On the Difficulty of Measuring Forecasting Skill in Financial Markets

The use of correlation between forecasts and actual returns is commonplace in the literature, often used as a measurement of investors' skill. A prominent application of this is the concept of the information coefficient (IC). Not only can the IC be used as a tool to rate analysts and fund managers but it also represents an important parameter in the asset allocation and portfolio construction process. Nevertheless, a theoretical understanding of it has typically been limited to the partial equilibrium context where the investing activities of each agent have no effect on other market participants. In this paper we show that this can be an undesirable oversimplification and we demonstrate plausible circumstances in which conventional empirical measurements of IC can be highly misleading. We suggest that improved understanding of IC in a general equilibrium setting can lead to refined portfolio decision making ex ante and more informative analysis of performance ex post. Copyright © 2015 John Wiley & Sons, Ltd.     

Predicting Recessions with Leading Indicators: Model Averaging and Selection over the Business Cycle

Four methods of model selection—equally weighted forecasts, Bayesian model‐averaged forecasts, and two models produced by the machine‐learning algorithm boosting—are applied to the problem of predicting business cycle turning points with a set of common macroeconomic variables. The methods address a fundamental problem faced by forecasters: the most useful model is simple but makes use of all relevant indicators. The results indicate that successful models of recession condition on different economic indicators at different forecast horizons. Predictors that describe real economic activity provide the clearest signal of recession at very short horizons. In contrast, signals from housing and financial markets produce the best forecasts at longer forecast horizons. A real‐time forecast experiment explores the predictability of the 2001 and 2007 recessions. Copyright © 2015 John Wiley & Sons, Ltd.     

Gastrointestinal helminths of nine species of Cnemaspis (Squamata: Gekkonidae) from Peninsular Malaysia,one species from Cambodia and Thailand and two species from Vietnam

A total of 12 species of Cnemaspis (N = 104) from Southeast Asia were examined for gastrointestinal helminths. Samples consisted of nine species (n = 86) from Peninsular Malaysia: Cnemaspis affinis (n = 4); Cnemaspis baueri (n = 17); Cnemaspis biocellata (n = 12); Cnemaspis grismeri (n = 8); Cnemaspis kumpoli (n = 11); Cnemaspis limi (n = 9): Cnemaspis monachorum (n = 7); Cnemaspis pemanggilensis (n = 10); Cnemaspis peninsularis (n = 8); one species (n = 5) from Cambodia and Thailand, Cnemaspis chanthaburiensis (n = 5); and two species (n = 13) from Vietnam: Cnemaspis nuicamensis (n = 6) and Cnemaspis tucdupensis (n = 7). The aggregate helminth community consisted of one species of Cestoda, Cylindrotaenia malayi and nine species of Nematoda: Bakeria schadi, Meteterakis singaporensis, Parapharyngodon maplestoni, Maxvachonia sp., Physalopteroides sp., Physalopteridae gen. sp., Riticulariidae gen. sp., Seuratoidea gen. sp., Ascaridoidea gen. sp. Meteterakis singaporensis had the largest number of individuals (457) and greatest prevalence (24%). Twenty-eight new host records are reported.     

A new species of Schizopera (Copepoda: Harpacticoida) from Japan,its phylogeny based on the mtCOI gene and comments on the genus Schizoperopsis

The predominantly marine genus Schizopera Sars, 1905 has only two significant inland water species-flocks, one in the ancient African Lake Tanganyika and the other in subterranean waters of Western Australia. Discovery of Schizopera abei sp. nov. from several interstitial locations in the vicinity of the ancient Lake Biwa has wider implications for the study of morphological homoplasies in the genus, as well as for the study of freshwater invasions in harpacticoid copepods. The new Schizopera species belongs to a small group of congeners with a two-segmented endopod of the fourth leg, which used to be recognised as a separate genus, Schizoperopsis Apostolov, 1982. Our reconstructed phylogenies based on the mtCOI partial sequences suggest that this character probably evolved convergently in at least some Schizopera, thus rendering the genus Schizoperopsis polyphyletic. However, almost all basal nodes in our cladograms are weakly supported, which shows limitations of a single-gene approach for reconstructing phylogenetic relationships. The new species is the first member of its genus from Japanese inland waters, and it has no close relatives among extent congeners anywhere in the world. We speculate that its ancestor may have invaded Lake Biwa, and subsequently its surrounding subterranean waters, from brackish areas around central Japan, presumably during a period of high sea water level through its major outflow river. This discovery may provide further support for the hypothesis about the role of ancient lakes as biodiversity pumps for subterranean habitats.

http://zoobank.org/urn:lsid:zoobank.org:pub:1F71F7AD-B7C8-4AD3-BE44-5E1BEE4E2AA8     

Muhaka icipe,an enigmatic new genus and species of Kleidotomini (Hymenoptera: Figitidae: Eucoilinae) from an East African coastal forest

A remarkable new eucoiline genus and species, Muhaka icipe, is described herein. The genus is clearly a Kleidotomini, but is distinguished from other genera in the tribe by a unique head and scutellar morphology. The genus belongs to the ‘wedge-head’-syndrome group of species that, to date, is unique to Afrotropical eucoilines. The new genus and species is reminiscent of Stentorceps Quinlan and Nanocthulhu Buffington, but is readily distinguished from these genera. Muhaka was collected from a threatened kaya (sacred forest) of coastal Kenya. The biological importance of this and other kaya forests, as well as their protection, is discussed.

http://www.zoobank.org/urn:lsid:zoobank.org:pub:6918ED2C-69A4-48FC-A1E4-2B5DFF58E876     

探讨积分的极限

证明了若可积函数列{fn}在[a,b]上一致收敛,则nl→im∞∫abfn(x)dx中极限运算与积分运算可交换,从而揭示了"积分的极限"解法的内在本质,并且对于limn→∞∫01xnF(x)dx及nl→im∞∫ab[f(x)]ndx两种类型给出了更为具体有效的一般性解法.     

基于加权主成分分析和改进密度峰值聚类的协同训练算法

[目的]针对协同训练算法在视图分割时未考虑噪声影响和两视图分类器对无标记样本标注不一致问题,提出了基于加权主成分分析和改进密度峰值聚类的协同训练算法.[方法]首先引入加权主成分分析对数据进行预处理,通过寻求初始有标记样本中特征和类标记之间的依赖关系求得各特征加权系数,再对加权变换后的数据进行降维并提取高贡献度特征进行视...