Errors-in-variables models in high-dimensional settings pose two challenges in application. First, the number of observed covariates is larger than the sample size, while only a small number of covariates are true predictors under an assumption of model sparsity. Second, the presence of measurement error can result in severely biased parameter estimates, and also affects the ability of penalized methods such as the lasso to recover the true sparsity pattern. A new estimation procedure called SIMulation-SELection-EXtrapolation (SIMSELEX) is proposed. This procedure makes double use of lasso methodology. First, the lasso is used to estimate sparse solutions in the simulation step, after which a group lasso is implemented to do variable selection. The SIMSELEX estimator is shown to perform well in variable selection, and has significantly lower estimation error than naive estimators that ignore measurement error. SIMSELEX can be applied in a variety of errors-in-variables settings, including linear models, generalized linear models, and Cox survival models. It is furthermore shown in the Supporting Information how SIMSELEX can be applied to spline-based regression models. A simulation study is conducted to compare the SIMSELEX estimators to existing methods in the linear and logistic model settings, and to evaluate performance compared to naive methods in the Cox and spline models. Finally, the method is used to analyze a microarray dataset that contains gene expression measurements of favorable histology Wilms tumors.
Perceptual studies of timbre semantics have revealed certain consistencies in the linguistic conceptualization of acoustic attributes. In the standard experimental paradigm, participants hear timbral stimuli and provide behavioral responses. However, it remains unclear the extent to which descriptive consistency would be observed if this paradigm were reversed, that is, if participants were instructed to create novel timbres in response to target adjectives. Given an unfamiliar synthesis interface, would musically trained participants craft similar timbral profiles for the same familiar adjectives? In this study, we explore timbre semantics using a novel frequency modulation (FM) synthesis production task. Participants (N = 64) created unique timbral outputs in response to 20 common timbre descriptors drawn from orchestration treatises (e.g., brilliant, dull, harsh). Acoustic analyses of the resultant 1,280 signals, in conjunction with linear mixed-effects modeling and clustering analysis, indicate that participants were moderately consistent in their timbral creations. Word valence and arousal interacted to influence average spectral centroid and noisiness. Specifically, clearly positive and negative words produced significantly different acoustical profiles than more affectively neutral words. This result confirms a number of findings from the perceptual literature while offering preliminary evidence that affective dimensions of timbre semantics systematically influence sound production in an unfamiliar context.
Musical timbre is often described using terms from non-auditory senses, mainly vision and touch; but it is not clear whether crossmodality in timbre semantics reflects multisensory processing or simply linguistic convention. If multisensory processing is involved in timbre perception, the mechanism governing the interaction remains unknown. To investigate whether timbres commonly perceived as “bright-dark” facilitate or interfere with visual perception (darkness-brightness), we designed two speeded classification experiments. Participants were presented consecutive images of slightly varying (or the same) brightness along with task-irrelevant auditory primes (“bright” or “dark” tones) and asked to quickly identify whether the second image was brighter/darker than the first. Incongruent prime-stimulus combinations produced significantly more response errors compared to congruent combinations but choice reaction time was unaffected. Furthermore, responses in a deceptive identical-image condition indicated subtle semantically congruent response bias. Additionally, in Experiment 2 (which also incorporated a spatial texture task), measures of reaction time (RT) and accuracy were used to construct speed-accuracy tradeoff functions (SATFs) in order to critically compare two hypothesized mechanisms for timbre-based crossmodal interactions, sensory response change vs. shift in response criterion. Results of the SATF analysis are largely consistent with the response criterion hypothesis, although without conclusively ruling out sensory change.
The major problem associated with phase-behavior matching with a cubic equation of state is the selection of regression parameters. There are many parameters that can be selected as the best set of parameters, and therefore a dynamic parameter-solution scheme is desired to avoid tedious and time-consuming trial-and-error regression runs. This paper proposes a regression technique where the most significant parameters are selected from a large set of parameters during the regression process. This reduces the regression effort considerably and alleviates the problem associated with the a priori selection of regression parameters. The success of the technique is demonstrated by matching the experimental data for a light oil and a gas condensate. Introduction It is well known that cubic equations of state (EOS) will not generally predict accurately laboratory data of oil/gas mixtures without the tuning of the EOS parameters (Coats and Smart, 1986). It has often been the practise to adjust the properties of the components (usually the heavy fractions), e.g. Pc, Tc, Ï? etc., to fit the experimental data. The objective function in the regression involves the solution of complex nonlinear equations such as flash and saturation-pressure calculations. A robust minimization method is therefore required for rapid convergence to the minimum. In this report a modification of the adaptive least-squares algorithm of Dennis et al (1981) is used. The modification involves the use of some other nonlinear optimization concepts on direction and step-size selection due to Chen and Stadtherr (1981).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.