397 research outputs found
Power and sample-size analysis for the Royston–Parmar combined test in clinical trials with a time-to-event outcome: Correction and program update
No full textThe changes made to Royston (2018) and to power ct are i) in section 2.4 (Sample-size calculation for the combined test), to replace ordinary leastsquares (OLS) regression using regress with grouped probit regression using glm; ii) in section 4 (Examples), to revisit the worked examples of sample-size estimation in light of the revised estimation procedure; and iii) to update the help file entry for the option n(numlist). The updated software is version 1.2.0
Review of Flexible Parametric Survival Analysis Using Stata: Beyond the Cox Model by Patrick Royston and Paul C. Lambert
No full textIn this article, I review Flexible Parametric Survival Analysis Using Stata: Beyond the Cox Model, by Patrick Royston and Paul C. Lambert (2011 [Stata Press])
Flexible parametric alternatives to the Cox model: update
No full textRoyston (2001) and Royston and Parmar (2002) introduced flexible parametric models for survival analysis, implemented in Stata through the ado-file stpm (Royston 2001). In the present article, stpm is updated to Stata 8.1 and has been shown to work correctly with Stata 8.2. To increase the reliability of the estimation procedure, the basis functions of the splines used to approximate the baseline distribution function have been orthogonalized
STSURVIMPUTE: Stata module for flexible imputation of censored survival data
No full textstsurvimpute singly imputes censored observation-times using a parametric survival model. Available basic parametric models are Weibull, log-logistic and lognormal; also supported are Royston-Parmar flexible parametric models, implemented by stpm2. Variables in varlist constitute a prognostic model that is used for predicting individual imputed survival times. Such a model should make the imputations more accurate than using only the overall distribution.survival, censoring, parametric model, Weibull, log-logistic, lognormal, Royston-Parmar
Power and sample-size analysis for the Royston–Parmar combined test in clinical trials with a time-to-event outcome
No full textRandomized controlled trials with a time-to-event outcome are usually designed and analyzed assuming proportional hazards (PH) of the treatment effect. The sample-size calculation is based on a log-rank test or the nearly identical Cox test, henceforth called the Cox/log-rank test. Nonproportional hazards (non-PH) has become more common in trials and is recognized as a potential threat to interpreting the trial treatment effect and the power of the log-rank test—hence to the success of the trial. To address the issue, in 2016, Royston and Parmar (BMC Medical Research Methodology 16: 16) proposed a “combined test” of the global null hypothesis of identical survival curves in each trial arm. The Cox/logrank test is combined with a new test derived from the maximal standardized difference in restricted mean survival time (RMST) between the trial arms. The test statistic is based on evaluations of the between-arm difference in RMST over several preselected time points. The combined test involves the minimum p-value across the Cox/log-rank and RMST-based tests, appropriately standardized to have the correct distribution under the global null hypothesis. In this article, I introduce a new command, power ct, that uses simulation to implement power and sample-size calculations for the combined test. power ct supports designs with PH or non-PH of the treatment effect. I provide examples in which the power of the combined test is compared with that of the Cox/log-rank test under PH and non-PH scenarios. I conclude by offering guidance for sample-size calculations in time-to-event trials to allow for possible non-PH
Assessing the reasonableness of an imputation model
No full textMultiple imputation is a popular way of dealing with missing values under the missing at random (MAR) assumption. Imputation models can become quite complicated, for instance, when the model of substantive interest contains many interactions or when the data originate from a nested design. This paper will discuss two methods to assess how plausible the results are. The first method consists of comparing the point estimates obtained by multiple imputation with point estimates obtained by another method for controlling for bias due to missing data. Second, the changes in standard error between the model that ignores the missing cases and the multiple imputation model are decomposed into three components: changes due to changes in sample size, changes due to uncertainty in the imputation model used in multiple imputation, and changes due to changes in the estimates that underlie the standard error. This decomposition helps in assessing the reasonableness of the change in standard error. These two methods will be illustrated with two new user written Stata commands.
Multiple imputation of missing values: Update of ice
No full textRoyston (2004) introduced mvis, an implementation for Stata of MICE, a method of multiple multivariate imputation of missing values under missing-at-random (MAR) assumptions. In a second article, Royston (2005) described ice, an upgrade incorporating various improvements and changes to the software based on personal experience, discussion with colleagues, and user requests. This article describes an update to ice. The changes are less substantial but nevertheless important enough to warrant a brief explanation. The major modification is that the default method of imputing missing values in ice is now by sampling from the posterior predictive distribution rather than by predicted mean matching.
The ice system comprises five ado-files: ice, micombine, mijoin, misplit, and uvis. The last three programs have not been changed and are included in the present release for the sake of completeness
MICE for multiple imputation of missing values
No full textThe publication of Royston (2004)'s Stata implementation of the MICE method for multiple imputation of missing values has stimulated much interest, comment and further development of the software. In this talk I will describe enhancements of what used to be called mvis.ado and is now known as mice.ado. The main changes are greatly increased flexibility in the specification of the prediction equations for individual variables, better handling of ordered and nominal categoric variables, and support for so-called passive imputation in which derived variables are updated from primary variables. All of these features reflect van Buuren's implementation of MICE on a different statistical platform. I will demonstrate their use by an example with real data. An article on the topic is in preparation (Royston 2005).
Explained variation for survival models
No full textThis article introduces a new measure of explained variation for use with censored survival data. It is a modified version of a measure previously described by John O’Quigley and colleagues, itself a modification of Nagelkerke’s earlier proposal for a general index of determination. I describe Stata programs str2ph, which implements the new measure, and str2d, which implements a measure proposed in 2004 by Royston and Sauerbrei. I provide examples with real data
Review of Multivariable Model-building: A Pragmatic Approach to Regression Analysis Based on Fractional Polynomials for Modeling Continuous Variables, by Royston and Sauerbrei
No full textThis article reviews Multivariable Model-building: A Pragmatic Approach to Regression Analysis Based on Fractional Polynomials for Modeling Continuous Variables, by Patrick Royston and Willi Sauerbrei
- …
