Interval Level Of Measurement Research Articles

Application of the Rasch measurement model in rehabilitation research and practice: early developments, current practice, and future challenges.

The application of the Rasch measurement model in rehabilitation is now well established. Both its dichotomous and polytomous forms provide for transforming ordinal scales into interval-level measures, consistent with the requirements of fundamental measurement. The growth of applying the model in rehabilitation spans 30 years, during which both the protocol has steadily developed and several software packages have emerged that provide for analysis, together with the "R" language that has an increasing set of codes for applying the model. This article reviews that development and highlights current practice requirements, including those for providing the relevant information for the methods, and what is expected of the analysis. In addition, this provides a worked example and looks at the remaining issues and current developments of its application.

GMLM-CNN: A Hybrid Solution to SWIR-VIS Face Verification with Limited Imagery

Cross-spectral face verification between short-wave infrared (SWIR) and visible light (VIS) face images poses a challenge, which is motivated by various real-world applications such as surveillance at night time or in harsh environments. This paper proposes a hybrid solution that takes advantage of both traditional feature engineering and modern deep learning techniques to overcome the issue of limited imagery as encountered in the SWIR band. Firstly, the paper revisits the theory of measurement levels. Then, two new operators are introduced which act at the nominal and interval levels of measurement and are named the Nominal Measurement Descriptor (NMD) and the Interval Measurement Descriptor (IMD), respectively. A composite operator Gabor Multiple-Level Measurement (GMLM) is further proposed which fuses multiple levels of measurement. Finally, the fused features of GMLM are passed through a succinct and efficient neural network based on PCA. The network selects informative features and also performs the recognition task. The overall framework is named GMLM-CNN. It is compared to both traditional hand-crafted operators as well as recent deep learning-based models that are state-of-the-art, in terms of cross-spectral verification performance. Experiments are conducted on a dataset which comprises frontal VIS and SWIR faces acquired at varying standoffs. Experimental results demonstrate that, in the presence of limited data, the proposed hybrid method GMLM-CNN outperforms all the other methods.

Methodology for identifying homogeneous consumer groups based on qualitative data

In this article, the author proposes a method for identifying homogeneous consumer groups based on qualitative data. The problem is that when researching the end-user market, information is often presented not in quantitative but in qualitative form. The random variables with which mathematical statistics deal are usually assumed to be numeric. Therefore, among researchers there is an opinion that achieving at least an interval level of measurement is always desirable, since it expands the researcher capabilities, giving him grounds to use data mathematical and statistical analysis traditional methods. Sociologists, on the other hand, emphasize the qualitative data enormous role in the respondents’ study. The presented methodology is based on cluster analysis, differs from the applied market segmentation methods in that it uses cluster analysis algorithms developed concerning qualitative indicators, and involves a proximity measure use that allows one to determine the natural weights between clustering variables. Also, the technique provides for the optimal partition determination based on the changes’ graph in the average internal communication, depending on the selected clusters’ number. The optimal among the partitions set is considered to be a partition in which the average internal connection increases sharply in comparison with the previous partition. Provided that the clusters’ number in each subsequent partition in comparison with the previous one is greater by one. Thus, the methodology allows identifying the existing market structure.

Decision-making by Heads of Academic Department using Student Evaluation of Instruction (SEI)

This study investigates the ways in which heads of academic department use student evaluation of instruction (SEI) to make decisions about individual faculty members and/or whole academic departments. The study utilized a convenience sample of 57 heads of department, who completed an online questionnaire with two main constructs, which were assessed at the interval level of measurement. The results of the study revealed significant differences between heads of department who tend to trust SEI results compared to those who tend not to trust SEI results. The findings suggest there is a significant association between how heads of department perceive SEI and how they use it to make decisions about individual faculty members and their academic departments. In addition, analysis of the respondents as per two groups, according to their attitudes of trust or distrust toward SEI, showed that disparities within these groups were greater with respect to issues or decisions that affect individuals as opposed to whole departments. Therefore, the study concludes that decisions should not be made based solely on the results of SEI; rather, multiple sources of evaluation should be utilized to make proper decisions. The author strongly recommends that academic leaders should use SEI across multiple years or courses in order to obtain more reliable information. Future research may include qualitative studies on the topic and discipline-specific studies within certain academic departments or college clusters.

