The C-OAR-SE procedure for scale development in marketing

By John R. Rossiter. 2002

2,425 citations recorded by the source corpus.

Construct definition, Object classification, Attribute classification, Rater identification, Scale formation, and Enumeration and reporting (C-OAR-SE) is proposed as a new procedure for the development of scales to measure marketing constructs. COAR-SE is based on content validity, established by expert agreement after pre-interviews with target raters. In C-OAR-SE, constructs are defined in terms of Object, Attribute, and Rater Entity. The Object classification and Attribute classification steps in C-OAR-SE produce a framework (six types of scales) indicating when to use single-item vs. multiple-item scales and, for multiple-item scales, when to use an index of essential items rather than selecting unidimensional items with a high coefficient alpha. The Rater Entity type largely determines reliability, which is a precision-of-score estimate for a particular application of the scale.

Subfields: Marketing, Organizational Behavior and Human Resource Management, Social Psychology

View Paper: https://www.semanticscholar.org/paper/ad69ff5977d98201cc09d1322184ad43a1f5bed2

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Marketing

In Organizational Behavior and Human Resource Management

In Social Psychology

Citations in the corpus

Destination image and tourist behavioural intentions: A meta-analysis (2020, neutral): “Most of studies have seen destination image as an abstract formed object (Rossiter, 2002) and adopted the two-or three-component approach (Gartner, 1994; Baloglu & McCleary, 1999; Sönmez & Sirakaya, 2002; Lin, Morais, Kerstetter, & Hou, 2007).”
The service recovery paradox: true but overrated? (2008, background): “Multi-item measures are preferred, but not always required, in service research (Drolet and Morrison's, 2000, Rossiter, 2002) if cost consideration and respondent fatigue are limiting factors.”
Cultural intelligence: A theory-based, short form measure (2015, background): “opment and contrasts to the mechanistic application of psychometric procedures, which has been recently criticized (see Diamantopoulos, 2005; Rossiter, 2002).”
Marketing measurement revolution: the C-OAR-SE method and why it must replace psychometrics (2011, methodology): “Leading this revolution is the C-OAR-SE method (see Rossiter, 2002b, 2005, 2007, 2008, 2009a, and 2010).”
Sport Stadium Atmosphere: Formative and Reflective Indicators for Operationalizing the Construct (2010, background): “The goal is to find a universe of indicators that fully covers the scope of environmental perceptions (Bollen & Lennox, 1991; Rossiter, 2002).”
Knowledge workers' creativity and the role of the physical work environment (2011, background): “Because the item scores of a formative index do not need to correlate, common test methods for assessing construct reliability do not apply (Rossiter, 2002).”
Advancing formative measurement models (2008, background): “…characterize a set of distinct causes which are not interchangeable as each indicator captures a specific aspect of the construct's domain (see also Jarvis et al., 2003; and Rossiter, 2002); indeed, omitting an indicator potentially alters the nature of the construct (Bollen and Lennox, 1991).”
Exploration And Exploitation Fit And Performance In International Strategic Alliances (2012, background): “(2003) for determining whether the measurement mode for a construct is formative or reflective, and Rossiter’s (2002) C-OAR-SE procedure), yet we recognize the persistent possibility of estimatingmisspecifiedmodels.”
Appropriate use of single-item measures is here to stay (2014, background): “Moreover, Rossiter (2002, 2011) argues that construct definitions should make clear whether objects and attributes are concrete or abstract, a principle, which if it is adhered to, would reduce the risk of using single-item measures for other than doubly concrete constructs.”
Guilt appeals: The mediating effect of responsibility (2006, background): “Multi-item scales are often preferred by researchers (Peter, 1979); however, it has been argued that single-item intention measures are more appropriate at times (Rossiter, 2002).”