Length-of-stay times in hospital for COVID-19 patients using the smoothed Beran"s estimator with bootstrap bandwidth selection Articles uri icon

publication date

  • May 2024

International Standard Serial Number (ISSN)

  • 1645-6726

Electronic International Standard Serial Number (EISSN)

  • 2183-0371

abstract

  • The survival function of length-of-stay in hospital ward and Intensive Care Unit forCOVID-19 patients is studied in this paper. Flexible statistical methods are used toestimate this survival function given relevant covariates such as age, sex, obesity andchronic obstructive pulmonary disease. A doubly-smoothed Beran"s estimator hasbeen considered to this aim. The bootstrap method has been used to produce newsmoothing parameter selectors and to construct confidence regions for the conditionalsurvival function. Some simulation studies show the good performance of the proposedmethods.

subjects

  • Statistics

keywords

  • censored data; conditional survival function; bootstrap; bandwidth selector; confi-dence regions