.74 –0.02
Q7B 4.1 0.77 7.8 0.76 0.01
Q7C 4.0 0.75 7.7 0.74 0.01
Q7D 3.8 0.70 7.4 0.71 –0.01
Q7E 3.9 0.72 7.4 0.71 0.01
Q7F 3.8 0.71 7.5 0.72 –0.01
Q7G 3.7 0.66 7.2 0.69 –0.03
Perceived value
Q10 2.9 0.47 5.4 0.49 –0.02
Q11 3.4 0.60 6.4 0.60 0.00
Satisfaction
Q3 3.9 0.71 7.5 0.72 –0.01
Q9 3.8 0.69 7.3 0.70 –0.01
Q18 3.6 0.65 7.2 0.69 –0.04
Complaints
Q15 2.7 0.43 5.6 0.51 –0.08
Q16 3.7 0.67 7.0 0.67 0.00
Loyalty
Q12 4.2 0.79 7.7 0.75 0.04
Q17 4.1 0.77 7.7 0.75 0.02
Global average 3.8 0.70 7.3 0.70 0.00
It can be seen that for the transformed variables the global average is
identical both for the five-point and ten-point scales: 0.70. Also, when
analysing individual indicators, both means tend to show similar values
(the differences are always smaller than 0.08).
323
Coelho.qxp 26/04/2007 14:56 Page 324
where mi,5–p is the mean for variable i when using the five-point scale and
mi,10–p has the same meaning when using the ten-point scale, we never
reject the null hypothesis. Therefore we can not conclude that these means
are different in the population. Once again this result tends to confirm that
both scales produce equivalent mean scores and validate the acceptability
of the ten-point scale. In fact, if the efforts demanded of respondents were
too high using the ten-point scale we would expect to find different mean
scores for the two scales.
324
Coelho.qxp 26/04/2007 14:56 Page 325
Results for the analysis of variance are given in Tables 5 and 6. Table 5
shows the F tests for the significance of the regression and for each
individual variable (using Type III sum of squares). The null hypothesis
that all model coefficients are zero is rejected, showing the relevance of the
model. From the tested factors, only sex and education level are significant
at any reasonable significance level. These are important results that tend
to show that the scale used (ten-point or five-point) does not influence the
mean rating for the dependent variable. Also, although the education level
Table 5 F tests
325
Coelho.qxp 26/04/2007 14:56 Page 326
is a significant factor, there is no interaction between the scale used and the
education level. The conclusion is that people with different educations do
not tend to use the two scales differently.
Table 6 shows coefficient estimates for the significant parameters. Please
remember that only sex and education level were considered significant.
Results confirm the well-known notion in customer satisfaction studies
that females tend to show higher ratings than males, and also that mean
scores tend to decrease with the increase of education level.
With a logistic regression we intend to offer a complementary insight to
the question regarding the hypothetical influence of socio-demographic
variables on the rating profile. With the analysis of variance we have been
concerned with the response pattern to question Q3 (overall satisfaction).
Nevertheless, it is also interesting to understand whether the scale used
and socio-demographic characteristics influence the probability of non-
response. This is particularly important since, despite concluding that the
scale does not influence the response pattern (for respondents), it may
influence the probability of response and therefore the quality of collected
data. The dependent variable Q7c (quality of services provided) was
chosen for being one with the higher non-response rate among variables in
the questionnaire. Results for the logistic regression are given in Tables 7
and 8.
Table 7 shows a chi-square test for the model significance and Wald
statistics2 for individual independent variables. The null hypothesis that all
model coefficients are zero is rejected, showing the relevance of the model.
For the independent variables only age group and education level are
significant at any reasonable significance level. Once again, these results
2 The Wald statistic is used in this context to test the significance of model coefficients. Under the null hypothesis
(corresponding to the nullity of each coefficient) the statistic follows a chi-square distribution with degrees of
freedom equal to the number of restrictions to be tested.
326
Coelho.qxp 26/04/2007 14:56 Page 327
tend to show that the scale used (ten-point or five-point) does not influence
the probability of non-response for the dependent variable. Also, although
the education level is a significant factor, there is no interaction between
the scale used and the education level. The conclusion is that within an
education level, people using different scales do not tend to show different
response rates.
Coefficient estimates for the significant parameters are shown in
Table 8. Note that only age group and education level were considered
significant. Also note that the probability modelled in our analysis is with
regard to the response event. Results show that the response probability
tends to decrease with the increase of age. Also it can be seen that the
response probability tends to be higher for people with higher education
levels.
