Advantages of Rasch Modelling For the Development of a Scale to Measure Affective Response to Consumption

ABSTRACT - This paper describes why Rasch Modelling is a valuable alternative to Classical Test Theory (CTT) when developing a scale to measure Affective Response to Consumption, an extension for satisfaction (Ganglmair and Lawson 2002). Selected characteristics related to item selection and reliability issues in CTT and Rasch Modelling are discussed. While features of CTT frequently lead to scales that measure a point on the dimension of interest, Rasch Models require the inclusion of items that tap different intensity levels, and thereby help to overcome shortcomings in current measurement, particularly regarding negative skewness and limited discrimination.


Alexandra Ganglmair and Rob Lawson (2003) ,"Advantages of Rasch Modelling For the Development of a Scale to Measure Affective Response to Consumption", in E - European Advances in Consumer Research Volume 6, eds. Darach Turley and Stephen Brown, Provo, UT : Association for Consumer Research, Pages: 162-167.

European Advances in Consumer Research Volume 6, 2003      Pages 162-167


Alexandra Ganglmair, University of Otago, New Zealand

Rob Lawson, University of Otago, New Zealand


This paper describes why Rasch Modelling is a valuable alternative to Classical Test Theory (CTT) when developing a scale to measure Affective Response to Consumption, an extension for satisfaction (Ganglmair and Lawson 2002). Selected characteristics related to item selection and reliability issues in CTT and Rasch Modelling are discussed. While features of CTT frequently lead to scales that measure a point on the dimension of interest, Rasch Models require the inclusion of items that tap different intensity levels, and thereby help to overcome shortcomings in current measurement, particularly regarding negative skewness and limited discrimination.


Affective Response to Consumption (ARC) is an extension to satisfaction that has been developed after extensive literature research into the role of satisfaction in marketing, and the recognition of problems inherent in current measurement of satisfaction (Ganglmair 2001; Ganglmair and Lawson 2002).

While Classical Test Theory (CTT) is the unchallenged theory behind scale development in marketing, Rasch Modelling (Rasch 1960), although extensively used in educational measurement and other social sciences, has been almost entirely ignored. Rasch Modelling offers an alternative theory for constructing measurement that is based on a strict mathematical formula. It combines the ordering features of Guttman scaling with a more realistic probabilistic framework (Bond and Fox 2001). This paper compares a number of characteristics of both approaches to measurement, particularly those related to item generation and reliability. Rasch Modelling puts particular emphasis on covering the entire continuum and requires the inclusion of items with different intensity to achieve acceptable measures (Wright and Stone 1979). This feature is considered particularly useful for developing a measurement for ARC, as the concept is designed to cover the entire width of possible responses to an experience, particularly at the highest, positive end of the scale.


In order to clarify the background under which ARC was developed, it is important to look at the historic development of satisfaction in marketing. Satisfaction is a key building block "in marketing philosophy, theory and practice" (Babin and Griffin 1998 p. 127), and can be regarded as a cornerstone in the marketing concept (Peterson and Wilson 1992). However, specific research interest in the area is relatively new. The beginning of the 20th century was mainly concerned with getting goods to the market and most writing was done in the area of distribution (Erevelles and Lockshin 1991). Satisfaction received only very limited attention. One of the first times satisfaction is mentioned in a marketing text was by Percival White, published in 1927. He states the need for market research in the area of customer satisfaction. Although satisfaction gained some importance during the Great Depression in the 1930s, the time after the Second World War can be seen as a time of increased consumer awareness and a shift towards consumer satisfaction (Erevelles and Lockshin 1991). The earliest significant satisfaction research was not until Cardozo’s classic article in 1965. From then on, customer satisfaction grew rapidly to become the cornerstone of marketing (Peterson and Wilson 1992), and a fundamental aspect of the marketing concept (Erevelles and Lockshin 1991), with tens of thousands of articles written on the topic, especially in the 1980s and early 1990s (Peterson and Wilson 1992).

Historically, satisfaction was viewed as a cognitive concept (Erevelles and Lockshin 1991; Hunt 1977; Westbrook 1987). It has been widely regarded as the product (outcome) of the expectation-disconfirmation comparison mentioned by Anderson in 1973 but widely introduced by Oliver in 1980. A majority of research uses variations of Oliver’s (1980) model and focuses on theoretical determinants of satisfaction. Halstead, Hartman and Schmidt (1994) state that modifications mainly add new predictor variables to provide greater explanatory power.

