In this paper, we deal with the data-driven selection of multidimensional and possibly anisotropic bandwidths in the general framework of kernel empirical risk minimization. We propose a universal selection rule, which leads to optimal adaptive results in a large variety of statistical models such as nonparametric robust regression and statistical learning with errors in variables. These results are stated in the context of smooth loss functions, where the gradient of the risk appears as a good criterion to measure the performance of our estimators. The selection rule consists of a comparison of gradient empirical risks. It can be viewed as a nontrivial improvement of the so-called Goldenshluger–Lepski method to nonlinear estimators. Furthermore, one main advantage of our selection rule is the nondependency on the Hessian matrix of the risk, usually involved in standard adaptive procedures.

In this paper, we deal with the data-driven selection of multidimensional and possibly anisotropic bandwidths in the general framework of kernel empirical risk minimization. We propose a universal selection rule, which leads to optimal adaptive results in a large variety of statistical models such as nonparametric robust regression and statistical learning with errors in variables. These results are stated in the context of smooth loss functions, where the gradient of the risk appears as a good criterion to measure the performance of our estimators. The selection rule consists of a comparison of gradient empirical risks. It can be viewed as a nontrivial improvement of the so-called Goldenshluger–Lepski method to nonlinear estimators. Furthermore, one main advantage of our selection rule is the nondependency on the Hessian matrix of the risk, usually involved in standard adaptive procedures.

This paper considers the problem of defining distributions over graphical structures. We propose an extension of the hyper Markov properties of Dawid and Lauritzen [ Ann. Statist. 21 (1993) 1272–1317], which we term structural Markov properties , for both undirected decomposable and directed acyclic graphs, which requires that the structure of distinct components of the graph be conditionally independent given the existence of a separating component. This allows the analysis and comparison of multiple graphical structures, while being able to take advantage of the common conditional independence constraints. Moreover, we show that these properties characterise exponential families, which form conjugate priors under sampling from compatible Markov distributions.

In this article, we study a partially linear single-index model for longitudinal data under a general framework which includes both the sparse and dense longitudinal data cases. A semiparametric estimation method based on a combination of the local linear smoothing and generalized estimation equations (GEE) is introduced to estimate the two parameter vectors as well as the unknown link function. Under some mild conditions, we derive the asymptotic properties of the proposed parametric and nonparametric estimators in different scenarios, from which we find that the convergence rates and asymptotic variances of the proposed estimators for sparse longitudinal data would be substantially different from those for dense longitudinal data. We also discuss the estimation of the covariance (or weight) matrices involved in the semiparametric GEE method. Furthermore, we provide some numerical studies including Monte Carlo simulation and an empirical application to illustrate our methodology and theory.

Random forests are a learning algorithm proposed by Breiman [ Mach. Learn. 45 (2001) 5–32] that combines several randomized decision trees and aggregates their predictions by averaging. Despite its wide usage and outstanding practical performance, little is known about the mathematical properties of the procedure. This disparity between theory and practice originates in the difficulty to simultaneously analyze both the randomization process and the highly data-dependent tree structure. In the present paper, we take a step forward in forest exploration by proving a consistency result for Breiman’s [ Mach. Learn. 45 (2001) 5–32] original algorithm in the context of additive regression models. Our analysis also sheds an interesting light on how random forests can nicely adapt to sparsity.

We propose a roughness regularization approach in making nonparametric inference for generalized functional linear models. In a reproducing kernel Hilbert space framework, we construct asymptotically valid confidence intervals for regression mean, prediction intervals for future response and various statistical procedures for hypothesis testing. In particular, one procedure for testing global behaviors of the slope function is adaptive to the smoothness of the slope function and to the structure of the predictors. As a by-product, a new type of Wilks phenomenon [ Ann. Math. Stat. 9 (1938) 60–62; Ann. Statist. 29 (2001) 153–193] is discovered when testing the functional linear models. Despite the generality, our inference procedures are easy to implement. Numerical examples are provided to demonstrate the empirical advantages over the competing methods. A collection of technical tools such as integro-differential equation techniques [ Trans. Amer. Math. Soc. (1927) 29 755–800; Trans. Amer. Math. Soc. (1928) 30 453–471; Trans. Amer. Math. Soc. (1930) 32 860–868], Stein’s method [ Ann. Statist. 41 (2013) 2786–2819] [Stein, Approximate Computation of Expectations (1986) IMS] and functional Bahadur representation [ Ann. Statist. 41 (2013) 2608–2638] are employed in this paper.

