We consider estimation in the single‐index model where the link function is monotone. For this model, a profile least‐squares estimator has been proposed to estimate the unknown link function and index. Although it is natural to propose this procedure, it is still unknown whether it produces index estimates that converge at the parametric rate. We show that this holds if we solve a score equation corresponding to this least‐squares problem. Using a Lagrangian formulation, we show how one can solve this score equation without any reparametrization. This makes it easy to solve the score equations in high dimensions. We also compare our method with the effective dimension reduction and the penalized least‐squares estimator methods, both available on CRAN as R packages, and compare with link‐free methods, where the covariates are elliptically symmetric.

We construct √ n-consistent and asymptotically normal estimates for the finite dimensional regression parameter in the current status linear regression model, which do not require any smoothing device and are based on maximum likelihood estimates (MLEs) of the infinite dimensional parameter. We also construct estimates, again only based on these MLEs, which are arbitrarily close to efficient estimates, if the generalized Fisher information is finite. This type of efficiency is also derived under minimal conditions for estimates based on smooth non-monotone plug-in estimates of the distribution function. Algorithms for computing the estimates and for selecting the bandwidth of the smooth estimates with a bootstrap method are provided. The connection with results in the econometric literature is also pointed out.

Dengue is a major public health problem worldwide. Although several drug candidates have been evaluated in randomized controlled trials, none has been effective and at present, early recognition of severe dengue and timely supportive care are used to reduce mortality. While the first dengue vaccine was recently licensed, and several other candidates are in late stage clinical trials, future decisions regarding widespread deployment of vaccines and/or therapeutics will require evidence of product safety, efficacy and effectiveness. Standard, quantifiable clinical endpoints are needed to ensure reproducibility and comparability of research findings. To address this need, we established a working group of dengue researchers and public health specialists to develop standardized endpoints and work towards consensus opinion on those endpoints. After discussion at two working group meetings and presentations at international conferences, a Delphi methodology-based query was used to finalize and operationalize the clinical endpoints. Participants were asked to select the best endpoints from proposed definitions or offer revised/new definitions, and to indicate whether contributing items should be designated as optional or required. After the third round of inquiry, 70% or greater agreement was reached on moderate and severe plasma leakage, moderate and severe bleeding, acute hepatitis and acute liver failure, and moderate and severe neurologic disease. There was less agreement regarding moderate and severe thrombocytopenia and moderate and severe myocarditis. Notably, 68% of participants agreed that a 50,000 to 20,000 mm3 platelet range be used to define moderate thrombocytopenia; however, they remained divided on whether a rapid decreasing trend or one platelet count should be case defining. While at least 70% agreement was reached on most endpoints, the process identified areas for further evaluation and standardization within the context of ongoing clinical studies. These endpoints can be used to harmonize data collection and improve comparability between dengue clinical trials.

ABSTRACT. We discuss a new way of constructing pointwise confidence intervals for the distribution function in the current status model. The confidence intervals are based on the smoothed maximum likelihood estimator, using local smooth functional theory and normal limit distributions. Bootstrap methods for constructing these intervals are considered. Other methods to construct confidence intervals, using the non-standard limit distribution of the (restricted) maximum likelihood estimator, are compared with our approach via simulations and real data applications.