A Method of Cluster Analysis

Cureton, Edward E.; Cureton, Louise W.; Durfee, R.C.

doi:10.1207/s15327906mbr0501_7

Cited by 12 publications

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, it was necessary that these combinations be distinct from one another, to reduce the problems that arise in predictive analyses when predictors are overlapping. Gorsuch (1983) noted that some investigators (e.g., Cureton, Cureton, and Durfee, 1970) have combined factor analysis with cluster analysis to improve detection of constructs when measures have not been refined a priori to provide simple structure. In this twostage procedure, correlations among variables ultimately determine the inferred structure and scheme for combining measured variables into composite variables.…”

Section: Rationale For Using An Empirical Approach To Form Composite mentioning

confidence: 99%

Predictors of the Survival of Innovations^*

Astebro¹,

Michela²

2005

J of Product Innov Manag

View full text Add to dashboard Cite

This article examines the impact of key success factors on the survival of innovations that have reached the market and were developed by inventors outside of established organizations. It is of interest to learn which characteristics predict, at an early stage, the duration of the innovation's length of sales, because this duration is important to the financial success of new products. A focus on survival also can contribute conceptual clarity to the study of new product development. This study uses the Inventor's Assistance Program (IAP) at the Canadian Innovation Centre (CIC) in Waterloo, Canada, as the source of data. The CIC is a not-for-profit agency that provides various services to foster business development involving innovative products and services. Analysts in the IAP evaluate a specific product idea or invention on 37 dimensions before it has reached the market. The data for the present study involved these 37 variables evaluated each with a three-point linguistic scale. As the evaluations of the criteria are subjective, they might be argued to contain inaccuracies compared to objective data. On the other hand, the analysts use multiple related measures of concepts that have been shown to increase predictive accuracy. The use of experts who are unrelated to the projects avoids decisionmaking biases potentially associated with project managers' assessment of their own projects, such as unrealistic optimism. The recording of the expert evaluations of the ideas before they reached the market and independent of the measure of success, rather than using post-project completion evaluations, eliminates measurement biases such as hindsight bias and common method variance bias. Identifying information was used in these records to conduct a telephone survey of the inventors. An exploratory method of data analysis is identified and used that distinguishes research-appropriate constructs and their indicators in these data. Cluster analysis was performed, and survival regression correlated cluster scores with survival.

show abstract

Section: Rationale For Using An Empirical Approach To Form Composite mentioning

confidence: 99%

Predictors of the Survival of Innovations^*

Astebro¹,

Michela²

2005

J of Product Innov Manag

View full text Add to dashboard Cite

show abstract

Cluster Analysis, Variables

D’Agostino

Russell

2005

Encyclopedia of Biostatistics

View full text Add to dashboard Cite

Cluster analysis involves grouping objects, subjects or variables, with similar characteristics into groups. Similarity or dissimilarity of objects is measured by a particular index of association. The focus here is on clustering of variables instead of subjects. Types of methods that cluster variables based on correlation structure of variables or factorial structure of variables are considered, where factorial structure refers to a structure obtained from principal component analysis or factor analysis. The approaches described for cluster analysis uses various indices of association such as factor loadings, correlation matrix, and cosine matrix. Examples of these are shown and the advantages and disadvantages of each approach are discussed.

show abstract