Weak Measurements vs. Strong Statistics: An Empirical Critique of S. S. Stevens' Proscriptions nn Statistics

Baker, Bela O.; Hardyck, Curtis; Petrinovich, Lewis

doi:10.1177/001316446602600204

Cited by 205 publications

(90 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Consistent with the fi ndings of Baker et al (1966), this study's ordered categorical variables (as shown in Table 4) are considered to be continuous and fi t for t-test comparisons.…”

Section: Limitationsmentioning

confidence: 99%

Green segmentation and environmental certification: insights from forest products

Anderson²,

et al. 2009

View full text Add to dashboard Cite

Firms engage in environmental marketing in order to appeal to environmentally conscious consumers. Within the context of the forest product industry, this research uses data from two studies to empirically test whether a relationship exists between demographic/psychographic characteristics and reported environmentally conscious intentions. In both studies, the results indicate that the environmental marketing of certifi ed/ecolabeled forest products appeals to a segment of environmentally conscious consumers. This appeal occurs for both a value-added product (furniture) and a non-value-added product (plywood). Thus, there is support for the argument that environmental marketing to environmentally conscious consumers can result in 'green segmentation'. Key fi ndings from this study suggest that those consumers reporting the strongest preferences for environmentally certifi ed forest products were more willing to pay a premium for certifi ed products, more likely to display environmentally conscious behavior and more likely to perceive that green consumer purchases effectively benefi t the environment. These characteristics were most common among females and those familiar with the concept of environmental certifi cation.

show abstract

“…Consistent with the fi ndings of Baker et al (1966), this study's ordered categorical variables (as shown in Table 4) are considered to be continuous and fi t for t-test comparisons.…”

Section: Limitationsmentioning

confidence: 99%

Green segmentation and environmental certification: insights from forest products

Anderson²,

et al. 2009

View full text Add to dashboard Cite

show abstract

“…It has been suggested that parametric statistical methods (e.g., t test, that assume normal distribution of the sample, and that data are derived from an interval scale) be used only with interval or ratio data and nonparametric tests (e.g., Wilcoxon rank-sum test) be used for ordinal data, although this is also subject to some controversy. The argument for using parametric statistics for ordinal data, which is not an uncommon practice, is that the sum scores approximate interval data and parametric statistics can handle the shortcomings of ordinal scales [3,65].…”

Section: Methodological Aspects Of Rating Scales: Ordinal Scales and mentioning

confidence: 99%

The Spectrum of Functional Rating Scales in Neurology Clinical Trials

Narayanaswami

2017

Neurotherapeutics

View full text Add to dashboard Cite

The selection of an appropriate outcome measure is crucial to the success of a clinical trial, in order to obtain accurate results, which, in turn, influence patient care and future research. Outcomes that can be directly measured are mortality/survival. More frequently, neurology clinical trials evaluate outcomes that cannot be directly measured, such as disability, cognitive function, or change in symptoms of the condition under study. These complex outcomes are abstract ideas or latent constructs and are measured using rating scales. Functional rating scales typically assess the ability of patients to perform tasks and roles for everyday life. Rating scales should be valid (measure what they are supposed to measure), reliable (provide similar results if administered under the same conditions), and responsive (able to detect clinically important changes over time). The clinical relevance of rating scales depends on their ability to detect a minimal clinically important difference, and should be distinguished from statistical significance. Most rating scales are ordinal scales and have limitations. Modern psychometric methods of Rasch analysis and item response theory, termed latent trait theory, are increasingly being utilized to convert ordinal data to interval measurements, both to validate existing scales and to develop new scales. Patient-reported outcomes are being increasingly used in clinical trials and have a role in clinical quality assessment. The PROMIS and NeuroQoL databases are excellent resources for rigorously developed and validated patientreported outcomes.

show abstract

“…The above view of the predominant role of measurement theory in data analysis has been criticized by several authors, see Lord (1953), Savage (1957), Tukey (1961), Adams et al (1965) and Baker et al (1986) for instance. More references and a detailed discussion survey are given by Velleman and Wilkinson (1993).…”

Section: Scale Interpretation and Statistical Methodologymentioning

confidence: 99%