论文部分内容阅读
In this talk,I will discuss a nonlinear mixed-effects scalar-on-function regression model using a Gaussian process prior.
Functional LARS and Analysis of Big Medical Movement Data
【摘 要】
：
In this talk,I will discuss a nonlinear mixed-effects scalar-on-function regression model using a Gaussian process prior.
【机 构】
：
MRC Biostatistics Unit,Cambridge Institute of Public Health,Cambridge University,Cambridge,CB2 0SR,U
【出 处】
：
上海交通大学
【发表日期】
：
2016年4期
其他文献
Tertiary care facilities often maintain registries of patients with longitudinal follow-up to create a platform for research on the course of chronic disease and the identification of associated risk
Longitudinal data is one of the important primary endpoint types in clinical trial.Usually it is analyzed using mixed-effects model repeated measures(MMRM).
The analysis of Big Data is one of the challenges in the 21st century.A promising strategy is the rank order representation of data that do not share a specific numerical scale.
In this talk,a factor model with errors generated from independent Gaussian stochastic processes is proposed for the longitudinal/functional data analysis.
会议
Pairwise comparisons is a very common multiple comparisons problem.It is widely accepted that Fishers LSD test does not control the familywise error rate(FWER)when there are more than three groups to
Competing risks data arise naturally in observational cohort studies and clinical trials.Frequently,outcome determination is based on imperfect,and usually less expensive,diagnostic procedures leading
Study of the effect of metal trace elements from old antimony mine on plant communities by cluster a
It has been shown in a previous study that the old antimony mine of Djebel Hamimat(Northeast of Algeria)engendered an important pollution of the surrounding areas by metallic trace elements,in particu
会议
The Ginibre point process has attracted considerable attention recently because of its wide use in modelling mobile networks.
There is an increasing interest in moving cognitive studies beyond the identification of anatomical locations of functional processes that are time-locked to a particular task,to the detection of the
Its theoretically desirable to perform variable selection via penalized likelihood that directly penalizes the number of variables in generalized linear models(L0 penalized methods).