Measuring coping in people with amyotrophic lateral sclerosis using the Coping Index-ALS: A patient derived, Rasch compliant scale

ObjectiveThe progressively disabling and terminal nature of ALS/MND imposes major coping demands on patients. We wished to improve the psychometric properties of our previously published MND-Coping Scale, so that parametric analyses were valid, and to make it simpler for patients to complete and clinicians to score. MethodsAfter a new qualitative analysis of 26 patients with ALS/MND, the draft Coping Index-ALS (CI-ALS) was administered to 465 additional patients, alongside COPE-60, General Perceived Self Efficacy scale, and WHOQOL-BREF. Validity of the CI-ALS was assessed using the Rasch model. External validity was checked against comparator measures. ResultsThirteen centres contributed 465 patients, mean age 64.9 years (SD 10.8), mean disease duration 28.4 months (SD 37.5). The CI-ALS-Self and CI-ALS-Others both satisfied Rasch model expectations and showed invariance across age, gender, marital status and type of onset. Expected correlations were observed with comparator scales. A nomogram is available to convert the raw scores to interval level measures suitable for parametric analysis. ConclusionsCoping abilities in ALS/MND can now be measured using a simple 21 item self-report measure, offering two subscales with a focus of ‘coping by self ’ and ‘coping with others’. This allows clinicians to identify individuals with poor coping and facilitates research on interventions that may improve coping skills.

Analyzing the cross-national comparability of party positions on the socio-cultural and EU dimensions in Europe

AbstractUsing survey vignettes and scaling techniques, we estimate common socio-cultural and European integration dimensions for political parties across the member states of the European Union. Previous research shows that party placements on the economic left-right dimension are cross-nationally comparable across the EU; however, the socio-cultural dimension is more complex, with different issues forming the core of the dimension in different countries. The 2014 wave of the Chapel Hill Expert Survey included anchoring vignettes which we use as “bridge votes” to place parties from different countries on a common liberal/authoritarian dimension and a separate common scale for European integration. We estimate the dimensions using the Bayesian Aldrich–McKelvey technique. The resulting scales offer cross-nationally comparable, interval-level measures of a party's socio-cultural and EU ideological positions.

Relevance and comprehension of patient-reported outcome measures of mobility, physical function, and speech among patients with late-onset GM2 gangliosidoses

The progressively disabling and terminal nature of ALS/MND imposes major coping demands on patients. We wished to improve the psychometric properties of our previously published MND-Coping Scale, so that parametric analyses were valid, and to make it simpler for patients to complete and clinicians to score.After a new qualitative analysis of 26 patients with ALS/MND, the draft Coping Index-ALS (CI-ALS) was administered to 465 additional patients, alongside COPE-60, General Perceived Self Efficacy scale, and WHOQOL-BREF. Validity of the CI-ALS was assessed using the Rasch model. External validity was checked against comparator measures.Thirteen centres contributed 465 patients, mean age 64.9 years (SD 10.8), mean disease duration 28.4 months (SD 37.5). The CI-ALS-Self and CI-ALS-Others both satisfied Rasch model expectations and showed invariance across age, gender, marital status and type of onset. Expected correlations were observed with comparator scales. A nomogram is available to convert the raw scores to interval level measures suitable for parametric analysis.Coping abilities in ALS/MND can now be measured using a simple 21 item self-report measure, offering two subscales with a focus of ‘coping by self ’ and ‘coping with others’. This allows clinicians to identify individuals with poor coping and facilitates research on interventions that may improve coping skills.

Beyond homophily: Incorporating actor variables in statistical network models

AbstractWe consider the specification of effects of numerical actor attributes, having an interval level of measurement, in statistical models for directed social networks. A fundamental mechanism is homophily or assortativity, where actors have a higher likelihood to be tied with others having similar values of the variable under study. But there are other mechanisms that may also play a role in how the attribute values of two actors influence the likelihood of a tie between them. We discuss three additional mechanisms: aspiration, the tendency to send more ties to others having high values; attachment conformity, sending more ties to others whose values are close to the “social norm”; and sociability, where those having higher values will tend to send more ties generally. These mechanisms may operate jointly, and then their effects will be confounded. We present a specification representing these effects simultaneously by a four-parameter quadratic function of the values of sender and receiver. Flexibility can be increased by a five-parameter extension. We argue that for numerical actor attributes having important effects on directed networks, these specifications may provide an improvement. An illustration is given of dependence of advice ties on academic grades, analyzed by the Stochastic Actor-oriented Model.

