Comparison of algorithms to generate event times conditional on time-dependent covariates

2008 ◽  
Vol 27 (14) ◽  
pp. 2618-2634 ◽  
Author(s):  
Marie-Pierre Sylvestre ◽  
Michal Abrahamowicz
Keyword(s):  
Time Dependent ◽  
Comparison Of Algorithms ◽  
Event Times ◽  
Time Dependent Covariates

scholarly journals Joint Modelling Approaches to Survival Analysis via Likelihood-Based Boosting Techniques

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Colin Griesbach ◽  
Andreas Groll ◽  
Elisabeth Bergherr
Keyword(s):  
Survival Analysis ◽  
Variable Selection ◽  
Time Dependent ◽  
Gradient Boosting ◽  
Joint Models ◽  
Cell Counts ◽  
Longitudinal Outcome ◽  
Event Times ◽  
Time Dependent Covariates ◽  
Updating Procedure

Joint models are a powerful class of statistical models which apply to any data where event times are recorded alongside a longitudinal outcome by connecting longitudinal and time-to-event data within a joint likelihood allowing for quantification of the association between the two outcomes without possible bias. In order to make joint models feasible for regularization and variable selection, a statistical boosting algorithm has been proposed, which fits joint models using component-wise gradient boosting techniques. However, these methods have well-known limitations, i.e., they provide no balanced updating procedure for random effects in longitudinal analysis and tend to return biased effect estimation for time-dependent covariates in survival analysis. In this manuscript, we adapt likelihood-based boosting techniques to the framework of joint models and propose a novel algorithm in order to improve inference where gradient boosting has said limitations. The algorithm represents a novel boosting approach allowing for time-dependent covariates in survival analysis and in addition offers variable selection for joint models, which is evaluated via simulations and real world application modelling CD4 cell counts of patients infected with human immunodeficiency virus (HIV). Overall, the method stands out with respect to variable selection properties and represents an accessible way to boosting for time-dependent covariates in survival analysis, which lays a foundation for all kinds of possible extensions.

scholarly journals Marginal quantile regression for longitudinal data analysis in the presence of time-dependent covariates

2020 ◽  
Vol 0 (0) ◽  
Author(s):  
I-Chen Chen ◽  
Philip M. Westgate
Keyword(s):  
Parameter Estimation ◽  
Longitudinal Data ◽  
Quantile Regression ◽  
Mean Squared Error ◽  
Time Dependent ◽  
Regression Methods ◽  
Squared Error ◽  
Highly Correlated ◽  
Time Dependent Covariates ◽  
Independence Structure

AbstractWhen observations are correlated, modeling the within-subject correlation structure using quantile regression for longitudinal data can be difficult unless a working independence structure is utilized. Although this approach ensures consistent estimators of the regression coefficients, it may result in less efficient regression parameter estimation when data are highly correlated. Therefore, several marginal quantile regression methods have been proposed to improve parameter estimation. In a longitudinal study some of the covariates may change their values over time, and the topic of time-dependent covariate has not been explored in the marginal quantile literature. As a result, we propose an approach for marginal quantile regression in the presence of time-dependent covariates, which includes a strategy to select a working type of time-dependency. In this manuscript, we demonstrate that our proposed method has the potential to improve power relative to the independence estimating equations approach due to the reduction of mean squared error.

The analysis of binary longitudinal data with time-dependent covariates

2012 ◽  
Vol 31 (10) ◽  
pp. 931-948 ◽  
Author(s):  
Matthew W. Guerra ◽  
Justine Shults ◽  
Jay Amsterdam ◽  
Thomas Ten-Have
Keyword(s):  
Longitudinal Data ◽  
Time Dependent ◽  
Binary Longitudinal Data ◽  
Time Dependent Covariates

scholarly journals Number of Inseminations to Conception in Holstein Cows Using Censored Records and Time-Dependent Covariates

2005 ◽  
Vol 88 (10) ◽  
pp. 3655-3662 ◽  
Author(s):  
O. González-Recio ◽  
Y.M. Chang ◽  
D. Gianola ◽  
K.A. Weigel
Keyword(s):  
Time Dependent ◽  
Holstein Cows ◽  
Time Dependent Covariates

scholarly journals Mortality Risk and The Progression of The Electronic Frailty Index and Hospital Frailty Risk Score Over Time

2020 ◽  
Vol 5 (5) ◽  
Author(s):  
Joe Hollinghurst ◽  
Alan Watkins
Keyword(s):  
Risk Score ◽  
Frailty Index ◽  
Time Frame ◽  
Time Dependent ◽  
Cox Models ◽  
Hazard Ratios ◽  
Increased Risk ◽  
The Matrix ◽  
Time Dependent Covariates ◽  
Over Time

IntroductionThe electronic Frailty Index (eFI) and the Hospital Frailty Risk Score (HFRS) have been developed in primary and secondary care respectively. Objectives and ApproachOur objective was to investigate how frailty progresses over time, and to include the progression of frailty in a survival analysis.To do this, we performed a retrospective cohort study using linked data from the Secure Anonymised Information Linkage Databank, comprising 445,771 people aged 65-95 living in Wales (United Kingdom) on 1st January 2010. We calculated frailty, using both the eFI and HFRS, for individuals at quarterly intervals for 8 years with a total of 11,702,242 observations. ResultsWe created a transition matrix for frailty states determined by the eFI (states: fit, mild, moderate, severe) and HFRS (states: no score, low, intermediate, high), with death as an absorbing state. The matrix revealed that frailty progressed over time, but that on a quarterly basis it was most likely that an individual remained in the same state. We calculated Hazard Ratios (HRs) using time dependent Cox models for mortality, with adjustments for age, gender and deprivation. Independent eFI and HFRS models showed increased risk of mortality as frailty severity increased. A combined eFI and HFRS revealed the highest risk was primarily determined by the HFRS and revealed further subgroups of individuals at increased risk of an adverse outcome. For example, the HRs (95% Confidence Interval) for individuals with an eFI as fit, mild, moderate and severe with a high HFRS were 18.11 [17.25,19.02], 20.58 [19.93,21.24], 21.45 [20.85,22.07] and 23.04 [22.34,23.76] respectively with eFI fit and no HFRS score as the reference category. ConclusionFrailty was found to vary over time, with progression likely in the 8-year time-frame analysed. We refined HR estimates of the eFI and HFRS for mortality by including time dependent covariates.

Sign in / Sign up

Export Citation Format

Share Document