Jackson Bonner (tenorcurve30)

Multiple Imputation (MI) is always challenging in high dimensional settings. The imputation model with some selected number of predictors can be incompatible with the analysis model leading to inconsistent and biased estimates. Although compatibility in such cases may not be achieved, but one can obtain consistent and unbiased estimates using a semi-compatible imputation model. We propose to relax the lasso penalty for selecting a large set of variables (at most n). The substantive model that also uses some formal variable selection procedure in high-dimensional structures is then expected to be nested in this imputation model. The resulting imputation model will be semi-compatible with high probability. The likelihood estimates can be unstable and can face the convergence issues as the number of variables becomes nearly as large as the sample size. To address these issues, we further propose to use a ridge penalty for obtaining the posterior distribution of the parameters based on the observed data. The proposed technique is compared with the standard MI software and MI techniques available for high-dimensional data in simulation studies and a real life dataset. Our results exhibit the superiority of the proposed approach to the existing MI approaches while addressing the compatibility issue.The shift from postauricular to transcanal microscopic tympanoplasty brings potential advantages of minimal morbidity, less postoperative pain, patient comfort, and surgical ease and speed, but also uncertainties of unfamiliar grafting material, an inadequate operation view, and an uncertain learning curve. These challenges might affect the successful repair rate and the frequency-specific hearing outcome, which is important for hearing perception. Rare studies reported frequency-specific hearing outcome with the learning curve for shifting from postauricular to transcanal microscopic tympanoplasty. Here, from Jul. 2013 to Nov. 2018, we compared patients in a shift from postauricular approach (35 ears) to transcanal approach (35 ears) of microscopic type-1 tympanoplasty. The results show that both of postauricular and transcanal microscopic tympanoplasties reduced the mean air-bone gap, 0.5k Hz gap, and 1k Hz gap after the surgery. The further analyses on gap change as a function of frequency (0.5, 1, 2, and 4k Hz) show that both of postauricular and transcanal tympanoplasties improved postoperative air-bone gap among the levels of frequency. The post hoc comparisons display a common gap reduction difference between 0.5k and 4k Hz. The successful repair rate did not differ between the 2 groups. There was no correlation between the postoperative mean gap change and the surgery date, suggesting a minimal learning-curve effect. The results of similar frequency-specific improvements and a minimal learning-curve effect may help to ease the concerns of those uncertainties before the shift. Norway has not implemented universal varicella vaccination, despite the considerable clinical and economic burden of varicella disease. An existing dynamic transmission model of varicella infection was calibrated to age-specific seroprevalence rates in Norway. Six two-dose vaccination strategies were considered, consisting of combinations of two formulations each of a monovalent varicella vaccine (Varivax® or Varilrix®) and a quadrivalent vaccine against measles-mumps-rubella-varicella (ProQuad® or PriorixTetra®), with the first dose given with a monovalent vaccine at age 15 months, and the second dose with either a monovalent or quadrivalent vaccine at either 18 months, 7 or 11 years. Costs were considered from the perspectives of both the health care system and society. Quality-adjusted life-years saved and incremental cost-effectiveness ratios relative to no vaccination were calculated. A one-way sensitivity analysis was conducted to assess the impact of vaccine efficacy, price, the costs of a lost wor to no vaccination in Norway.