327
Coelho.qxp 26/04/2007 14:56 Page 328
Validity assessment
Figures 2 and 3 show the estimated path coefficients and t values (between
parentheses) for the structural models estimated with five-point and ten-
point scales, respectively. Generally, the hypothesised links tend to be
significant at 5% significance level. For the model estimated with the five-
point scale the only exceptions are the Image–Loyalty, Expectations–
Satisfaction and the Complaints–Loyalty paths that are not significant at
10% significance level. In particular, the estimate for the hypothesised
path between Complaints and Loyalty is negative (contradicting the
theory) and shows an extremely low t ratio. When using the ten-point scale
only the Image–Loyalty, Expectations–Satisfaction paths are not
significant at 5% significance level. Nevertheless, the Expectations–
Satisfaction path is significant at 10% significance level and the
Image–Loyalty path at 10.5% significance level. Globally the ten-
point scale showed a greater ability to capture the significance of
theoretically supported links, resulting in a higher nomological validity for
this scale.
328
Coelho.qxp 26/04/2007 14:56 Page 329
0.10
(1.31**)
Image
Loyalty
0.25
(3.87)
0.65 0.46
(17.22) (5.73)
0.11
(1.46**)
Satisfaction
0.31 0.25 (ECSI) –0.03
Expectations (3.99) (4.44) (0.34)**
Perceived
value
0.29 0.58
0.66 (3.21) (13.42)
(16.78)
0.30
Perceived (3.93)
Complaints
quality
* Non-significant at 5% significance level
** Non-significant at 10% significance level
Figure 2 Model parameter estimate and t values for the five-point scale
0.14
(1.62**)
Image
Loyalty
0.34
(4.83)
0.64 0.48
(15.43) (4.89)
0.14
(1.79*)
Satisfaction
0.19 0.34 (ECSI) 0.22
Expectations (2.22) (4.56) (3.22)
Perceived
value
0.38 0.55
0.68 (4.76) (9.77)
(22.42)
0.17
Perceived (2.31)
Complaints
quality
* Non-significant at 5% significance level
** Non-significant at 10% significance level
Figure 3 Model parameter estimate and t values for the ten-point scale
329
Coelho.qxp 26/04/2007 14:56 Page 330
Latent variable 1 to 5 1 to 10
Satisfaction 0.59 0.66
Loyalty 0.27 0.54
3 The determination coefficient reveals the proportion of variation in each dependent variable (satisfaction and
330
Coelho.qxp 26/04/2007 14:56 Page 331
Communality Difference
Latent variable 1 to 5 1 to 10 10 to 5 points Number of indicators
Image 0.51 0.60 0.09 5
Expectations 0.72 0.67 –0.04 3
Perceived quality 0.48 0.52 0.04 8
Perceived value 0.74 0.74 0.00 2
Satisfaction 0.68 0.70 0.02 3
Complaints – – – 1
Loyalty 0.47 0.56 0.09 3
and 0.674 for the ten-point scale). Once again these results tend to favour
the convergent validity of the ten-point scale.
Some authors (e.g. Givon & Shapira 1984) have contended that the
advantages of using a higher number of response alternatives tend to be
more pronounced for constructs with fewer number of indicators. The
results showed in Table 10 do not confirm this statement. In fact, the latent
variables with a higher difference between communality for the ten-point
scale and five-point scale are image (0.093), loyalty (0.089) and perceived
quality (0.041). Nevertheless, image and quality are the constructs in our
model with a higher number of indicators (five and eight, respectively). So,
globally, we could not find a relation between the communality
improvements resulting from using a higher number of response
alternatives and the number of indicators in the construct.
One way to assess discriminant validity is to determine whether each
latent variable shares more variance with its own measurement variables
than with other constructs. For that we start to compare measurement
variables communalities with the squared correlations between their own
construct and other constructs in the model. A low percentage of latent
variable squared correlations exceeding measurement variables
communalities tends to confirm discriminant validity (Chin 1998).
Communalities for the indicators of each latent variable and the
percentage of latent variable squared correlations exceeding measurement
variables communalities are shown in Table 11. Regarding the indicators
communalities it can be seen that values tend to be higher for the ten-point
scale, when compared to the five-point one. Among the 24 indicators
considered, only five show higher communalities in the five-point scale.
Regarding the latent variable squared correlations exceeding
measurement variables communalities, in general there are few violations.
