Bayesian Regularization for Normal Mixture Estimation and Model-Based Clustering

Normal mixture models are widely used for statistical modeling of data, including cluster analysis. However maximum likelihood estimation (MLE) for normal mixtures using the EM algorithm may fail as the result of singularities or degeneracies. To avoid this, we propose replacing the MLE by a maximum a posteriori (MAP) estimator, also found by the EM algorithm. For choosing the number of components and the model parameterization, we propose a modified version of BIC, where the likelihood is evaluated at the MAP instead of the MLE. We use a highly dispersed proper conjugate prior, containing a small fraction of one observation's worth of information. The resulting method avoids degeneracies and singularities, but when these are not present it gives similar results to the standard method using MLE, EM and BIC.     

Metallothionein promotes regenerative axonal sprouting of dorsal root ganglion neurons after physical axotomy

Prior studies have reported that metallothionein I/II (MT) promote regenerative axonal sprouting and neurite elongation of a variety of central nervous system neurons after injury. In this study, we evaluated whether MT is capable of modulating regenerative axon outgrowth of neurons from the peripheral nervous system. The effect of MT was firstly investigated in dorsal root ganglion (DRG) explants, where axons were scratch-injured in the presence or absence of exogenous MT. The application of MT led to a significant increase in regenerative sprouting of neurons 16 h after injury. We show that the pro-regenerative effect of MT involves an interaction with the low-density lipoprotein receptor megalin, which could be blocked using the competitive antagonist RAP. Pre-treatment with the mitogen-activated protein kinase (MAPK) inhibitor PD98059 also completely abrogated the effect of exogenous MT in promoting axonal outgrowth. Interestingly, we only observed megalin expression in neuronal soma and not axons in the DRG explants. To investigate this matter, an in vitro injury model was established using Campenot chambers, which allowed the application of MT selectively into either the axonal or cell body compartments after scratch injury was performed to axons. At 16 h after injury, regenerating axons were significantly longer only when exogenous MT was applied solely to the soma compartment, in accordance with the localized expression of megalin in neuronal cell bodies. This study provides a clear indication that MT promotes axonal regeneration of DRG neurons, via a megalin- and MAPK-dependent mechanism.     

State-space models for predicting IBNR reserve in row-wise ordered runoff triangles: Calendar year IBNR reserves & tail effects

The issue of modeling and forecasting IBNR (incurred but not reported) actuarial reserve under Kalman filter techniques and extensions, using data arranged in a runoff triangle, is a frequent theme in the literature. One quite recent approach is to order the runoff triangle under a row-wise fashion and use linear state-space models for the resulting data set. To allow new possibilities for short-term IBNR reserves as well as to mitigate insolvency risk, in this paper we extend such a state-space method by: (i) a calendar year IBNR reserve prediction; and (ii) a tail effect for the row-wise ordered triangle. The extension is implemented with a real runoff triangle and compared with some traditional IBNR predictors. Empirical results indicate that the approach of this paper outperforms the competing methods in terms of out-of-sample comparisons and gives more conservative IBNR reserves than the original state-space method.     

Creativity,conservativeness & the social epistemology of science

The special issue Creativity, Conservatism & the Social Epistemology of Science collects six papers which, in different ways, tackle 'promotion questions' concerning scientific communities: which features shape those communities, and which might be changed to promote the kinds of epistemic features we desire. In this introduction, I connect these discussions with more traditional debate in the philosophy of science and reflect upon the notions of creativity which underwrite the papers.     

Ethnographic analogy,the comparative method,and archaeological special pleading

Ethnographic analogy, the use of comparative data from anthropology to inform reconstructions of past human societies, has a troubled history. Archaeologists often express concern about, or outright reject, the practice—and sometimes do so in problematically general terms. This is odd, as (or so I argue) the use of comparative data in archaeology is the same pattern of reasoning as the ‘comparative method’ in biology, which is a well-developed and robust set of inferences which play a central role in discovering the biological past. In pointing out this continuity, I argue that there is no ‘special pleading’ on the part of archaeologists in this regard: biologists must overcome analogous epistemic difficulties in their use of comparative data. I then go on to emphasize the local, empirically tractable ways in which particular ethnographic analogies may be licensed.     

Peripheral SMN restoration is essential for long-term rescue of a severe spinal muscular atrophy mouse model

Spinal muscular atrophy (SMA) is a motor neuron disease and the leading genetic cause of infant mortality; it results from loss-of-function mutations in the survival motor neuron 1 (SMN1) gene. Humans have a paralogue, SMN2, whose exon 7 is predominantly skipped, but the limited amount of functional, full-length SMN protein expressed from SMN2 cannot fully compensate for a lack of SMN1. SMN is important for the biogenesis of spliceosomal small nuclear ribonucleoprotein particles, but downstream splicing targets involved in pathogenesis remain elusive. There is no effective SMA treatment, but SMN restoration in spinal cord motor neurons is thought to be necessary and sufficient. Non-central nervous system (CNS) pathologies, including cardiovascular defects, were recently reported in severe SMA mouse models and patients, reflecting autonomic dysfunction or direct effects in cardiac tissues. Here we compared systemic versus CNS restoration of SMN in a severe mouse model. We used an antisense oligonucleotide (ASO), ASO-10-27, that effectively corrects SMN2 splicing and restores SMN expression in motor neurons after intracerebroventricular injection. Systemic administration of ASO-10-27 to neonates robustly rescued severe SMA mice, much more effectively than intracerebroventricular administration; subcutaneous injections extended the median lifespan by 25 fold. Furthermore, neonatal SMA mice had decreased hepatic Igfals expression, leading to a pronounced reduction in circulating insulin-like growth factor 1 (IGF1), and ASO-10-27 treatment restored IGF1 to normal levels. These results suggest that the liver is important in SMA pathogenesis, underscoring the importance of SMN in peripheral tissues, and demonstrate the efficacy of a promising drug candidate.