The expectation-disconfirmation research paradigm was still and is so dominant in satisfaction research that a special session, titled Is Satisfaction Research Dead?, at the Conference of Advances in Consumer Research in 2000, questioned the usefulness of further exploration of this out-researched comparison paradigm (Shiv and Soman 2000).


In the second half of the 1990s, affect and the potential role of emotions, became recognised as more important in marketing (Bagzzi, Gopinath and Nyer 1999; Erevelles 1998) and satisfaction research slowly started to investigate the possibility of an affective side of satisfaction. Satisfaction itself is still regarded as cognitive, but is viewed as being influenced by affective variables (e.g. Dube-Rioux 1990; Evrard and Aurier 1994; Mano and Oliver 1993; Oliver 1989, 1992, 1994; Westbrook 1987; Westbrook and Oliver 1991; Wirtz, Mattila and Tan 2000).

Recently, a stream of research emerged that questions the strict distinction between satisfaction and other positive emotions altogether (e.g. Arnould and Price 1993; Bagozzi et al. 1999; Fisher Gardial et al. 1994; Fournier and Mick 1999; Giese and Cote 2000). These studies found that people do not use satisfaction in order to express the outcome of an experience (Fisher Gardial et al. 1994; Fournier and Mick 1999; Giesse and Cote 1999). Instead, satisfaction is exchanged for stronger emotional terms like happy (Giesse and Cote 1999) and people express their level of satisfaction only if they are explicitly asked to do so (Fisher Gardial et al. 1994). In a paper on The Role of Emotions in Marketing, Bagozzi et al. (1999) express their doubts about the strict distinction between satisfaction and other emotions when they state that: " it is unclear whether satisfaction is phenomenologically distinct from many other positive emotions. The centrality of satisfaction in marketing studies is perhaps more due to being the first emotion to receive scrutiny in postpurchase behaviour research than to constituting a unique, fundamental construct in and of itself" (p. 201). Furthermore, the strict distinction between satisfaction and other positive emotions fails to appear in one of marketing’s most important parent disciplineBpsychology (Sheth, Gardener and Garrett 1988; Shaver et al. 1987; Storm and Storm 1987).

ARC has been conceptualised in line with this research (Ganglmair and Lawson 2002). It is an emotional continuum that does not rely on a single term (or a small number of terms) to express the outcome of an experience, but shifts the focus to a multitude of positive emotions. The relatively weak word satisfaction can be complemented by words that describe much stronger emotional states found in post-purchase/post-experience situations.

Thus in line with Bagozzi et al., ARC conceptualises satisfaction as one of many positive emotions. It thereby extends current theories of satisfaction by including terms that people use when they talk about their experiences: e.g. happy, pleased (Fisher Gardial et al. 1994, Giesse and Cote 2000), and by including stronger terms than the ones currently used. Inclusion of strongly positive words is considered necessary, as satisfaction scales regularly produce negative skewness and discriminate only weakly between respondents (Peterson and Wilson 1992).

Scales currently used to measure satisfaction that include more than one emotion (e.g. Delighted-Terrible scale (Andrew and Withey (1976)) have not been developed explicitly in a marketing context. The content of variations of emotion scales that were developed in psychology (e.g. Differential Emotions Scales (Izard 1977) or Pleasure-Arousal-Dominance scale (Mehrabian and Russel 1974)) is also suboptimal in a consumption context (Richins, 1997). While Richins’ (1997) Consumption Emotion Set (CES) aims to cover the entire space of emotions experienced during consumption including fear, ARC originates from the term satisfaction and puts the emphasis solely on emotions that reflect favourable/unfavourable responses to consumption experiences.

ARC is only concerned with the single dimension of emotions that relates to consumption. While the existence of mixed emotions is not denied, a recent study shows that they are the exception, rather than the norm (Larsen, McGraw and Cacioppo, 2001). In a marketing context, Mackoy and Spreng (1995) also found only weak evidence for different dimensions of satisfaction and dissatisfaction and question whether people truly think about the same things when they answer two-dimensional questions.

