A generalized linear model with smoothing effects for claims reserving

In this paper, we continue the development of the ideas introduced in England and Verrall (2001) by suggesting the use of a reparameterized version of the generalized linear model (GLM) which is frequently used in stochastic claims reserving. This model enables us to smooth the origin, development and calendar year parameters in a similar way as is often done in practice, but still keep the GLM structure. Specifically, we use this model structure in order to obtain reserve estimates and to systemize the model selection procedure that arises in the smoothing process. Moreover, we provide a bootstrap procedure to achieve a full predictive distribution.     

Variance computations for functional of absolute risk estimates

We present a simple influence function based approach for computing the variances of estimates of absolute risk and functions of absolute risk. We apply this approach to criteria that assess the impact of changes in the risk factor distribution on absolute risk for an individual and at the population level. As an illustration we use an absolute risk prediction model for breast cancer that includes modifiable risk factors in addition to standard breast cancer risk factors. Influence function based variance estimates for absolute risk and the criteria are compared to bootstrap variance estimates.     

Data analysis in stability studies of biopharmaceutical drugs with isothermal and non-isothermal assays

Stability is a particular problem for biopharmaceutical products because the efficacy of peptides and proteins as therapeutic or diagnostic agents can be affected during preparation, shipping, and storage. A particular formulation may have no immediately apparent effect on physical or chemical stability, and the time required for these studies at ambient temperature can be very lengthy because chemical reactions proceed relatively slowly at low temperatures. Undoubtedly, accelerated and stress testing of stability can provide useful information for future product development. The many methods used to study kinetics in aqueous solution may be experimental or computational. Experimental approaches may be isothermal or non-isothermal. Non-linear and linear regression methods can be used to analyze data from these experimental approaches, and the Monte Carlo method could be useful to obtain information about uncertainties in experimental data.The purpose of this review is to describe and to discuss options for the accelerated study of peptide and protein drugs. These options are not necessarily the same as those used for regulatory testing to set expiration dates. We also review statistical techniques to estimate kinetic parameters (rate constant, activation energy, and pre-exponential factor). Further, we establish the advantages and the limitations of both thermal approaches. We analyze and discuss all aspects using the most recent examples of peptide and protein stability.