Abstract
A cure model is a useful approach for analysing failure time data in which some subjects could eventually experience, and others never experience, the event of interest. A cure model has two components: incidence which indicates whether the event could eventually occur and latency which denotes when the event will occur given the subject is susceptible to the event. In this paper, we propose a semi-parametric cure model in which covariates can affect both the incidence and the latency. A logistic regression model is proposed for the incidence, and the latency is determined by an accelerated failure time regression model with unspecified error distribution. An EM algorithm is developed to fit the model. The procedure is applied to a data set of tonsil cancer patients treated with radiation therapy.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 3235-3247 |
| Number of pages | 13 |
| Journal | Statistics in Medicine |
| Volume | 21 |
| Issue number | 21 |
| DOIs | |
| State | Published - Nov 15 2002 |
| Externally published | Yes |
Fingerprint
Keywords
- Accelerated failure time model
- Cure model
- EM algorithm
- Incidence
- Latency
ASJC Scopus subject areas
- Epidemiology
Cite this
A semi-parametric accelerated failure time cure model. / Li, Chin-Shang; Taylor, Jeremy M G.
In: Statistics in Medicine, Vol. 21, No. 21, 15.11.2002, p. 3235-3247.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - A semi-parametric accelerated failure time cure model
AU - Li, Chin-Shang
AU - Taylor, Jeremy M G
PY - 2002/11/15
Y1 - 2002/11/15
N2 - A cure model is a useful approach for analysing failure time data in which some subjects could eventually experience, and others never experience, the event of interest. A cure model has two components: incidence which indicates whether the event could eventually occur and latency which denotes when the event will occur given the subject is susceptible to the event. In this paper, we propose a semi-parametric cure model in which covariates can affect both the incidence and the latency. A logistic regression model is proposed for the incidence, and the latency is determined by an accelerated failure time regression model with unspecified error distribution. An EM algorithm is developed to fit the model. The procedure is applied to a data set of tonsil cancer patients treated with radiation therapy.
AB - A cure model is a useful approach for analysing failure time data in which some subjects could eventually experience, and others never experience, the event of interest. A cure model has two components: incidence which indicates whether the event could eventually occur and latency which denotes when the event will occur given the subject is susceptible to the event. In this paper, we propose a semi-parametric cure model in which covariates can affect both the incidence and the latency. A logistic regression model is proposed for the incidence, and the latency is determined by an accelerated failure time regression model with unspecified error distribution. An EM algorithm is developed to fit the model. The procedure is applied to a data set of tonsil cancer patients treated with radiation therapy.
KW - Accelerated failure time model
KW - Cure model
KW - EM algorithm
KW - Incidence
KW - Latency
UR - http://www.scopus.com/inward/record.url?scp=0037110528&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0037110528&partnerID=8YFLogxK
U2 - 10.1002/sim.1260
DO - 10.1002/sim.1260
M3 - Article
C2 - 12375301
AN - SCOPUS:0037110528
VL - 21
SP - 3235
EP - 3247
JO - Statistics in Medicine
JF - Statistics in Medicine
SN - 0277-6715
IS - 21
ER -