In ongoing research, the first author has generated an extensive item pool (715 words). As this original list was composed of a large variety of terms gained from extensive literature search (studies in marketing and psychology, as well as three thesauri), some of which where clearly not suitable, three judges with qualifications in English were asked to select items that an average New Zealander could appropriately use as a possible response to the question: How do you feel about your experience with this excursion train ride. The judges chose 29 items for inclusion in a scale to measure ARC and rated the items on a five-point scale from strongly negative to strongly positive. Interestingly, all terms suggested by the literature e.g. satisfied, happy, pleased or delighted are rated on the same intensity level, namely positive. The scale to measure ARC will also include a number of items that are rated strongly positive e.g. enthralled, fantastic, and superb in order to ensure sufficient discrimination and avoid negative skewness.


With ARC being conceptualised as an extension of satisfaction, it is important to look at scales currently used to measure satisfaction to overcome present shortcomings and limitations. Measurement of satisfaction and satisfaction scale development has gained only limited attention (Babin and Griffen 1998). Studies published by Oliver and Westbrook more than 20 years ago, are still the most cited sources for scales ((Oliver 1980, 1981; Westbrook 1980; Westbrook and Oliver 1981) c.f. Babin and Griffen 1998). The lack of measurement research is not confined to satisfaction, but is a characteristic of marketing in general, although it is supposed to be a fundamental activity of social science (DeVellis 1991). As early as 1967 Hughes titled an article Measurement, the Neglected Half of Marketing Theory (c.f. Parameswaran et al. 1979, p. 18) and Jacoby (1978) mentioned about ten years later that " most of our measures are only measures because someone says that they are, not because they have been shown to satisfy standard measurement criteria" (p.91). In spite of this early criticism and calls for further investigations into the topic, basic measurement issues are still widely neglected in marketing.

Peterson and Wilson (1992) are two of only a few researchers who investigated problems inherent in measuring satisfaction. In their article Measuring Customer Satisfaction: Fact and Artefact Peterson and Wilson (1992) discuss a striking characteristic of satisfaction measurement: "Virtually all self-reports of customer satisfaction possess a distribution in which a majority of the responses indicate that customers are satisfied. Moreover, the modal response to a satisfaction question is typically the most positive response allowed" (Peterson and Wilson 1992, p.62). The ceiling effect limits the suitability of commonly used data analysis techniques and reduces the possibility of uncovering group differences (Diener and Fujita 1995). Although observations of the phenomenon are discussed in several articles (Diener 1984; La Barbara and Mazursky 1983; Oliver 1981; Westbrook 1980), negatively skewed distribution in consumer satisfaction has been frequently overlooked (Peterson and Wilson 1992). A number of possible explanations for the special characteristic of satisfaction have been investigated but none of them seem to be conclusive and sufficient (Diener and Fujita 1995; Peterson and Wilson 1992).

It is therefore surprising that, while thousands of articles have been written investigating variables that influence satisfaction (Halstead et al. 1994), only a few articles focusing specifically on measurement have appeared in top marketing journals (Babin and Griffin 1998).


In line with general social sciences, the Classical Test Theory (CTT) has been the leading measurement paradigm in marketing (Embretson 1996; Hambleton 1991; Salzberger, Sinkovics and Schlegelmilch 1999). Extensive discussions of the classic approach can be found in Lord and Novick (1968) or Nunnally and Bernstein (1994). In marketing, the most influential paper for scale development based on CTT is Churchill’s (1979) classical piece, A Paradigm for Developing Better Measures of Marketing Constructs that has become the standard work when developing new measurement instruments.

However, George Rasch (1960) developed an alternative approach to measurement. Originally intended for educational measurement, Rasch Modelling follows mathematical and scientific rules of measurement and aims at introducing rigid rules of measurementBsimilar to physicsBinto social sciences (Wright 1997). Rasch Modelling specifies what data has to look like to constitute measurement, while leaving the question of whether measurement is accomplished to empiricism (Salzberger et al. 1999).

Although it measures an abstract construct (latent trait), the model has the same measurement properties as a ruler. Its mathematical characteristics allow a transformation from binary or ordinal answer patterns, as they are commonly observed in marketing surveys (e.g. Likert type data), into measures on an equal-interval scale (Peck 2000). The mathematical model is based "on a probabilistic relation between any item’s difficulty and any person’s ability" (Bond and Fox 2001, p.199). Rasch belongs to the family of logit models and its basic formula for binary data can be shown as:

Pvi=exp (Bv-Di)/[1+exp(Bv-Di)] where

Pvi=probability of person v answering correctly to item I

Bv=Location of person v on Rasch scale and

Di=Location of ith item on Rasch Scale

For a detailed discussion of the Rasch Model see e.g. Andrich (1988), Bond and Fox (2001), Fischer and Molenaar (1995), Wright and Stone (1979). The following characteristics of the Rasch Model are important when comparing it to CTT, especially in the context of measuring the newly conceptualised extension to satisfaction: Affective Response to Consumption.

