摘要 :
This article studies the difference between the criterion validity coefficient of the widely used overall scale score for a unidimensional multicomponent measuring instrument and the maximal criterion validity coefficient that is ...
展开
This article studies the difference between the criterion validity coefficient of the widely used overall scale score for a unidimensional multicomponent measuring instrument and the maximal criterion validity coefficient that is achievable with a linear combination of its components. A necessary and sufficient condition of their identity is presented in the case of measurement errors being uncorrelated among themselves and with a used criterion. An upper bound of the difference in these validity coefficients is provided, indicating that it cannot exceed the discrepancy between the maximal reliability and composite reliability indexes. A readily applicable latent variable modeling procedure is discussed that can be used for point and interval estimation of the difference between the maximal and scale criterion validity coefficients. The outlined method is illustrated with a numerical example.
收起
摘要 :
Purpose Statistical equivalence testing is more appropriate than conventional tests of difference to assess the validity of physical activity (PA) measures. This article presents the underlying principles of equivalence testing an...
展开
Purpose Statistical equivalence testing is more appropriate than conventional tests of difference to assess the validity of physical activity (PA) measures. This article presents the underlying principles of equivalence testing and gives three examples from PA and fitness assessment research.
收起
摘要 :
Introduction: As patient-reported outcome measures (PROMs) continue to evolve as vital measures of patient status, it may be useful to identify efficiently, Single Assessment Numeric Evaluation (SANE) scores that are valid and rel...
展开
Introduction: As patient-reported outcome measures (PROMs) continue to evolve as vital measures of patient status, it may be useful to identify efficiently, Single Assessment Numeric Evaluation (SANE) scores that are valid and related to the patient's specific functional needs. Objective: To evaluate the concurrent validity between SANE scores and commonly used body region-specific functional PROMs, functional percentage change scores, and total visits in patients with musculoskeletal (MSK) disorders. Methods: 479 patients completed the SANE and one of the following PROMs at physical therapy discharge: Modified Low Back Pain Disability Questionnaire [MDQ], Neck Disability Index [NDI], Penn Shoulder Score [PSS], International Knee Documentation Committee [IKDC], Lower Extremity Functional Scale [LEFS]. Pearson correlation coefficients were used to assess the relationship between SANE and the aforementioned outcomes and total visits. Results: The SANE was moderately negatively correlated with the MDQ and NDI at discharge. There were high positive correlations between SANE and PSS and IKDC and moderate positive correlation between SANE and LEFS. The SANE and MDQ and IKDQ demonstrated low positive correlation for functional percentage change scores, and the SANE and NDI demonstrated moderate positive correlation for functional percentage change scores. For total visits outcome, there was a negligible negative correlation between SANE and MDQ and NDI at discharge. Conclusion: The SANE exhibits acceptable concurrent validity across all investigated PROMs at physical therapy discharge. However, inconsistent relationships across body regions for functional percentage change and total visits suggest differences in these values as compared to raw discharge scores.
收起
摘要 :
Introduction A lack of standardization with accelerometry-based monitors has made it hard to advance applications for both research and practice. Resolving these challenges is essential for developing methods for consistent, agnos...
展开
Introduction A lack of standardization with accelerometry-based monitors has made it hard to advance applications for both research and practice. Resolving these challenges is essential for developing methods for consistent, agnostic reporting of physical activity outcomes from wearable monitors in clinical applications. Methods This article reviewed the literature on the methods used to evaluate the validity of contemporary consumer activity monitors. A rationale for focusing on energy expenditure as a key outcome measure in validation studies was provided followed by a summary of the strengths and limitations of different analytical methods. The primary review included 23 recent validation studies that collectively reported energy expenditure estimates from 58 monitors relative to values from appropriate criterion measures. Results The majority of studies reported weak indicators such as correlation coefficients (87%), but only half (52%) reported the recommended summary statistic of mean absolute percent error needed to evaluate actual individual error. Fewer used appropriate tests of agreement such as equivalence testing (22%). Conclusions The use of inappropriate analytic methods and incomplete reporting of outcomes is a major limitation for systematically advancing research with both research grade and consumer-grade activity monitors. Guidelines are provided to standardize analytic methods and reporting in these types of studies to enhance the utility of the devices for clinical mHealth applications.
