spduration | R Documentation |

The spduration package provides functions to estimate split-population duration regression models in which only a subset of the population is at risk for failure, while the remainder is immune, or cured, from the possibility of experiencing a failure event. In practice, this class of models also may produce better performance in sparse data with few actual failure events.

The main function `spdur`

is used to estimate the model
objects with class `spdur`

.

Postestimation tools include `predict.spdur`

, for calculating
fitted values with arbitrary data and for several probabilities that
might be of interest, as well as `plot.spdur`

for visual
display of model fit.

**Maintainer**: Andreas Beger adbeger@gmail.com (ORCID)

Authors:

Daina Chiba dchiba@essex.ac.uk (ORCID)

Daniel W. Hill, Jr. dwhill@uga.edu

Nils W. Metternich n.metternich@ucl.ac.uk (ORCID)

Shahryar Minhas hermes829@gmail.com

Michael D. Ward michael.don.ward@gmail.com (ORCID) [copyright holder]

Boag, J.W. 1949. “Maximum Likelihood Estimates of the Proportion of Patients Cured by Cancer Therapy.” <https://www.jstor.org/stable/2983694>

Berkson, J. and Gage, R.P. “Survival Curve for Cancer Patients Following Treatment.” <https://www.jstor.org/stable/2281318>

Leisch, Friedrich. 2009. “Creating R Packages: A Tutorial.”

Schmidt, Peter and Witte, Ann Dryden. 1989. “Predicting Criminal Recidivism Using "Split Population" Survival Time Models.” <doi:10.1016/0304-4076(89)90034-1>

Svolik, Milan. 2008. “Authoritarian Reversals and Democratic Consolidation.” American Political Science Review.

Useful links:

Embedding an R snippet on your website

Add the following code to your website.

For more information on customizing the embed code, read Embedding Snippets.