Vision-Related Quality of Life in Keratoconus: A Save Sight Keratoconus Registry Study.

To assess vision-related quality of life using the Impact of Vision Impairment Questionnaire (IVI) in patients with keratoconus enrolled in the Save Sight Keratoconus Registry. In this cross-sectional study, data on 107 keratoconic patients were collected through a prospectively designed web-based registry from a quaternary referral eye hospital and 2 corneal subspecialty practices. Vision-related quality of life was evaluated using the IVI. Rasch analysis was used to transform the IVI responses into interval-level measures comprising reading, mobility, and emotional well-being subscales. Associations between best-corrected visual acuity (BCVA), maximum simulated keratometry (Kmax), steep keratometry (K2), and pachymetry for each eye and IVI subscale scores were evaluated with univariate (Pearson correlations) and multivariable regression adjusted for age and gender. Of the 107 patients, 37 (34.5%), 41 (38.0%) and 29 (26.9%) had mild, moderate, and severe keratoconus, respectively. On uni- and multivariable analysis, BCVA in the better eye had the strongest association with reading [r = 0.51; 95% confidence interval (CI), 0.35-0.64, P = 0.004] and mobility (r = 0.55; 95% CI, 0.41-0.67, P < 0.001) subscale scores. BCVA in the better and worse eye, both had the joint strongest associations with emotional scores on univariate analysis, but only the latter was significant on multivariable analysis (r = 0.37; 95% CI, 0.20-0.53, P < 0.001). K2 and Kmax in the better eye also displayed significant associations with reading and mobility scores. In patients with keratoconus, BCVA in the better eye had the strongest correlation with reading and mobility scores, whereas BCVA in the worse eye was significantly correlated with emotional scores.

Scaling properties of pain intensity ratings in paediatric populations using the Faces Pain Scale-revised: Secondary analyses of published data based on the item response theory

BackgroundThe Faces Pain Scale-revised (FPS-r) has been developed as an interval scale. For other pain measurement instruments, several studies found evidence for and against an interval level of measurement. ObjectivesThe primary aim of the current study was to evaluate the scale properties of the FPS-r using an item response theory approach. DesignSecondary analysis of published data. SettingThree studies; Study 1 and study 2: One university hospital; Study 3: international pain registry. ParticipantsStudy 1: n = 246, female: 41%, age: 11–18 years, 3 pain items; Study 2: n = 240, female: 43%, age: 11–18 years, 9 pain items; Study 3: n = 2266, female: 41%, age: 4–18 years, 3 pain items. MethodsThe rating scale model (interval scale), the graded response model (no interval scale, ordered response categories) and the partial credit model (no interval scale) were used to scale the data. ResultsIn all three studies, the rating scale model was outperformed by the graded response model or the partial credit model in terms of model fit. Overlapping response categories were found in items associated with less pain. Response category widths were wider for categories associated with low pain intensity and smaller for categories associated with high pain intensities. Smallest response categories were 1%–67% smaller compared to the widest response category of the same item. ConclusionAccording to these findings, the interval scale properties of the FPS-r may be questioned. Item response theory methods may help to solve the problem of missing linearity in pain intensity ratings using FPS-r.

Impact of Incidence and Progression of Diabetic Retinopathy on Vision-Specific Functioning

