An unsupervised one-class-classifier support vector machine to simultaneously monitor location and scale of multivariate quality characteristics

PurposeThe purpose of this study is to propose an effective unsupervised one-class-classifier (OCC) support vector machine (SVM)-based single multivariate control chart (OCC-SVM) to simultaneously monitor “location” and “scale” shifts of a manufacturing process.Design/methodology/approachThe step-by-step approach to developing, implementing and fine-tuning the intrinsic parameters of the OCC-SVM chart is demonstrated based on simulation and two real-life case examples.FindingsA comparative study, considering varied known and unknown response distributions, indicates that the OCC-SVM is highly effective in detecting process shifts of samples with individual observations. OCC-SVM chart also shows promising results for samples with a rational subgroup of observations. In addition, the results also indicate that the performance of OCC-SVM is unaffected by the small reference sample size.Research limitations/implicationsThe sample responses are considered identically distributed with no significant multivariate autocorrelation between sample observations.Practical implicationsThe proposed easy-to-implement chart shows satisfactory performance to detect an out-of-control signal with known or unknown response distributions.Originality/valueVarious multivariate (e.g. parametric or nonparametric) control chart(s) are recommended to monitor the mean (e.g. location) and variance (e.g. scale) of multiple correlated responses in a manufacturing process. However, real-life implementation of a parametric control chart may be complex due to its restrictive response distribution assumptions. There is no evidence of work in the open literature that demonstrates the suitability of an unsupervised OCC-SVM chart to simultaneously monitor “location” and “scale” shifts of multivariate responses. Thus, a new efficient OCC-SVM single chart approach is proposed to address this gap to monitor a multivariate manufacturing process with unknown response distributions.

Repeated measures discriminant analysis using multivariate generalized estimation equations

Discriminant analysis procedures that assume parsimonious covariance and/or means structures have been proposed for distinguishing between two or more populations in multivariate repeated measures designs. However, these procedures rely on the assumptions of multivariate normality which is not tenable in multivariate repeated measures designs which are characterized by binary, ordinal, or mixed types of response distributions. This study investigates the accuracy of repeated measures discriminant analysis (RMDA) based on the multivariate generalized estimating equations (GEE) framework for classification in multivariate repeated measures designs with the same or different types of responses repeatedly measured over time. Monte Carlo methods were used to compare the accuracy of RMDA procedures based on GEE, and RMDA based on maximum likelihood estimators (MLE) under diverse simulation conditions, which included number of repeated measure occasions, number of responses, sample size, correlation structures, and type of response distribution. RMDA based on GEE exhibited higher average classification accuracy than RMDA based on MLE especially in multivariate non-normal distributions. Three repeatedly measured responses namely severity of epilepsy, current number of anti-epileptic drugs, and parent-reported quality of life in children with epilepsy were used to demonstrate the application of these procedures.

Research on the efficiency of single-wire power transmission

With the development of related theoretical research on Single Wire Power Transfer(SWPT), the SWPT system has demonstrated its advantages in a variety of special environments. In this paper, the influence of capacitance and inductance on transmission efficiency is studied in order to improve the transmission efficiency of swpt system. This article simplifies and analyzes the circuit model of the SWPT system. It can be found that the system is a second-order circuit, and its response distribution trend conforms to the Gaussian function distribution. There should be an optimal ratio between the capacitor and the inductance to maximize the circuit response. Through the influence of different capacitance, inductance, and transmission distance on transmission efficiency, multiple sets of experiments and simulations are carried out. The experiment found that the capacitance, inductance, and transmission efficiency are in accordance with the Gaussian non-normal distribution, and the acquired data is fitted by the Gaussian function. The average relative error of the fitting is less than 1% under different transmission distances, which can be better reflect the relationship between the three. The study of single-wire power transmission system will provide a key reference for wireless power transmission.

The HDR CARE Scale, Inpatient Version: A validated survey instrument to measure environmental affordance for nursing tasks in inpatient healthcare settings

Rigorous healthcare design research is critical to inform design decisions that improve human experience. Current limitations in the field include a lack of consistent and valid measures that provide feedback about the role of the built environment in producing desirable outcomes. Research findings about nurses’ efficiency, quality of care, and satisfaction related to inpatient unit designs have been mixed, and there was previously no validated instrument available to quantitatively measure nurses’ ability to work efficiently and effectively in their environment. The objective of this study was to develop, refine, and validate a survey instrument to measure affordance of the care environment to nurse practice, based on various aspects of their work in inpatient units. The HDR Clinical Activities Related to the Environment (CARE) Scale Inpatient Version was developed using item design, refinement, and reliability and validity testing. Psychometric methods from classical test theory and item response theory, along with statistical analyses involving correlations and factor analysis, and thematic summaries of qualitative data were conducted. The four-phase process included (1) an initial pilot study, (2) a content validation survey, (3) cognitive interviews, and (4) a final pilot study. Results from the first three phases of analysis were combined to inform survey scale revisions before the second pilot survey, such as a reduction in the number and rewording of response options, and refinement of scale items. The updated 9-item scale showed excellent internal consistency and improved response distribution and discrimination. The factor analysis revealed a unidimensional measure of nurse practice, as well as potential subscales related to integration, efficiency, and patient care. Within the healthcare design industry, this scale is much needed to generate quantitative and standardized data and will facilitate greater understanding about the aspects of an inpatient healthcare facility that best support nurses’ ability to provide quality patient care.