331
Coelho.qxp 26/04/2007 14:56 Page 332
1 to 5 1 to 10
Latent variable Latent variable
square correlations square correlations
exceeding measurement exceeding measurement
variables communalities variables communalities
Commu- Number of % of Commu- Number of % of
Indicator nality comparisons violations nality comparisons violations
Image
Q4A 0.49 6 16.7 0.59 6 0.0
Q4B 0.21 6 83.3 0.43 6 33.3
Q4C 0.57 6 0.0 0.62 6 0.0
Q4D 0.71 6 0.0 0.70 6 0.0
Q4E 0.54 6 16.7 0.64 6 0.0
Expectations
Q5A 0.71 6 0.0 0.65 6 0.0
Q5B 0.78 6 0.0 0.70 6 0.0
Q5C 0.65 6 0.0 0.67 6 0.0
Perceived quality
Q6 0.51 6 16.7 0.59 6 0.0
Q7A 0.45 6 33.3 0.51 6 0.0
Q7B 0.39 6 50.0 0.44 6 50.0
Q7C 0.50 6 16.7 0.63 6 0.0
Q7D 0.50 6 16.7 0.53 6 0.0
Q7E 0.57 6 0.0 0.60 6 0.0
Q7F 0.57 6 0.0 0.53 6 0.0
Q7G 0.33 6 50.0 0.34 6 66.7
Perceived value
Q10 0.67 6 0.0 0.68 6 0.0
Q11 0.80 6 0.0 0.80 6 0.0
Satisfaction
Q3 0.63 6 0.0 0.59 6 0.0
Q9 0.66 6 0.0 0.73 6 0.0
Q18 0.75 6 0.0 0.78 6 0.0
Complaints
Q15–16 1.00 6 0.0 1.00 6 0.0
Loyalty
Q12 0.30 6 0.0 0.72 6 0.0
Q17 0.32 6 0.0 0.76 6 0.0
332
Coelho.qxp 26/04/2007 14:56 Page 333
Table 12 Square roots of average variance extracted and correlations between constructs
Perceived
Image Expectations value Quality Satisfaction Complaints Loyalty
Five-point scale
Image 0.74
Expectations 0.65 0.85
Perceived value 0.46 0.50 0.85
Quality 0.75 0.66 0.50 0.69
Satisfaction 0.67 0.60 0.58 0.69 0.83
Complaints 0.50 0.42 0.44 0.51 0.58 1.00
Loyalty 0.40 0.34 0.37 0.45 0.51 0.29 0.82
Ten-point scale
Image 0.78
Expectations 0.64 0.82
Perceived value 0.52 0.45 0.86
Quality 0.70 0.68 0.51 0.71
Satisfaction 0.72 0.62 0.66 0.67 0.84
Complaints 0.44 0.49 0.40 0.49 0.55 1.00
Loyalty 0.58 0.52 0.49 0.60 0.71 0.55 0.70
333
Coelho.qxp 26/04/2007 14:56 Page 334
results tend to favour the ten-point scale. In fact, with the five-point scale
a lack of discriminant validity is detected between image and quality
constructs (note that these are the constructs where we have found some
construct squared correlations exceeding measurement variables
communalities). Also, the square root of AVE for quality is equal to the
correlation between this construct and satisfaction, while with the ten-
point scale all constructs show square roots of AVEs higher than all the
corresponding correlations.
334
Coelho.qxp 26/04/2007 14:56 Page 335
335
Coelho.qxp 26/04/2007 14:56 Page 336
336
Coelho.qxp 26/04/2007 14:56 Page 337
out that the analysis was limited to the fact that the two questionnaires
(using different scales) were administered to independent samples. Some
additional analysis would be beneficial if the two questionnaires were
administered to the same sample.
Acknowledgements
The authors would like to thank Dr Dwayne Ball (University of Nebraska-
Lincoln) and the anonymous referees for their helpful comments.
References
Alwin, D.F. (1991) Research on survey quality. Sociological Methods & Research,
20, pp. 3–29.
Alwin, D.F. (1997) Feeling thermometers versus 7-point scales – which are better?
Sociological Methods and Research, 25, 3, pp. 318–340.
Alwin, D.F. & Krosnick, J.A. (1991) The reliability of attitudinal survey measures:
the role of question and respondent attributes. Sociological Methods & Research,
20, pp. 139–181.
Andrews, F.M. & Withey, S.B. (1976) Social Indicators of Well-Being: Americans’
Perceptions of Life Quality. New York: Plenum.
Ball, A.D., Coelho, P.S. & Machás, A. (2004) The role of communication and trust
in explaining customer loyalty: an extension to the ECSI model. European Journal
of Marketing, 38, available from the authors.
Cassel, C. & Eklof, J.A. (2001) Modeling customer satisfaction and loyalty on
aggregate levels: experience from the ECSI pilot study. Total Quality Management,
12, 7–8, pp. 834–841.
Cassel, C., Hackl, P. & Westlund, A. (2000) On measurement of intangibles assets: a
study of robustness of partial least squares. Total Quality Management, 7,
pp. 897–907.
