The analysis of incomplete data using stochastic covariates

In the development of many diseases there are often associated random variables which continuously reflect the progress of a subject towards the final expression of the disease (failure). At any given time these processes, which we call stochastic covariates, may provide information about the current hazard and the remaining time to failure. Likewise, in situations when the specific times of key prior events are not known, such as the time of onset of an occult tumour or the time of infection with HIV-1, it may be possible to identify a stochastic covariate which reveals, indirectly, when the event of interest occurred. The analysis of carcinogenicity trials which involve occult tumours is usually based on the time of death or sacrifice and an indicator of tumour presence for each animal in the experiment. However, the size of an occult tumour observed at the endpoint represents data concerning tumour development which may convey additional information concerning both the tumour incidence rate and the rate of death to which tumour-bearing animals are subject. We develop a stochastic model for tumour growth and suggest different ways in which the effect of this growth on the hazard of failure might be modelled. Using a combined model for tumour growth and additive competing risks of death, we show that if this tumour size information is used, assumptions concerning tumour lethality, the context of observation or multiple sacrifice times are no longer necessary in order to estimate the tumour incidence rate. Parametric estimation based on the method of maximum likelihood is outlined and is applied to simulated data from the combined model. The results of this limited study confirm that use of the stochastic covariate tumour size results in more precise estimation of the incidence rate for occult tumours.     

Cognitive and interpersonal abilities related to the primary activities of R&D managers

This study attempted to identify the primary activities performed by R&D managers at different supervisory levels, and the cognitive and interpersonal ability requirements that underlie these activities. A task inventory containing 244 managerial tasks was completed by 117 R&D managers in nine organizations. The 48 tasks which managers rated as having spent the most time were factor analyzed, resulting in the identification of three primary activities: project management, personnel supervision, and strategic planning. Furthermore, these activities varied with supervisory level, with R&D managers performing a wider range of these activities with the progression from first-line to upper-level management.Thirty R&D managers later rated the degree to which 19 cognitive and interpersonal abilities were required for performing these primary activities. Strategic planning was rated as requiring significantly higher levels of oral expression, logical reasoning, originality, fluency of ideas, oral defense, and resistance to premature judgement than was required for the other two primary activities. Personnel supervision required a higher level of social sensitivity than was required for the other two activities. Project management required high levels of information ordering, oral fact- finding ability, problem sensitivity, and oral and written comprehension. Implications of the findings for understanding R&D managerial performance and personnel staffing functions are discussed.     

R＆D经费投入的国际比较与借鉴

R&D经费投入是评价国家科技实力和科技发展水平的首选指标 ,长期以来已为世界各国和重要国际组织所普遍采用。本文主要针对我国R&D经费投入与国际间的比较 ,分析我国R&D投入所处的阶段及R&D投入方面存在的差距与困难 ,最后提出对策与建议     

基于因子分析的区域R&D绩效评价研究

研究与试验发展(R&D)活动是促进区域和谐发展的重要力量,区域R&D绩效水平的评价对促进区域R&D活动的有很强的实际意义,因子分析方法对于大量数据的抽象分析有较好的效果,适合R&D活动评价的特点,它在评价过程中能够避免人为因素影响而进行客观的评价,文章最后根据结果数据分析得出了我国创新效率有待提高的结论。     

垂直性研究与开发合作联盟的博弈模型新探

修改了Banerjee和Lin (2 0 0 1)提出的博弈模型 ,在考虑了组成研究与开发 (R&D)成本因素的条件下 ,重新考察了产业内形成垂直的R&D合作联盟的动机 ,得出上游 (或下游 )企业的利润与下游企业的数目之间并不存在特定的关系 ,根据CassimanBrano (2 0 0 0 )的研究结论 ,认为应该对产业中的基础研究工作给予R&D补贴     

Stochastic Modelling of Times to Temperature for Furnaces Supplying Titanium Blooms to a Rolling Mill at TIMET

In conjunction with TIMET at Waunarlwydd (Swansea, UK) a model has been developed that will optimise the scheduling of various blooms to their eight furnaces so as to minimise the time taken to roll these blooms into the finished mill products. This production scheduling model requires reliable data on times taken for the various furnaces that heat the slabs and blooms to reach the temperatures required for rolling. These times to temperature are stochastic in nature and this paper identifies the distributional form for these times using the generalised F distribution as a modelling framework. The times to temperature were found to be similarly distributed over all furnaces. The identified distributional forms were incorporated into the scheduling model to optimise a particular campaign that was run at TIMET Swansea. Amongst other conclusion it was found that, compared to the actual campaign, the model produced a schedule that reduced the makespan by some 35%.     

Estimating ordered parameters by linear programming

There are many models that require the estimation of a set of ordered parameters. For example, multivariate analysis of variance often is formulated as testing for the equality of the parameters versus an ordered alternative. This problem, referred to as isotonic inference, constrained inference, or isotonic regression, has led to the development of general solutions, not often easy to apply in special models. In this expository paper, we study the special case of a separable convex quadratic programming problem for which the optimality conditions lead to a readily solved linear complementarity problem in the Lagrange multipliers, and subsequently to an equivalent linear programming problem, whose solution can be used to recover the solution of the original isotonic problem. The method can be applied to estimating ordered correlations, ordered binomial probabilities, ordered Poisson parameters, ordered exponential scale parameters, or ordered risk differences.     

Bayesian analysis of outlier problems using divergence measures

A Bayesian approach is presented for detecting influential observations using general divergence measures on the posterior distributions. A sampling-based approach using a Gibbs or Metropolis-within-Gibbs method is used to compute the posterior divergence measures. Four specific measures are proposed, which convey the effects of a single observation or covariate on the posterior. The technique is applied to a generalized linear model with binary response data, an overdispersed model and a nonlinear model. An asymptotic approximation using Laplace method to obtain the posterior divergence is also briefly discussed.     

Two point priors and Γ-minimax estimating in families of uniform distributions

It is shown that when a parameter lying in a sufficiently small interval is to be estimated in a family of uniform distributions, a two point prior is least favourable under squared error loss. The unique Bayes estimator with respect to this prior is minimax. The Γ-minimax estimator is derived for sets Γ of priors consisting of all priors that give fixed probabilities to two specified subintervals of the parameter space if a two point prior is least favourable in Γ.     

研发投入对企业绩效的影响研究 ——基于企业金融化水平门限回归

本文选取1435家A股上市公司2011—2018年度的面板数据,以企业金融化水平作为门限变量,研究企业研发投入对企业绩效的非线性影响关系。研究结果表明:(1)企业金融化行为给研发投入对企业绩效的促进作用带来严重的时滞效应,研发投入对当年企业绩效不存在促进作用;(2)研发投入对未来一年企业绩效有双门限效应,二者呈倒N型关系,在第二区间内研发投入促进未来一年企业绩效;研发投入对未来二年企业绩效有单门限效应,在第一区间内研发投入促进未来二年企业绩效;(3)在适度的企业金融化水平区间内,研发投入才会促进未来企业绩效。本文指出上市公司金融化水平最优区间占比分布具有区域、行业和企业性质异质性,并进一步基于实证研究结果提出了相应的政策建议,有利于企业合理管理研发投入和防止企业脱实向虚。