Romance N Prep N constructions in visual word recognition

N Prep N constructions such as Sp. bicicleta de montaña ‘mountain bike’ are very productive and frequent in Romance languages. They commonly have been classified as syntagmatic compounds that show no orthographic union and exhibit an internal structure that resembles free syntactic structures, such as Sp. libro para niños ‘book for children’. There is no consensus on how to best distinguish lexical from syntactic N Prep N constructions. The present paper presents an explorative eye-tracking study on N Prep N constructions, varying both lexical type (lexical vs. syntactic) and preposition across three languages, French, Spanish and Portuguese. The task of the eye-tracking study was a reading aloud paradigm of the constructions in sentence context. Constructions were fixated on less when more frequent, independent of lexical status. There was also modest evidence that a higher construction frequency afforded shorter total fixation durations, but only for lower deciles of the response distribution. The (construction-initial) head noun also received fewer fixations as construction frequency increased, and also when the head noun was more frequent. The second fixation durations on the head noun also revealed an effect of lexical status, with syntactic constructions receiving shorter fixations at the 5th and 7th deciles. The probability of a fixation on the preposition decreased with preposition frequency, but first fixations on the preposition increased with preposition frequency. The prepositions of Portuguese, the language with the richest inventory of prepositions, received more fixations than the prepositions of French and Spanish. The observed pattern of results is consistent with models of lexical processing in which reading is guided by knowledge of both higher-level constructions and knowledge of key constituents such as the head noun and the preposition.

Comparing the monetary value of a quality-adjusted life year from the payment card and the open-ended format

Background The payment card (PC) format and the open-ended (OE) format are common methods in eliciting willingness-to-pay (WTP) of one additional quality-adjusted life year (QALY). The aim of this research is to compare these two formats in eliciting the monetary value of a QALY. Methods A contingent valuation survey was carried out using a pre-designed questionnaire with various hypothetical scenarios. The difference between the PC and the OE formats was evaluated by a two-sample equality test. Furthermore, generalized linear models were carried out to control observed heterogeneity and to test theoretical validity. Results In total, 461 individuals were involved, among whom 235 (51%) answered the PC question, while 226 (49%) answered the OE question. Excluding zero response, the mean WTP values of these two formats for different scenarios varied dramatically, which was from 13,278 to 280,177 RMB for the PC, 18,119 to 620,913 RMB for the OE. The OE format tended to elicit lower values for less serious condition and higher values for more serious condition. However, equality test of mean and median demonstrated insignificant difference of these two formats for all scenarios. For both OE and PC format, most variables were found to have significant effect on the value of WTP/QALY. Moreover, joint estimation indicated a statistically significant positive effect on the OE results. Further analysis demonstrated that the imbalanced zero response distribution caused the main difference of these two formats. Conclusions This research indicated insignificantly different WTP/QALY estimates of the PC format and OE format with the grouped data whereas significantly higher estimates of the OE format from the pooled data. These two formats were found to be valid. More research about the difference and the validity of various WTP eliciting methods would be recommended for a robust estimation of WTP/QALY.

Translation and psychometric evaluation of the German version of the IcanSDM measure – a cross-sectional study among healthcare professionals

Background Shared decision-making (SDM) between patients and healthcare professionals (HCPs) is a key component of patient-centred care. To implement SDM in clinical practice and to evaluate its effects, it is helpful to know about HCPs’ perception of SDM barriers. The measure IcanSDM was developed in Canada and assesses the perception of SDM barriers. To our knowledge, no equivalent measure exists in German. Therefore, the aim of this study was to translate and adapt the IcanSDM measure to be used by a German speaking population and evaluate its psychometric properties. Methods This is a cross-sectional psychometric study based on a secondary analysis of baseline data from a SDM implementation study. The original 8-item IcanSDM was translated into German using a team translation protocol. We assessed comprehensibility via cognitive interviews with n = 11 HCPs. Based on results of cognitive interviews, the translated IcanSDM version was revised. Two hundred forty-two HCPs filled out the measure. Psychometric analysis included acceptance (completion rate), item characteristics (response distribution, skewness, item difficulties, corrected item-total correlations, inter-item correlations), factorial structure (confirmatory factor analysis (CFA), model fit), and internal consistency (Cronbach’s α). Results We translated and adapted the German IcanSDM successfully except for item 8, which had to be revised after the cognitive interviews. Completion rate was 98%. Skewness of the items ranged between −.797 and 1.25, item difficulties ranged between 21.63 and 70.85, corrected item-total-correlations ranged between .200 and .475, inter-item correlations ranged between .005 and .412. Different models based on CFA results did not provide a valid factorial structure. Cronbach’s α ranged between .563 and .651 for different factor models. Conclusion We provide the first German measure for assessing perception of SDM barriers by HCPs. The German IcanSDM is a brief measure with good acceptance. However, we found unsatisfying psychometric properties, which were comparable to results of the original scale. In a next step, the IcanSDM should be further developed and modified and predictive validity should be evaluated.

Interactively visualizing distributional regression models with distreg.vis

A newly emerging field in statistics is distributional regression, where not only the mean but each parameter of a parametric response distribution can be modelled using a set of predictors. As an extension of generalized additive models, distributional regression utilizes the known link functions (log, logit, etc.), model terms (fixed, random, spatial, smooth, etc.) and available types of distributions but allows us to go well beyond the exponential family and to model potentially all distributional parameters. Due to this increase in model flexibility, the interpretation of covariate effects on the shape of the conditional response distribution, its moments and other features derived from this distribution is more challenging than with traditional mean-based methods. In particular, such quantities of interest often do not directly equate the modelled parameters but are rather a (potentially complex) combination of them. To ease the post-estimation model analysis, we propose a framework and subsequently feature an implementation in R for the visualization of Bayesian and frequentist distributional regression models fitted using the bamlss, gamlss and betareg R packages.