Skip to main content

Questions tagged [accelerated-failure-time]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
0 votes
0 answers
41 views

Constructing nomogram from approximate model in Regression Modelling Strategies

In section 19.5 in Regression Modelling Strategies by Frank Harrell we make an approximate model using linear regression with ols. Since this is an ols object we have to calculate survival quantities ...
ScapeProf's user avatar
0 votes
0 answers
11 views

Interpreting AFT or Cox PH model in terms of median

An AFT model has been fit, with a binary sex variable. The coefficient estimate of female was 0.416 (reference level is Male). The interpretation of the coefficient is provided as below.: "This ...
fluffyfluffy's user avatar
0 votes
0 answers
28 views

What is the distribution of error term in Gompertz AFT model?

Given the AFT model $\ln(T)=\beta+\sigma\times W$, the distribution of $T$ depends on the random term $W$. If $T$ follows a Gompertz distribution with the shape and rate, how can I derive the value of ...
Ellen1230's user avatar
0 votes
0 answers
31 views

Interpreting AFT Model Coefficients: Mean vs. Median Survival Time in Log-Normal Distribution

When interpreting the coefficients of an Accelerated Failure Time (AFT) model that assumes a log-normal distribution, should we focus on the impact of coefficients on the mean survival time or the ...
ebrahimi's user avatar
  • 291
0 votes
0 answers
49 views

Best way to write the likelihood of a model?

Suppose we have the classic AFT (Accelerated Failure Time) model: $$\log T = -X'\beta + \epsilon$$ I have seen the Likelihood corresponding to this model written in different ways. For example, I have ...
Uk rain troll's user avatar
4 votes
1 answer
73 views

How to write a Gompertz model as an accelerated failure time model?

Accelerated failure time models are usually defined as a model for $X>0$ with (constants) covariates $Z\in \mathbb{R}^p$ such that \begin{equation} \log(X) = \mu + \beta^*Z + \sigma W, \end{...
Nikolaj Pedersen's user avatar
1 vote
0 answers
25 views

The AFT and PH model

According to the following - https://dylanspicker.com/courses/STAT437/content/041%20+%20044.%20Lecture%20Notes.pdf the PH and AFT models are equivalent for Weibull distribution. Does this implies the ...
Kozolovska's user avatar
  • 1,355
2 votes
1 answer
53 views

Counting process equality for linear rank test under AFT model

I am currently reading through the paper: Estimating Regression Parameters Using Linear Rank Tests for Censored Data - A.A. Tsiatis, Annals of Statistics 18(1): 354-372, 1990. https://projecteuclid....
J McVittie's user avatar
3 votes
1 answer
156 views

R package for Accelerated failure time Models with arbitrary censoring and left truncation

This is a simple exploratory R question i hope somebody can help me with. I am trying to model accelerated failure time models on data that is arbitrarily censored (right, left, or interval censored) ...
Nikolaj Pedersen's user avatar
0 votes
0 answers
74 views

Test assumptions Log-Logistic AFT Model

I'm considering adopting a Log-logistic Accelerated Failure Time (AFT) model for my analysis. Initially, I contemplated using the Cox Proportional Hazards (PH) model; however, the PH assumption was ...
John's user avatar
  • 277
0 votes
1 answer
19 views

How to speed up aftreg estimation?

I am performing an Accelerated Failure Time (AFT) regression data on a panel setting (multiple records per observation with time-dependent variables) using the eha ...
Babak Fi Foo's user avatar
3 votes
1 answer
455 views

Choice between Proportional Hazard and Accelerated Failure Time survival models

How can I determine whether to use proportional hazard (PH) or accelerate failure time (AFT) survival models in order to analyze my data? Are there any established guidelines or common practices that ...
John's user avatar
  • 277
0 votes
0 answers
43 views

Options on modelling a hazard function with a turning point

I have some survival data and need to fit survival models to it and extrapolate. I plotted the log cumulative hazard and empirical hazard plot (using muhaz). There appears to be a change in the hazard ...
Geoff's user avatar
  • 741
0 votes
1 answer
498 views

How do I choose correct model (AFT or PH) & distribution when Cox proportional hazards is not appropriate?

I have been tasked with evaluating hospital length of stay (LOS) in two groups of patients using the Cox proportional hazards model. One group of patients received a medication, the other did not. ...
Bradley's user avatar
1 vote
1 answer
109 views

How to predict survival curves with step changes over time

I'm trying to predict the survival curves for customers, knowing that for some rare customers after a certain time the survival probability has a jump. Those jumps are due to endings of minimum ...
TiTo's user avatar
  • 249
0 votes
1 answer
105 views

What is the model for dist="logistic" in R survreg, and in what unit are the coefficients?