Chin, W.W. (1998) The partial least squares approach to structural equation
modeling. In: G.A. Marcoulides (ed.) Modern Methods for Business Research.
Mahwah, NJ: Lawrence Erlbaum Associates.
Cicchetti, D.V., Showalter, D. & Tyrer, P.J. (1985) The effect of number of rating
scale categories on levels of interrater reliability: a Monte Carlo investigation.
Applied Psychological Measurement, 9, 1, pp. 31–36.
Colman, A.M., Norris, C.E. & Preston, C.C. (1997) Comparing rating scales of
different lengths: equivalence of scores from 5-point and 7-point scales.
Psychological Reports, 80, pp. 355–362.
Converse, J.M. & Presser, S. (1986) Survey Questions: Handcrafting the
Standardized Questionnaire. Newbury Park, CA: Sage.
Cox, E.P. (1980) The optimal number of response alternatives for a scale: a review.
Journal of Marketing Research, 17, pp. 407–422.
337
Coelho.qxp 26/04/2007 14:56 Page 338
ECSI (1998) European Customer Satisfaction Index. Report prepared for the ECSI
Steering Committee.
Fornell, C. (1992) A national customer satisfaction barometer: the Swedish
experience. Journal of Marketing, 56, 1, pp. 6–21.
Fornell, C. & Larcker, D.F. (1981) Evaluating structural equation models with
unobservable variables and measurement error. Journal of Marketing Research,
18, pp. 39–50.
Fornell, C., Johnson, M.D., Anderson, E.W., Cha, J. & Everitt Bryant, B. (1996)
The American Customer Satisfaction Index: nature, purpose and findings. Journal
of Marketing, 60, 4, pp. 7–18.
Fornell, C., Johnson, M.D., Anderson, E.W., Cha, J. & Everitt Bryant, B. (1998)
The American Customer Satisfaction Index: Methodology Report. Ann Arbor, MI:
University of Michigan.
Givon, M.M. & Shapira, Z. (1984) Response to rating scales: a theoretical model
and its application to the number of categories problem. Journal of Marketing
Research, 21, pp. 410–419.
Green, P.E. & Rao, V.R. (1970) Rating scales and information recovery – how many
scales and response categories to use. Journal of Marketing, 34, pp. 33–39.
Haley, R.I. & Case, P.B. (1979) Testing thirteen attitude scales for agreement and
brand discrimination. Journal of Marketing, 43, pp. 20–32.
Jenkins, G.D. & Taber, T.D. (1977) A Monte Carlo study of factors affecting three
indices of composite scale reliability. Journal of Applied Psychology, 62,
pp. 392–398.
Johnson, M., Gustafsson, A., Andreason, T.W., Lervik, L. & Cha, G. (2001) The
evolution and future of national customer satisfaction index models. Journal of
Economic Psychology, 22, pp. 217–245.
Krosnick, J.A. & Alwin, D.F. (1989) Response strategies for coping with the
cognitive demands of survey questions. Unpublished manuscript. Ann Arbor, MI:
University of Michigan, Institute for Social Research.
Malhotra, N. & Birks, D. (2003) Marketing Research: An Applied Approach,
2nd European edn. Prentice Hall.
Neumann, L. & Neumann, Y. (1981) Comparison of six lengths of rating scales:
students’ attitudes toward instruction. Psychological Reports, 48, pp. 399–404.
Ramsay, J.O. (1973) The effect of number of categories in rating scales on precision
of estimation of scale values. Psychometrika, 37, pp. 513–532.
Reynolds, F.D. & Neter, J. (1982) How many categories for respondent
classification. Journal of the Market Research Society, 24, 4, pp. 345–346.
Stem, D.E. & Noazin, S. (1985) The effects of number of objects and scale positions
on graphic position scale reliability. In: R.E. Lusch et al. (eds) AMA Educators’
Proceedings. Chicago: Marketing Association, pp. 370–372.
Tourangeau, R. (1984) Cognitive sciences and survey methods. In: T.B. Jabine, M.L.
Straf, J.M. Tanur & R. Tourangeau (eds) Cognitive Aspects of Survey
Methodology: Building a Bridge between Disciplines. Washington, DC: National
Academy Press, pp. 73–100.
Vilares, M. & Coelho, P. (2004) The employee–customer satisfaction chain in the
ECSI model. European Journal of Marketing, 37, pp. 1703–1722.
Vilares, M. & Coelho, P. (2006) ECSI-Portugal – Relatório de Sectores. Lisbon: IPQ.
338
Coelho.qxp 26/04/2007 14:56 Page 339
339