Recent results in ridge regression methodsSpringer Science and Business Media LLC - Tập 73 - Trang 359-376 - 2015
M. A. Alkhamisi, I. B. MacNeill
Necessary and sufficient conditions for superiority of the restricted ridge estimator over the restricted least squares estimator are derived when the set of a prior restrictions on parameters are assumed to be incorrect (as well as when the restrictions are assumed to hold). Condition number and trace of mean square error criteria are used to gauge the goodness of some new and some known ridge pa...... hiện toàn bộ
Book ReviewsSpringer Science and Business Media LLC - Tập 69 - Trang 223-226 - 2012
Paolo Piccinni
Dealing sensitive characters on successive occasions through a general class of estimators using scrambled response techniquesSpringer Science and Business Media LLC - Tập 76 - Trang 203-230 - 2017
Kumari Priyanka, Pidugu Trisandhya, Richa Mittal
Present article endeavours to propose a general class of estimators to estimate population mean of a sensitive character using non-sensitive auxiliary information under five different scrambled response models in two occasions successive sampling. Various well-known estimators have been modified for the estimation of sensitive population mean and hence they also become a member of proposed general...... hiện toàn bộ
Length biased weighted residual inaccuracy measureSpringer Science and Business Media LLC - Tập 68 - Trang 153-160 - 2012
Vikas Kumar, R. Srivastava, H. C. Taneja
In the present communication we introduce a length biased weighted residual inaccuracy measure between two residual lifetime distributions over the interval (t, ∞). Based on proportional hazard model (PHM), a characterization problem for the weighted residual inaccuracy measure has been studied. A lower bound to the weighted residual inaccuracy measure has also been derived.
Penalized estimation of flexible hidden Markov models for time series of countsSpringer Science and Business Media LLC - Tập 77 - Trang 87-104 - 2019
Timo Adam, Roland Langrock, Christian H. Weiß
We propose an effectively nonparametric approach to fitting hidden Markov models to time series of counts, where the state-dependent distributions are estimated in a completely data-driven way without the need to specify a parametric family of distributions. To avoid overfitting, a roughness penalty based on higher-order differences between adjacent count probabilities is added to the likelihood, ...... hiện toàn bộ