加州劳工委员会(California Labor Commission)裁定，优步(Uber)司机应属于员工，而不是独立的承包商。该裁定可能会对按需经济造成重大影响。

UNHCR annual global trends survey finds a record 59.5m people were refugees, internally displaced or seeking asylum by the end of 2014

War, violence and persecution left one in every 122 humans on the planet a refugee, internally displaced or seeking asylum at the end of last year, according to a stark UN report that warns the world is failing the victims of an “age of unprecedented mass displacement”.

The annual global trends study by the UN’s refugee agency, UNHCR, finds that the level of worldwide displacement is higher than ever before, with a record 59.5 million people living exiled from their homes at the end of 2014.

From Beyoncé’s I Was Here video to #Kony2012, online campaigns are everywhere, shared in their millions. But does technology really amplify our humanity or is it all meaningless clicktivism? Warscapes reports

In the past, if you wanted to help out in times of tragedy you might travel to disaster zones or volunteer with a charity. But with the growth of online campaigning, the internet appears to offer the opportunity to change the world without leaving your lounge.

From Facebook to games and viral pop songs, digital initiatives reassure us that we don’t need to look up from our laptops or phones to help others in their time of need.

晚上，班主任查宿舍，突然发现墙角有几个烟头。

　班主任：来福，你作为宿舍长，老实告诉我，是谁偷偷抽烟了？

　来福：老师，其实，那些烟头是您这几天查宿舍时，抽完扔掉的。

　班主任脸上一红，随即镇定下来

　说：哦，我明白了，原来这几天你就没有安排打扫卫生啊！你作为宿舍长，现在罚你操场 跑 3000米！

　来福：……

If you want to remember, you must pay attention
… Use any and all these memory strategies:
o Repeat, visualize, associate and organize what you want to remember
o Write things down - keep a “to-do” list and written schedule
o Do one thing at a time

1
Heed this next statement: No matter how sharp a mind you may have, no one can remember everything. Therefore, don't beat yourself up trying. Learning to write things down helps.

2
Find and use a special talent. Everyone has some type of special talent. Be open to trying different things. You could find a hidden talent that you are not aware of. Do you learn from sound and voice pitch or from pictures?

3
Maintain a regular exercise program. It will help to relieve tension. Relieving tension alone can improve your thought patterns. The less tension that you have the sharper your mind will become. You will begin to develop a better attitude as time goes on. You should find a program that works for you.

4
Write through self-expression. Writing poetry can be relaxing plus it is a great way to express yourself. Not everyone writes poetry so find your own mode of self expression. Try sewing, playing a musical instrument, or gardening. Get a Diary and express your thoughts.

端午节快乐！

迷上了github

稍微折腾了一下，终于在github上建立了一个个人主页，可以存放任意需要的东西，总共300M，无限流量，很不错

Jason Day retains a strong chance of completing what would be one of the more astonishing major championship victories in recent times, with the Australian part of a four-way 54-hole lead at the US Open.

Day’s prospects of even seeing out this event were slim after he collapsed on the course towards the end of his second round. The world No10 was suffering from vertigo, which has troubled him with worrying routine.

The prime minister must not dance to the tune of his backbenchers at the Brussels summit
The phoney war is almost over. At the Brussels summit on Thursday and Friday, David Cameron will unveil his priorities on EU reform. He hopes to clinch a final deal in December – allowing an in/out referendum to be held in 2016, probably in the autumn. On his recent tour of European capitals, Cameron left the impression that he was serious about winning the referendum. I followed in his wake, and found many of those he had met keen to help him – but absorbed by other issues, such as Mediterranean boat-people and Ukraine’s problems.

The real possibility that Greece will leave the euro is a particular headache for Cameron: Grexit could lead to financial, political and humanitarian crises, distracting EU leaders from British concerns.

Multitasking products to streamline your beauty regime

The waiting list for St Tropez’s In Shower Lotion (￡14.50, boots.com) apparently had almost 9,000 names on it. Which tells you two things: a) the “pale and interesting” trend did not quite take, and b) people are desperate to never have to stand with their arms outstretched waiting for their elbows to dry. Fake tans are still hard work. Some are better than others, but even the good ones rely on at least half an hour of application. So a gradual tan you can apply in the shower and wash off after shampooing your hair is an idea that could transform your life/summer. I tried it. It works (in that gentle, layer it on over a few weeks way) and it doesn’t even filthy up your shower. And in those three minutes it takes to work, you can slap a treatment on your hair. Multitasking!