Does anyone know the model and parameterization for surveg with dist="logistic"? I'm having trouble finding documentation anywhere. I checked Chapter 2.2 of Kalbfleisch and Prentice and only ...
Edward Kung's user avatar
0 votes
0 answers
154 views

Xgboost AFT model predicts infinity

I used Xgboost AFT model to predict survival time but get some infinity predictions. Is it normal? How should I interpret that? I changed aft_loss_distribution from 'normal' to 'logistic', then had ...
Yi Mao's user avatar
  • 1
2 votes
1 answer
540 views

Simulate a Weibull regression model

I am trying to simulate a AFT Weibull model in R using a log-linear model \begin{align} log(Y)=\beta_0 +\beta_1 X1+\beta_2 X2+c W \end{align} where $W ~$ a extreme value distribution. below is my ...
Vincent's user avatar
  • 431
3 votes
1 answer
245 views

Relationship between Survival Distributions and Log Linear Regression in Accelerated Failure Time models

The accelerated failure time model (AFT) can be expressed as: $S_{1}(t) = S_{0}(\frac{t}{\gamma})$ where $S_{0}$ is a specified baseline survival distribution and $\frac{1}{\gamma}$ is the accelerant/...
Pete's user avatar
  • 33
2 votes
1 answer
379 views

How to formulate and simulate data from an accelerated failure time model?

I understand that an accelerated failure time model can be conceptualized as a cox model which includes covariates whose effects depend on actual time, so the convenient expression of the partial ...
AdamO's user avatar
  • 63.8k
0 votes
1 answer
636 views

What is the meaning of the flexsurvreg plot and its res.t?

I use the flexsurverg to estimate the a Weibull survival model with a time varied covariate, where “utility” is a continuous function, and the result is shown as follows: I plot the fit function and ...
Ellen1230's user avatar
2 votes
1 answer
2k views

AFT model interpretation

I am slightly confused about the way accelerated failure time models work in comparison to proportional hazard models. Is it a correct statement that while the PH model assumes covariates multiply ...
fmtcs's user avatar
  • 555
1 vote
0 answers
398 views

Weibull and Lognormal Fits

I have simulated failure time data for some components. I tested whether a Weibull or lognormal distribution best fit the data. Please see Figures below. The figures provide median and $95\%$ ...
JLee's user avatar
  • 843
2 votes
1 answer
261 views

Recurrent event data modelling - Cox PH or AFT?

I am attempting to model recurrent event data in Stata. My data is dataset of patient records and I am modelling a patients first delivery of a mobility aid and the subsequent deliveries of new ...
owen1995's user avatar
0 votes
1 answer
451 views

flexsurvreg log logistic intercept in R

I'm trying to fit a log-logistic AFT model with flexsurvreg(). With AFT model, $$\log T = \gamma_0 + \gamma_1 z_1 + \gamma_2 z_2 + \sigma W,$$ where W ~ standard logistic distribution. Below is an ...
user avatar
1 vote
1 answer
1k views

Finding a distribution of Accelerated Failure Model

Can someone please answer these 3 questions related to AFT model? In Accelerated Failure Time (AFT) model, $S(t│β,x)=S_0 (exp(β^T x).t)$, where $S_0$ is the baseline survival function, does $S_0$ ...
Dushi Fdz's user avatar
  • 145
3 votes
1 answer
394 views

AFT models in Stata with time-varying covariates

The AFT models from Stata's streg can handle time-varying covaraites. In particular, the manual states that streg is suitable ...
Benjamin Christoffersen's user avatar
1 vote
1 answer
32 views

AFT model with varying production

I want to implement an AFT model to study the failure time of a product given it's width. $$S(t|width)=S_0((\beta_0+\beta_1 \times width)t)$$ However the prodction has varied during the time (less ...
Bérénice's user avatar
3 votes
2 answers
434 views

Scale Parameter in a Log-Linear Accelerated Failure Time Model

Let the logarithm of the random varible $T_i$, associated with the lifetime of the $i$th individual in a survival study, follow the disitribution $$log(T_i) = \mu + X_i\beta + \sigma\epsilon_i$$ with $...
Benykō-Zamurai's user avatar
1 vote
1 answer
485 views

D-Calibration for Survival Models with imbalanced outcomes

I am building an accelerated time failure (AFT) model on a highly imbalanced data set 90% survival 10% death. I understand that we can not use Brier score because of the outcome imbalance, Brier score ...
user14473305's user avatar
1 vote
1 answer
1k views

Assumptions of an Accelerated Failure Time model?

I have an AFT model, comparing the adjusted survival of 5 groups and seeming to give reasonable results. As I do not feel confident in survival modelling, does this model has assumptions that need to ...
st4co4's user avatar
  • 2,217