To investigate the independent impact of the incidence and progression of diabetic retinopathy (DR) on visual functioning (VF). Population-based cohort study. A total of 518 participants aged 40 to 80 years (baseline visit 2007-2009 and second visit 6 years later, 2013-2015), with diabetes, clinical data, and VF information at both visits. VF-7 scores, converted to interval-level person measures (in logits) using Rasch analysis. Incident DR was defined using the Modified Airlie House classification as "none or minimal" DR at baseline and at least mild nonproliferative DR at follow-up; incident vision-threatening DR (VTDR; severe nonproliferative DR, proliferative DR, and/or clinically significant macular edema) as no VTDR at baseline, and present at follow-up; and DR progression as at least a 1-step worsening in DR at follow-up from mild or worse status at baseline. The longitudinal associations between incident DR, VTDR, and DR progression, as well as change in composite and individual item scores of VF, were assessed using multivariable linear regression models. Of the 518 participants (mean age ± standard deviation [SD] 59.8±9.0 years; 47.7% female), 42 (9.8%), 14 (2.8%), and 32 (42.7%) had incident DR, incident VTDR, and DR progression, respectively, at follow-up. In models adjusting for traditional confounders, persons with incident DR and VTDR had a 13.7% (β=-0.60; 95% confidence interval [CI],-0.96 to -0.24; P= 0.001) and 23% (β=-1.00; 95% CI,-1.61 to-0.38; P= 0.001) reduction in mean VF scores at follow-up. Furthermore, individuals with incident DR had similar independent reductions in scores for 7 individual items of the VF-7, whereas those with incident VTDR had the largest reductions for activities like cooking (31%; P= 0.003), reading the newspaper (29.6%; P < 0.001), and seeing street signs (28%, P= 0.001) at follow-up. Progression of DR was not independently associated with change in overall VF (β=-0.18; 95% CI,-1.00, 0.64; P= 0.660). Incident DR, particularly vision-threatening stages, has a substantial negative impact on people's overall vision-dependent functioning and specific activities such as cooking, seeing street signs, and reading the newspaper. Our findings reinforce the need for strategies to prevent or delay the development of DR.

Using modern methods for missing data analysis with the social relations model: A bridge to social network analysis

Social network analysis identifies social ties, and perceptual measures identify peer norms. The social relations model (SRM) can decompose interval-level perceptual measures among all dyads in a network into multiple person- and dyad-level components. This study demonstrates how to accommodate missing round-robin data using Bayesian data augmentation, including how to incorporate partially observed covariates as auxiliary correlates or as substantive predictors. We discuss how data augmentation opens the possibility to fit SRM to network ties (potentially without boundaries) rather than round-robin data. An illustrative application explores the relationship between sorority members’ self-reported body comparisons and perceptions of friends’ body talk.

Development of the Hand Assessment for Infants: evidence of internal scale validity.

The aim of this study was to develop a descriptive and evaluative assessment of upper limb function for infants aged 3 to 12 months and to investigate its internal scale validity for use with infants at risk of unilateral cerebral palsy. The concepts of the test items and scoring criteria were developed. Internal scale validity and aspects of reliability were investigated on the basis of 156 assessments of infants at 3 to 12 months corrected age (mean 7.2mo, SD 2.5) with signs of asymmetric hand use. Rasch measurement model analysis and non-parametric statistics were used. The new test, the Hand Assessment for Infants (HAI), consists of 12 unimanual and five bimanual items, each scored on a 3-point rating scale. It demonstrated a unidimensional construct and good fit to the Rasch model requirements. The excellent person reliability enabled person separation to six significant ability strata. The HAI produced an interval-level measure of bilateral hand use as well as unimanual scores of each hand, allowing a quantification of possible asymmetry expressed as an asymmetry index. The HAI can be considered a valid assessment tool for measuring bilateral hand use and quantifying side difference between hands among infants at risk of developing unilateral cerebral palsy. The Hand Assessment for Infants (HAI) measures the use of both hands and quantifies a possible asymmetry of hand use. HAI is valid for infants at 3 to 12 months corrected age at risk of unilateral cerebral palsy.

Inter-relationship between visual symptoms, activity limitation and psychological functioning in patients with diabetic retinopathy

AimsWe explored the direct and indirect impact of restrictions in daily living activities on the relationship between perceived visual symptoms associated with diabetic retinopathy (DR) and psychological functioning.MethodsIn this prospective,...

Impact of type I Boston keratoprosthesis implantation on vision-related quality of life

AimTo determine the impact of type I Boston keratoprosthesis (KPro) implantation on vision-related quality of life (VRQoL).MethodsProspective study in 33 patients (mean age 56±12 years, 67% male) with bilateral corneal...

Evaluation of a guided continuous quality improvement program in community pharmacies