Rasch Modelling is a probabilistic approach compared to Guttman’s deterministic one (Andrich 1982; Wright 1997; Salzberger 1999): "A person having greater ability than another should have the greater probability of solving any item of the type in question and similarly, one item being more difficult than another one means that for any person the probability of solving the second item correctly is the greater one" (Rasch 1960, p. 117).

The term difficulty of an item refers to an educational situation. In a marketing context, difficulty can be taken as the amount of the concept that an item stands for e.g. how hard it is to endorse that item, or how extreme the item is. Ability stands for the characteristic of the person e.g. how high that person rates on the measured concept.

Being the probabilistic counterpart to Guttman scaling, an appropriate answer pattern for Rasch Modelling is easier accomplished if item difficulty and person ability spread widely (Andrich 1982). By linking back to the research tradition of Thurstone and Guttman (Andrich 1988; Engelhard Jr. 1990) the Rasch Model requires items showing different intensity levels of the construct (Salzberger 2000, 1999; Wright and Stone 1979).

Specific Objectivity is one of the theoretical merits of the Rasch Model. Item parameters do not depend on characteristics of persons taking the test and person parameter do not depend on items that are chosen from an item pool (Fischer and Moenaar 1995). It follows, that the resulting parameters do not depend on the samples’ mean location or its dispersion. Other characteristics of the Rasch Model are powerful tests of model fit statistics that investigate how well the items and persons match a unidimensional model (Peck 2000). Furthermore, the ability to scale items and persons on the same dimension makes them directly comparable.

Item Response Theorists frequently discuss Rasch Models and Item Response Theory (IRT) under the same heading (Embretson and Reise 2000; Hambleton 1991; van der Linden and Hambleton 1997; Lord 1980), by stating that Rasch Modelling is the equivalent of one-parameter models developed in IRT. However, the two techniques have not only been developed separately, they also follow considerably different underlying assumptions (Linacre 1999).

Although Rasch Modelling is extensively used in educational measurement and many areas of social science (Soutar and Monroe 2001), it has been almost entirely ignored in marketing and only recently gained some attention (e.g.: Salzberger 2000, 1999; Salzberger et al. 1999; Soutar and Cornish-Ward 1997; Soutar and Monroe 2001)


While general differences of CTT and Rasch ModellingBoften under the heading of one-parameter IRTBare discussed in detail by a number of authors (e.g. Embretson 1996; Embretson and Reise 2000; Hambleton 1991; Lord 1980), here only differences with respect to item selection and reliability issuesBespecially alphaBare discussed. These aspects are considered important for explaining why Rasch Models assist in overcoming current shortcomings in measurement of satisfaction and are particularly suited to develop a measurement instrument for the newly conceptualised Affective Response to Consumption.

During the process of item generation, CTT asks for terms that tap each dimension of the construct in question (Churchill 1979). When developing a suitable selection of items, e.g. DeVellis (1991) suggests thinking of other ways an item can be worded.

In Rasch Modelling, merely generating items that tap each dimension, represent different shades of meaning (Churchill 1979) or different wordings (DeVellis 1991) is not sufficient. The researcher is additionally asked to generate items that cover different intensity levels of the construct (Andrich 1988; Salzberger 2000, 1999; Wright and Stone 1979). The emphasis thereby shifts from measuring one point in the construct towards measuring the entire dimension at interest. This emphasis on investigating the entire breadth of the construct can be found throughout the Rasch Modelling process while, as will be shown in the next paragraphs, characteristic features of CTT discourage these attempts.

CTT relies heavily on the principle of correlation. It is expected that items show high factor loadings and contribute to reliability through high item-intercorrelation (Churchill 1979). Churchill (1979) mentions that low item inter-correlation points towards a lack of unidimensionality and leads to error and unreliability. Especially with Likert type data, as it is used in satisfaction surveys and marketing research in general, the usefulness of correlations is questionable. Due to a limited range of possible answers and the resulting floor and ceiling effects, items with a similar mean also show the highest item-intercorrelation (Salzberger 2000). CTT again encourages the inclusion of similar items or simply reworded alternatives of the items.