Drip brew systems are better for the environment but, if you really can’t do without your capsule, make sure you recycle it…
Email lucy.siegle@observer.co.uk with your ethical dilemma

The single-serve coffee pod is the hottest beverage invention since the kettle. In the US one in three households has a capsule machine, which explains the ubiquity of K-Cups, these are the pods made by US market leader Keurig, which sold 9.8bn K-Cups in 2014. UK coffee drinkers have awoken to the charms of single-serve pods, too. Here, Nespresso is the market leader and sales grew by 50% last year.

But the ubiquity of a single-use item that mixes organic waste (coffee), plastics and metals causes major eco-anxiety. Half a million viewers have watched Kill the K-Cup, a spoof disaster movie where spent capsules terrorise the planet. According to the haters, if last year’s spent coffee pods were taken out of landfills and lined up side by side, they’d wrap around the globe 10.5 times. Even the inventor of the pod, John Sylvan, has denounced them. They’ve been called the cigarette butts of the coffee industry. Ouch.

The use of high-throughput data to study the changing behaviour of biological pathways has focused mainly on examining the changes in the means of pathway genes. In this paper, we propose instead to test for changes in the co-regulated and unregulated variability of pathway genes. We assume that the eigenvalues of previously defined pathways capture biologically relevant quantities, and we develop a test for biologically meaningful changes in the eigenvalues between classes. This test reflects important and often ignored aspects of pathway behaviour and provides a useful complement to traditional pathway analyses.

由美国斯坦福大学、普林斯顿大学和伯克利大学研究人员参与的研究结果称，地球正在步入最新一轮的“大灭绝时期”，而人类将率先遭遇灭绝。参与研究的科学家们通过化石分析，对比了地球历史上脊椎动物灭绝率。研究指出，地球上脊椎动物灭绝率正迅急加速，结果发现，目前地球上脊椎动物的灭绝率已经超过正常地质时间段水平的114倍，达到以往大灭绝时期的水平。

有个国家手握3万亿美元海外净资产，去年净投资收益1700亿美元，这是日本。有一国家4.5万亿美元海外净负债，但去年净投资收益达2288亿美元，此即美国。世界上还有一国家，手握近两万亿美元海外净资产，但去年的净投资收益却是负298亿美元，这个国家是中国。

正当深港两地持续严打水货客之际，逾百名电动轮椅大军开始逐渐成为走私新势力。他们每天到上水领货后，将大袋水货挂在轮椅背，再乘港铁北上，经伤残人士优先通道过关，到深圳交货，全程“自动化”。有资深水货客透露，“轮椅水客”不乏四肢健全人士，有人更花钱购买假残疾证，若遭深圳关员截查，便出示证件“博同情”。

6月15日，有20多人在潍坊市中院门前举标语、打横幅、喊口号，引大量群众围观，造成交通混乱。警方通报，该起事件策划者、组织指挥者因涉嫌聚众扰乱社会秩序罪被刑拘。调查称,这些“访民”非真正访民，多数基本每次参加都为获得报酬。日前，该起事件的策划者、组织指挥者翟岩民，及大部分参与者，因涉嫌聚众扰乱社会秩序罪被刑拘。

什么叫新闻？新闻就是昨天你说那人姓许，毒驾无驾驶证，今天说那人姓王，正常驾驶，驾驶证有效；就是昨天你说评定的一类合格桥使用年限100年，今天你说桥垮原因超载；就是昨天你说获救人数14人，今天你说获救人数12人。如此种种不以事实为根据的报道，创造出了全球惊天大新闻。仅此一家，别无分号。

e present the R package gMWT which is designed for the comparison of several treatments (or groups) for a large number of variables. The comparisons are made using certain probabilistic indices (PI). The PIs computed here tell how often pairs or triples of observations coming from different groups appear in a specific order of magnitude. Classical two and several sample rank test statistics such as the Mann-Whitney-Wilcoxon, Kruskal-Wallis, or Jonckheere-Terpstra test statistics are simple functions of these PI. Also new test statistics for directional alternatives are provided. The package gMWT can be used to calculate the variable-wise PI estimates, to illustrate their multivariate distribution and mutual dependence with joint scatterplot matrices, and to construct several classical and new rank tests based on the PIs. The aim of the paper is first to briefly explain the theory that is necessary to understand the behavior of the estimated PIs and the rank tests based on them. Second, the use of the package is described and illustrated with simulated and real data examples. It is stressed that the package provides a new flexible toolbox to analyze large gene or microRNA expression data sets, collected on microarrays or by other high-throughput technologies. The testing procedures can be used in an eQTL analysis, for example, as implemented in the package GeneticTools.