收起
摘要 :
Objective: The aim of this study was to determine the concurrent, convergent and divergent validity as well as the stability reliability of the Igbo version of the SALSA.
摘要 :
For a modern mechanical system, it is inadequate to describe the complicated behavior by a single mathematical model. Usually, the input-output data have to be clustered into several different groups before performing the system i...
展开
For a modern mechanical system, it is inadequate to describe the complicated behavior by a single mathematical model. Usually, the input-output data have to be clustered into several different groups before performing the system identification. This paper introduces a novel data clustering method and the criteria for determining the proper regression models. The Fuzzy C-Regression Models (FCRM) clustering algorithm assumes that the data space could be drawn from c different regression models. The distance of object data vector to some representatives of cluster as the measure of goodness of fit is then replaced by the fitness of different regression models to each output. Although FCRM clustering algorithm is useful in fuzzy model identification, the reliable cluster validity criterion to guide the FCRM clustering algorithm is still lacking. Hence, it will be an important issue to design a cluster validity criterion suitable for FCRM clustering algorithm in order to choose the optimal number of clusters. In this article, we will introduce a cluster validity criterion suitable for FCRM, and take the limit analysis on it to understand its behavior as the weighting exponent m→1~+ and m→∞.
收起
摘要 :
Objectives: This investigation sought to test the construct validity of the irrational performance beliefs inventory (iPBI) in a sample of amateur and semi-professional athletes.
摘要 :
We examined the validity of self-report measures of narcissism and mania by relating them to interview-based ratings of psychopathology. Narcissism scales were taken from the Narcissistic Personality Inventory (NPI), the Personali...
展开
We examined the validity of self-report measures of narcissism and mania by relating them to interview-based ratings of psychopathology. Narcissism scales were taken from the Narcissistic Personality Inventory (NPI), the Personality Diagnostic Questionnaire-4+, and the Short Dark Triad. Mania measures included the Altman Self-Rated Mania Scale (ASRM) and scales taken from the Hypomanic Personality Scale (HPS) and Expanded Version of the Inventory of Depression and Anxiety Symptoms. Our analyses addressed two key issues. The first issue was whether these scales demonstrated significant criterion validity (e.g., whether the HPS scales correlated significantly with interview ratings of mania). The second issue was whether they displayed specificity to their target constructs (e.g., whether the NPI scales correlated more strongly with ratings of narcissistic personality disorder than with other forms of psychopathology). All of the narcissism scales-including all three NPI subscales-correlated significantly with interview ratings of narcissistic personality disorder and showed considerable evidence of diagnostic specificity. Most of the mania scales also displayed good criterion validity and diagnostic specificity. However, two measures-the ASRM and the HPS Social Vitality subscale-had weak, nonsignificant associations with interview ratings of manic episodes; these findings raise concerns regarding their validity as specific indicators of mania.
收起
摘要 :
The contingent valuation method (CV) has become a recognised tool for estimating monetary non-market values. Despite the pragmatic acceptance of CV in policy evaluation, the application of CV-based estimates in decisionmaking rema...
展开
The contingent valuation method (CV) has become a recognised tool for estimating monetary non-market values. Despite the pragmatic acceptance of CV in policy evaluation, the application of CV-based estimates in decisionmaking remains controversial, as critics argue that CV suffers of hypothetical bias and question its accuracy to reflect non-market values via willingness to pay (WTP) estimates. In this paper we approach the assessment of CV accuracy from a double perspective. First, we assess validity and reliability by comparing CV-based WTP estimates and real monetary contributions to a crowdfunding initiative. Second, we assess construct validity identifying whether changing individual preferences are driven by strictly rational economic behaviour or by other factors that are not consistent with it. For this purpose, we conduct regression analysis using a synthetic panel dataset constructed from two contingent valuation surveys using the Propensity Score Matching method. Our findings suggest that WTP estimates are suitable to infer the economic value of environmental assets. This evidence points towards non-market valuation methods being capable of eliciting rational behaviour from individuals that is free of hypothetical bias. However, hypothetical bias might be lurking in a less researched area, that of market participation, which calls for a rigorous treatment of protest behaviour.
收起
原文获取