Factor analysis and internal consistency indices like Cronbach’s alpha (1951), as methods to assess the performance of a scale can be misleading, as high correlations among a subset of items may be due to similarity of wording rather than the relationship of items with the construct in question (Steinberg and Thissen 1996). High alpha values might therefore be indicative of an inferior rather than superior quality of the scale e.g. due to duplicative items (Smith 1999).

In comparison, the Rasch Model is based on a strict mathematical model of a theoretical relationship (Bond and Fox 2001). The model represents an ideal form and neither items nor persons will ever fit it perfectly, instead the researcher is interested in which items or persons derive more than expected from the ideal model (Bond and Fox 2001). Therefore, item and person fit in relation to the model are computed (Wright 1977) and the items’ observed fit to the model is taken to investigate unidimensionality (Soutar and Monroe 2001).

In a Rasch Model items and respondents are projected on the same dimension and become directly comparable. Rasch Software programs e.g. RUMM 2010 (Andrich, Sheridan and Lou 2001) provides indices and visual displays that help to establish whether items spread sufficiently along the continuum as opposed to clump together on one point of the dimension. Persons are also investigated concerning their spread. This enables the researcher to visualize if and where additional items are necessary to cover the entire dimension of the construct, including extreme positions.


Currently used satisfaction scales that have been developed in the tradition of Classical Test Theory, constantly show limited discrimination and a strong negative skewness (Peterson and Wilson 1992; Diener and Fujita 1995; Diener 1984). These characteristics not only distort results of frequently used statistical procedures (Diener and Fujita), but also question the managerial usefulness of results gained. The limited discrimination of existing scale suggests that only a point on the dimension rather than the entire continuum is being measured, while the overwhelming use of the most positive answer category illustrates that this point is on a rather weak point on the continuum.

By introducing the concept of Affective Response to Consumption as an extension to satisfaction, the emphasis shifts from one word to a number of positive terms that can be used to express an experience and allows the inclusion of stronger words to insure that the entire dimensionBup to the very positive endBis covered. It has been pointed out that Rasch Modelling encourages the use of items with different intensities during scale development, while CTT is likely to eliminate especially difficult or easy to endorse items due to their lower correlation with other terms in the scale. Indices and graphic displays provided by Rasch Modelling further enables the researcher to determine whether the chosen items spread sufficiently along a continuum and where additional items might be included in the scale.


Recently traditional satisfaction research has been questioned, particularly the lack of the inclusion of stronger emotions found when people are asked about expressing their experience (Arnould and Price 1993; Fournier and Mick 1999; Giese and Cote 2000). Affective Response to Consumption provides an extension to the traditional view of satisfaction by being conceptualised as an emotion that includes a large variety of possible responses to experiences.

Rasch Modelling was developed in the 1960s (Rasch 1960) and although it has been widely used in other social sciences, its use in marketing has been very limited. It provides a useful tool to develop scales in marketing, especially a scale for measuring Affective Response to Consumption, as the model encourages the inclusion of items that tap different intensity levels of a continuum, and should therefore help to overcome shortcomings in currently used scales regarding lack of discrimination and negative skewness.

In ongoing research, the first author has engaged in an extensive item generation process that resulted in a pool of 29 items. First validity checks by three experts of the English language show that these items tap the entire continuum of ARC. In the next phase of the research, a measurement instrument for ARC will be developed using Rasch Modelling Software RUMM2010 (Andrich et al. 2001). This scale will be tested against currently used scales measuring satisfaction e.g. Delighted-Terrible Scale (Andrew and Whithey 1976) regarding its ability to avoid negative skewness and discriminate between respondents.


Anderson, Rolph A. (1973), "Consumer Dissatisfaction: The Effect of Disconfirmed Expectancy on Perceived Product Performance", Journal of Marketing Research 10 (February), 38B44.

Andrews, Frank M. and Steven B. Withey (1976), Social Indicators of Well-Being Americas Perception of Quality of Life, New York: Plenum Press.

Andrich, David (1982), "Using Latent Trait Measurement Models to Analyse Attitudinal Data: A Synthesis of Viewpoints", in The Improvement of Measurement in Education and Psychology, ed. D. Spearit, Melbourne: Australian Council for Educational Research, 89B126.

Andrich, David (1988), Rasch Models for Measurement, California: Sage University Paper Series on Quantitative Applications in Social Science.

Andrich, David, Berry Sheridan and Guanzhong Luo (2001), RUMM2010: Rasch Unidimensional Measurement Models [Computer Software].

