simPH: An R Package for Showing Estimates for Interactive and Nonlinear Effects from Cox Proportional Hazard Models

Christopher Gandrud

Hertie School of Governance

September 1, 2013

The R package simPH provides tools for effectively communicating results from Cox Proportional Hazard (PH) models, especially models with interactive and nonlinear effects. The Cox Proportional Hazard model is a popular tool for examining cross-unit cross-time data. However, many researchers misspecify their models and poorly communicate uncertainty about their estimates. This is unfortunate because causes of model misspecification – e.g., interactive and nonlinear effects – may be substantively meaningful. Uncertainty about these effects can be difficult to assess because quantities of interest are often on asymmetric and nonlinear scales. Part of the problem has been that available computational tools make it difficult to explore and communicate these effects. simPH overcomes these problems by making it easy for researchers to simulate and then plot quantities of interest for a variety of effects estimated from Cox PH models. The package can also be used for simple linear effects, making it a useful all-round package for showing results from Cox PH models. simPH’s plots employ visual weighting in order to effectively communicate estimation uncertainty. The user also has the option of showing either the standard central interval of the simulation’s distribution or the shortest probability interval – which can be especially useful for asymmetrically distributed estimates. I use hypothetical and empirical examples to illustrate simPH’s syntax and capabilities.

Number of Pages in PDF File: 21

working papers series

Download This Paper

Date posted: September 1, 2013 ; Last revised: February 22, 2014

Suggested Citation

Gandrud, Christopher, simPH: An R Package for Showing Estimates for Interactive and Nonlinear Effects from Cox Proportional Hazard Models (September 1, 2013). Available at SSRN: http://ssrn.com/abstract=2318977 or http://dx.doi.org/10.2139/ssrn.2318977

Contact Information

Christopher Gandrud (Contact Author)
Hertie School of Governance ( email )
Schlossplatz 1
Berlin, 10178
Feedback to SSRN

Paper statistics
Abstract Views: 384
Downloads: 119
Download Rank: 133,151

© 2014 Social Science Electronic Publishing, Inc. All Rights Reserved.  FAQ   Terms of Use   Privacy Policy   Copyright   Contact Us
This page was processed by apollo4 in 0.312 seconds