2. 您的位置
3. 首页
4. 会议论文
5. Sizes of Markov Equivalence Classes of Directed Acyclic Graphs

Sizes of Markov Equivalence Classes of Directed Acyclic Graphs

来源 :上海交通大学 | 被引量 : 0次 | 上传用户：LVBIN0077

【摘 要】

：

When learning a directed acyclic graph(DAG)model via observational data,one generally cannot identify the underlying DAG,but can potentially obtain a Markov equivalence class.

【作 者】

：

Yangbo He Jinzhu Jia Bin Yu 

【机 构】

：

Peking University,10086,China University of Calif

【出 处】

：

上海交通大学

【发表日期】

：

2016年4期

【关键词】

：

directed acyclic graphs Markov equivalence class size distribution causality 

下载到本地 , 更方便阅读

下载此文 赞助VIP

声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架

论文部分内容阅读

　　When learning a directed acyclic graph(DAG)model via observational data,one generally cannot identify the underlying DAG,but can potentially obtain a Markov equivalence class.

其他文献

CASH FLOWFORECAST AND ASSET VALUATION WITH BAYESIAN MODELING

Many assets do not trade frequently,such as privately held companies,private infrastruc-ture projects,real estate and many structured products.

会议

Bayesian regressionKalman filterGibbs samplingCash flow forecastPrivate mark

Shrinkage Estimation of the Covariance Matrix for Portfolio Choice Using High-frequency data

This paper examines the usefulness of high-frequency data for estimation the covariance matrix for portfolio choice.A computationally convenient nonlinear shrinkage estimator for the integrated covari

会议

Portfolio choiceHigh-frequency dataIntegrated covariance matrixNonlinear shri

Robust Hypothesis Testing for Asymmetric Nominal Densities under a Relative Entropy Tolerance

This talk addresses consider the design of a binary minimax test without the symmetry assumption on the nominal conditional probability densities of observations when the nominal likeli-hood ratio is

会议

Kullback-Leibler divergencerobust hypothesis testingmin-max problemleast-favo

Ordinal Profile Monitoring with Random Explanatory Variables

Profiles characterize the functional relationship between the response variable and one or more explanatory variables and have been playing an important role in many applications.

会议

latent continuous variablelocation shiftordinal attribute levelregression coe

Simultaneous selection for responses and predictors in multivariate regression

Multivariate linear regression analysis is one of the most useful techniques in statistical science.The technique is widely used in chemometrics,econometrics,financial engineering,ge-netics,psychometr

会议

Dynamic multivariate linear regressionsimultaneous selection for responses and

Double-layer sliced Latin hypercube designs

In this paper,we propose double-layer sliced Latin hypercube design(DSLHD),in which not only the whole design is an SLHD(the first layer),but also all its slices are small SLHDs(the second layer).

会议

Branching and nested factorComputer experimentOrthogonalityUniformity

Causal analysis of administrative data and methodological challenges

In this talk,I will introduce a motivating example of studying the causal mechanisms for the effect of socioeconomic inequalities on child mortality and whether or not this is mediated through prenata

会议

administrative dataelectronic health record databig datacausal inferencemeth

Systematic tissue-specific functional annotation of the human genome highlights immune-related DNA e

Continuing efforts from large international consortia have made genome-wide epigenomic and transcriptomic annotation data publicly available for a variety of cell and tissue types.

会议

GWASfunctional annotationAlzheimer's diseasetissue-specificityepigenomi

Selection of variables for estimation of the causal effects

The causal effect is hard to estimate because of the existence of the confounder.Under the effective controlling of the necessary confounder,the causal effect is identifiable.

会议

Selecting confounding variables via the Lasso

We study variable selection problem in causal inference.This is different from the regular variable selection problem such as in linear regression.

会议

ConfounderVariable selectionLassoCausal inference