Arnould, Eric J. and Linda L. Price (1993), "River Magic: Extraordinary Experience and the Extended Service Encounter", Journal of Consumer Research, 20 (June), 24B45.

Babin, Berry J. and Mitch Griffin (1998), "The Nature of Satisfaction: An Updated Examination and Analysis", Journal of Business Research, 41, 127B136.

Babin, Berry J. (1994), "An Empirical Comparison of Alternative Conceptualisations of Postconsumption Reactions", Journal of Satisfaction/Dissatisfaction and Complaining Behaviour, 7, 172-183.

Bagozzi, Richard P., Mahesh Gopinath, and Prashanth U. Nyer (1999), "The Role of Emotions in Marketing", Journal of the Academy of Marketing Science 27 (2), 184B206.

Bond, Trevor G. and Christine M. Fox (2001), Applying the Rasch Model, Mahwah, New Jersey: Lawrence Erlbaum Associates.

Cardozo, Richard N. (1965), "An Experimental Study of Customer Effort, Expectation, and Satisfaction", Journal of Marketing Research, 2 (August), 244B249.

Cronbach, Lee J. (1951), "Coefficient alpha and the internal structure of tests", Psychometrica, 16 (3), 297B334.

Churchill, Gilbert A. (1979), "A Paradigm for Developing Better Measures of Marketing Constructs", Journal of Marketing Research, 16 (February), 64B73.

DeVellis, Robert F. (1991), Scale Development: theory and application, Beverly Hills: Sage Publications.

Diener, Ed (1984), "Subjective Well-Being", Psychological Bulletin, 95 (3), 542B575.

Diener, Ed and Frank Fujita (1995). "Methodological Pitfalls and Solutions in Satisfaction Research", in New Dimensions in Marketing / Quality of Life Research, eds. Josef M. Sirgy and Coskum A. Samli, Westport: Quorum Books, 27B46.

Dube-Rioux Laurette (1990), "The power of Affective Reports in Predicting Satisfaction Judgments", Advances in Consumer Research, 17, 571B576.

Embretson, Susan E. (1996), "The new rules of measurement", Psychological Assessment, 8 (4), 341B 349.

Embretson, Susan and Steven P. Reise (2000), Item Response Theory for Psychologists, Mahwah, New Jersey: Lawrence Erlbaum Associates.

Engelhard, George J. (1990), "History of measurement", Rasch Measurement Transactions, 4 (4), 126B127, online at

Erevelles, Sunil (1998), "The Role of Affect in Marketing", Journal of Business Research, 42 (3), 199B 215.

Erevelles, Sunil and Lawrence S. Lockshin (1991), "The development of the concept of consumer satisfaction in marketing thought", in Marketing: Towards the Twenty-first Century, ed. Robert L. King, Proceedings of the Southern Marketing Association, 406B414.

Evrard, Yves and Philippe Aurier (1994), "The Influence of Emotions on Satisfaction with Movie Consumption", Journal of Satisfaction, Dissatisfaction and Complaining Behavior, 7, 119B 125.

Fischer, Gerhard H. and Ivo W. Molenaar (1995), Rasch Models, Recent Developments and Applications, New York: Springer Verlag.

Fisher-Gardial, Sarah, D. Scott Clemons, Robert B. Woodruff and Mary J. Burns (1994), "Comparing Consumers’ Recall of Repurchase and Postpurchase Product Evaluation Experiences", Journal of Consumer Research, 20 (March), 548B560.

Fournier, Susan and David G. Mick (1999), "Rediscovering Satisfaction", Journal of Marketing, 63 (October), 5B 23.

Ganglmair, Alexandra (2001). "Capturing more satisfaction", in Globalisation and Equity, Proceedings of the 26th Annual Macromarketing Conference, eds. Don R. Rahtz and Pierre McDonagh, Williamsburg: University of Rijeka, 359B369.

Ganglmair, Alexandra and Rob Lawson (2002). "Conceptualising affective satisfaction, in Proceedings of the 2002 Australia and New Zealand Marketing Academy Conference(ANZMAC) 2002, Melbourne, CD ROM.

Giese, Joan L. and Joseph A. Cote, (2000), "Defining Consumer Satisfaction", Academy of Marketing Science Review, [Online] 00 (01), online at:

Halstead, Diane, David Hartman and Sandra L. Schmidt (1944), "Multisource Effects on the Satisfaction Formation Process", Journal of the Academy of Marketing Science, 22 (2), 114B129.