BackgroundThe importance of creating and sustaining a strong culture of patient safety has been recognized as a critical component of safe medication use. This study aims to assess changes in attitudes toward patient safety culture and frequency of quality-related event (QRE) reporting after guided implementation of a continuous quality improvement (CQI) program in a panel of community pharmacies in the United States (U.S.).MethodsTwenty-one community pharmacies volunteered to participate in the project and were randomly assigned to intervention or control groups. Pharmacy staff in the intervention group received guided training to ensure full implementation of a CQI program while those in the control group partially implemented the program. Pharmacy staff in both groups completed retrospective pre-post safety culture questionnaires and reported medication errors and near misses that occurred in their practices. Rasch analysis was applied to assess questionnaire validity and reliability and to confirm if the ordinal level data approximated interval level measures. Paired t-tests and repeated measure analysis of covariance tests were subsequently used to compare observed changes in the attitudes of subjects and frequency of QREs reporting in intervention and control groups.ResultsSixty-nine employees completed the questionnaire, a 43.9% response rate. Improvement in attitudes toward patient safety was statistically significant in the intervention group in six domains: staff, training, and skill (p = 0.017); patient counseling (p = 0.043); communication about mistakes (p < 0.001); response to mistakes (p < 0.001); organizational learning – continuous improvement (p < 0.001); and overall patient safety perceptions (p = 0.033). No significant differences were observed in QRE reporting rates between intervention and control groups. However, differences were observed in the types of QREs reported (e.g., incorrect safety cap) and the point in the prescription processing workflow where a QRE was detected (e.g., partner check station, and drug utilization review station) in the intervention group (p < 0.001).ConclusionGuided CQI program implementation increased the self-reported patient safety culture attitudes among staff.

Measurement of the severity of disability in community-dwelling adults and older adults: interval-level measures for accurate comparisons in large survey data sets

ObjectivesTo (1) create a single metric of disability using Rasch modelling to be used for comparing disability severity levels across groups and countries, (2) test whether the interval-level measures were...

Study of the effectiveness of laughter yoga on the symptom checklist (SCL-90-R) of Youths suffering from Trichotillomania (Hair-pulling disorder)

Everyone has heard the adage that ‘Laughter is the best medicine’ or ‘Laughter is the incurable pain medication‘. Laughter has been associated with a number of physiological and psychological benefits. Laughter yoga (LY) is a contemporary technique that encourages participants to mimic the act of laughing, with the goal of achieving positive psychological outcomes. The study intended to evaluate the effectiveness of laughter yoga on the symptom checklist (SCL-90-R) of youths suffering from Trichotillomania (Hair-pulling disorder). Mached pairs or case control study design. The statistical method is a Paired samples T-test (Quantitative variables, interval level of measurement). Data analysis was down with using Version IBM SPSS Statistics study done in Tehran laughter yoga centers. The target population includes all youths (girls and boys) ages between 14 to 20 that suffering from Trichotillomania (TTM) that participating in Tehran laughter yoga centers's classes in between November 2014 to February 2015. Laughter yoga is done in groups, with eye contact and playfulness between participants that received 8 weeks LY (3 sessions per week, each session; 45 minutes). The findings showed a significant difference in the mean scores of before and after laughter Yoga intervention in the group of youths suffering from Trichotillomania (Hair-pulling disorder). The findings showed that laughter Yoga had a positive effect on reducing the symptom checklist (SCL-90-R) of youths suffering from Trichotillomania (Hair-pulling disorder) in 8 weeks (3 sessions per week, each session; 45 minutes).

Uma análise funcional da Wong-Baker Faces Pain Rating Scale: linearidade, discriminabilidade e amplitude

Background: Self-report measures of pain intensity are often treated as interval level measures, which is a rarely tested assumption. Objectives: To assess...

A Rasch analysis of patients' opinions of primary health care professionals' ethical behaviour with respect to communication issues.

Patients' opinions are crucial in assessing the effectiveness of the ethical theories which underlie the care relationship between patients and primary health care professionals. To study the ethical behaviour of primary health care professionals with respect to communication issues according to patients' opinions. Cross-sectional study using a self-administered questionnaire in patients from a network of 15 urban primary health centres. Participants were patients attended at the centres when the study was conducted. We used a Rasch analysis to verify the structure of the 17 questionnaire items, and to calculate interval level measures for patients and items. We analysed differences according to patient subgroups using analysis of variance tests and differences between the endorsement of each item. We analysed 1013 (70.34%) of questionnaires. Data fit to the Rasch model was achieved after collapsing two categories and eliminating five items. Items with the lowest degree of endorsement were related to the management of differences in conflictive situations between patients and health care professionals. We found significant differences (P < 0.001) in patients' opinions according to the degree of confidence in professionals and their educational level. Patients opined that empathy and traditional communication skills were respected by family physicians and nurses. However, opinions on endorsement were lower when patients disagreed with health care professionals. The differences found between patient subgroups demonstrated the importance of trust and confidence between patients and professionals.