RESUMEN
Pooling information from multiple, independent studies (meta-analysis) adds great value to medical research. Random effects models are widely used for this purpose. However, there are many different ways of estimating model parameters, and the choice of estimation procedure may be influential upon the conclusions of the meta-analysis. In this paper, we describe a recently proposed Bayesian estimation procedure and compare it with a profile likelihood method and with the DerSimonian-Laird and Mandel-Paule estimators including the Knapp-Hartung correction. The Bayesian procedure uses a non-informative prior for the overall mean and the between-study standard deviation that is determined by the Berger and Bernardo reference prior principle. The comparison of these procedures focuses on the frequentist properties of interval estimates for the overall mean. The results of our simulation study reveal that the Bayesian approach is a promising alternative producing more accurate interval estimates than those three conventional procedures for meta-analysis. The Bayesian procedure is also illustrated using three examples of meta-analysis involving real data. Copyright © 2016 John Wiley & Sons, Ltd.
Asunto(s)
Teorema de Bayes , Metaanálisis como Asunto , Acupuntura Auricular , Bioestadística , Simulación por Computador , Intervalos de Confianza , Humanos , Funciones de Verosimilitud , Modelos Estadísticos , Infecciones del Sistema Respiratorio/prevención & control , Stents/efectos adversosRESUMEN
DC-magnetoencephalography (DC-MEG) technique has been refined and allows to record cortical activity in the infraslow frequency range less than 0.1 Hz noninvasively. Important questions however, remained, especially, how specific these infraslow activations can be recorded and whether different activations, for example, motor versus acoustic, can be separated. To clarify these questions, in the present DC-MEG study, cortical infraslow activity was investigated intraindividually in response to different activation modalities, that is, motor versus acoustic: in 13 individuals, 30-s periods of finger movement or listening to concert music, were interleaved for 60 min. DC-MEG was capable to resolve intermodal differences concerning the relative amplitudes, field patterns, and source localizations. These results clarify that DC-MEG allows to identify and to discriminate modality-specific infraslow cortical neuronal signals.
Asunto(s)
Mapeo Encefálico/métodos , Encéfalo/fisiología , Magnetoencefalografía , Estimulación Acústica , Adulto , Femenino , Humanos , Masculino , Actividad Motora/fisiología , Adulto JovenRESUMEN
The compensation of LTI systems and the evaluation of the according uncertainty is of growing interest in metrology. Uncertainty evaluation in metrology ought to follow specific guidelines, and recently two corresponding uncertainty evaluation schemes have been proposed for FIR and IIR filtering. We employ these schemes to compare an FIR and an IIR approach for compensating a second-order LTI system which has relevance in metrology. Our results suggest that the FIR approach is superior in the sense that it yields significantly smaller uncertainties when real-time evaluation of uncertainties is desired.
Asunto(s)
Modelos Teóricos , Incertidumbre , Sistemas de Computación , Pesos y Medidas/normasRESUMEN
Two methods for single-trial analysis were compared, an established parametric template approach and a recently proposed non-parametric method based on complex bandpass filtering. The comparison was carried out by means of pseudo-real simulations based on magnetoencephalography measurements of cortical responses to auditory signals. The comparison focused on amplitude and latency estimation of the M100 response. The results show that both methods are well suited for single-trial analysis of the auditory evoked M100. While both methods performed similarly with respect to latency estimation, the non-parametric approach was observed to be more robust for amplitude estimation. The non-parametric approach can thus be recommended as an additional valuable tool for single-trial analysis.
Asunto(s)
Algoritmos , Diagnóstico por Computador/métodos , Electroencefalografía/métodos , Potenciales Evocados Auditivos/fisiología , Procesamiento de Señales Asistido por Computador , Funciones de Verosimilitud , Reproducibilidad de los Resultados , Tamaño de la Muestra , Sensibilidad y EspecificidadRESUMEN
A semi-parametric approach for the quantitative analysis of magnetic resonance (MR) spectra is proposed and an uncertainty analysis is given. Single resonances are described by parametric models or by parametrized in vitro spectra and the baseline is determined nonparametrically by regularization. By viewing baseline estimation in a reproducing kernel Hilbert space, an explicit parametric solution for the baseline is derived. A Bayesian point of view is adopted to derive uncertainties, and the many parameters associated with the baseline solution are treated as nuisance parameters. The derived uncertainties formally reduce to Cramér-Rao lower bounds for the parametric part of the model in the case of a vanishing baseline. The proposed uncertainty calculation was applied to simulated and measured MR spectra and the results were compared to Cramér-Rao lower bounds derived after the nonparametrically estimated baselines were subtracted from the spectra. In particular, for high SNR and strong baseline contributions the proposed procedure yields a more appropriate characterization of the accuracy of parameter estimates than Crémer-Rao lower bounds, which tend to overestimate accuracy.
Asunto(s)
Química Encefálica , Espectroscopía de Resonancia Magnética/métodos , Modelos Estadísticos , Procesamiento de Señales Asistido por Computador , Teorema de Bayes , Simulación por Computador , Humanos , Análisis de los Mínimos CuadradosRESUMEN
To assess the applicability of magnetic resonance spectroscopy (MRS) for long-term follow-up of neurological diseases a longitudinal 1H-MRS study at 3 T was carried out on ten patients having relapsing-remitting multiple sclerosis (MS) who, after baseline examination, received interferon-beta (IFN) 1b. At 8-20 examinations within up to 34 months absolute concentrations of N-acetylaspartate (NAA), total creatine (tG), and choline-containing compounds (tCho) were determined in a large non-enhancing lesion and contralateral normal appearing white matter (NAWM). MR spectra were analyzed using a novel time domain-frequency domain method including non-parametric background characterization. For comparison at baseline, ten healthy controls were examined. The concentrations of tCho and tCr were found to be higher in MS brain than in control brain. Besides a non-significantly lower NAA concentration in lesions there were no concentration differences between lesions and NAWM. Over the follow-up period the measured metabolite concentrations exhibited a high variability. Most concentrations remained within this scatter, and statistical tests revealed significant fluctuations in the levels of metabolites in one case only. This stability of the metabolite concentrations over time might result from IFN therapy as for the spontaneous course of relapsing-remitting MS decreasing metabolite (NAA/tCr) ratios have been reported. The results further suggest that future treatment trials intending to use metabolite concentrations as a secondary outcome indicator use even longer observation periods and, besides group analysis of large cohorts, investigate the time behavior of selected single cases. The biochemical abnormalities found in NAWM emphasize the importance of analyzing both lesion and NAWM.