Hambleton, Ronald K. (1991), Fundamentals of Item Response Theory, Newbury Park, California: Sage Publications.

Hunt, H. Keith (1977), "CS/DBOverview and Future Research Directions", in Conceptualisation and Measurement of Consumer Satisfaction and Dissatisfaction, ed. H. Keith Hunt, Cambridge, Mass: Marketing Science Institute, 455B488.

Izard, Carroll E. (1977), Human Emotions, New York: Plenum

Jacoby, Jacob (1978), "Consumer Research: A State of the Art Review", Journal of Marketing, 42 (April), 87B96.

LaBarbara, Priscilla and David A. Mazursky (1984), "A Longitudinal Assessment of Consumer Satisfaction/Dissatisfaction: The Dynamic Aspect of the Cognitive Process", Journal of Marketing Research, 20 (November), 394B404.

Larsen, Jeff T., A. Peter McGraw, and John T. Cacioppo (2001), "Can People Feel Happy and Sad at the Same Time?," Journal of Personality and Social Psychology, 81(4), 684-696.

Lord, Frederique M. (1980), Applications of item response theory to practical testing problems, Hillside NJ: Erlbaum.

Lord, Frederique M. and Melvin Novick (1968), Statistical theories of mental test scores, Reading, Mass.: Addison-Wesley.

Mackoy, Robert D. and Richard A. Spreng (1995), The Dimensionality of Consumer Satisfaction/Dissatisfaction: An Empirical Examination," Journal of Consumer Satisfaction, Dissatisfaction and Complaining Behavior, 8, 54-58

Mano, Haim and Richard L. Oliver, (1993), "Assessing the Dimensionality and Structure of the Consumption Experience: Evaluation, Feeling, and Satisfaction", Journal of Consumer Research, 20 (December), 451B466.

Mehrabian, Albert and James A. Russell (1974), An Approach to Environmental Psychology, Cambridge Mass.: MIT Press.

Nunnally, Jum C. and Ira H. Bernstein (1994), Psychometric Theory, New York: McGraw Hill.

Oliver, Richard L. (1980), "A Cognitive Model of Antecedents and Consequences of Satisfaction Decisions", Journal of Marketing Research, 17 (November), 460B469.

Oliver, Richard L. (1981), "Measurement and Evaluation of Satisfaction Processes in Retail Settings", Journal of Retailing, 57 (3), 25B48.

Oliver, Richard L. (1989), "Processing of the Satisfaction Response in Consumption: A Suggested Framework and Research Propositions", Journal of Consumer Satisfaction, Dissatisfaction, and Complaining Behavior, 2, 1B16.

Oliver, Richard L. (1992), "An Investigation of the Attribute Basis of Emotion and Related Affects in Consumption: Suggestions for a Stage-Specific Satisfaction Framework", Advances in Consumer Research, 19, 237B244.

Oliver, Richard L. (1994), "Cognitive, Affective, and Attribute Bases of the Satisfaction Response", Journal of Consumer Research, 20 (December), 418B430.

Parameswaran, Ravi, Barnett A. Greenberg, Danny N. Bellenger and Dan H. Robertson (1979), "Measuring Reliability: A Comparison of Alternative Techniques", Journal of Marketing Research, 16 (February), 18B29.

Peck, Bob (2000), Ethnicity: A Study of Participation, Aspirations and Achievement in Education, A thesis submitted in part completion of the requirements of the degree of Doctor of Education, Perth: Murdoch University.

Peterson, Robert A. and William R. Wilson (1992), "Measuring Customer Satisfaction: Fact and Artifact", Journal of the Academy of Marketing Science, 20 (1), 61B71.

Rasch, Georg (1960/80), Probabilistic Models for Some Intelligence and Attainment Tests, Chicago: MESA Press.

Richins, Marsha L. (1997), Measuring Emotions in the Consumption Experience, Journal of Consumer Research, 24(September), 127-146.

Salzberger, Thomas (1999), "How the Rasch model may shift our perspective of measurement in marketing research" in Proceedings of the 1999 Australia and New Zealand Marketing Academy Conference(ANZMAC), eds. Jack Cadeaux and Marc Uncles, Sydney, CD ROM.

Salzberger, Thomas (2000), "An alternative way of establishing measurement in marketing researchBits implications for scale development and validity", in Proceedings of the 2000 Australia and New Zealand marketing Academy Conference(ANZMAC), ed. Aron O’Cass, Gold Coast, CD ROM.

Salzberger, Thomas, Rudolf R. Sinkovics and Bodo B. Schlegelmilch (1999), "Data Equivalence in Crosscultural Research: A Comparison of Classical Test Theory and Latent Trait Theory Based Approaches", Australasian Marketing Journal, 7 (2), 23B38.

Shaver, Philip, Judy Schwartz, Donald Kirson and Cary O’Connor (1987), "Emotion Knowledge: Further Exploration of a Prototype Approach", Journal of Personality and Social Psychology, 52 (6), 1061B1086.

Sheth, Jagdish N., David M. Gardner, and Dennis E. Garrett, (1988), Marketing Theory: evolution and evaluation, New York: John Wiley and Sons, Inc.

Shiv, Baba and Dilip Soman (2000), "Is Satisfaction Research Dead?", Advances in Consumer Research, 27, 252.

Smith, Anne M. (1999), "Some Problems When Adopting Churchill’s Paradigm for the Development of Service Quality Measurement Scales", Journal of Business Research, 46 (2), 109B120.

Soutar, Geoff N. and Steven P. Cornish-Ward (1997), "Ownership Patterns for Durable Goods and Financial Assets: a Rasch analysis", Applied Economics, 29 (7), 903B911.

Soutar, Geoff N. and Garry Monroe (2001), "Rasch modelling: An alternative to summated scales" in ANZAM 2001BClosing the Divide, Auckland.

Steinberg, Lynne and David Thissen (1996), "Uses of Item Response Theory and the Testlet Concept in the Measurement of Psychopathology", Psychological Methods, 1 (1), 81B97.

Storm, Chrisine and Tom Storm (1987), "A Taxonomic Study of the Vocabulary of Emotions", Journal of Personality and Social Psychology, 53 (4), 805B816.

van der Linden, Wim J. and Ronald K. Hambleton (1997), "Item response theory: Brief history, common models, and extensions", in Handbook of modern item response theory, eds. Wim J. van der Linden and Ronald K. Hambleton, New York: Springer Verlag, 1B28.

Westbrook, Robert A. (1989), "Product/consumption-based affective responses and postpurchase processes", Journal of Marketing Research, 24 (August), 258B270.

Westbrook, Robert A. and Richard L. Oliver (1981), "Developing Better Measures of Consumer Satisfaction", Advances in Consumer Research, 3, 94B99.

Westbrook, Robert A. (1991), "The Dimensionality of Consumption Emotion Patterns and Consumer Satisfaction", Journal of Consumer Research, 18 (June), 84B91.

Wirtz, Jochen, Anna S. Mattila and Rachel L. Tan (2000), "The Moderating Role of Target-Arousal on the Impact of Affect on Satisfaction: An Examination in the Context of Service Experiences", Journal of Retailing, 76 (3), 347B365.

Wright, Benjamin D. (1997), "Fundamental measurement for psychology", MESA Research Memorandum 64, available online at

Wright, Benjamin D. and Mark H. Stone (1979), Best Test Design, Chicago: MESA Press.



Alexandra Ganglmair, University of Otago, New Zealand
Rob Lawson, University of Otago, New Zealand


E - European Advances in Consumer Research Volume 6 | 2003

Share Proceeding

Featured papers

See More


Using a Meta-Analysis to Unravel Relative Importance of Postulated Explanations for the Endowment Effect

Peter Nguyen, Ivey Business School
Xin (Shane) Wang, Western University, Canada
David J. Curry, University of Cincinnati, USA

Read More


Metaphorically Transgressing the Brand Relationship

Alberto Lopez, Tecnológico de Monterrey, MEXICO
Martin Reimann, University of Arizona, USA
Raquel Castaño, Tecnológico de Monterrey, MEXICO

Read More


B6. A Study About the Moderator Effect of the Information Trust in the Relationships Between the Users´ Participation in Virtual Communities and the Benefits Obtained.

Sara Campo, Autonomous University of Madrid
Jano Jiménez, Autonomous University of Madrid
Natalia Rubio, Universidad Autónoma of Madrid
Nieves Villaseñor, Universidad Autónoma of Madrid
Mªjesus Yague, Universidad Autónoma of Madrid

Read More

Engage with Us

Becoming an Association for Consumer Research member is simple. Membership in ACR is relatively inexpensive, but brings significant benefits to its members.