morse: predict – R documentation

Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!

predict

Predict method for survFit objects

Description

This is the generic predict S3 method for the survFit class. It provides simulation for "SD" or "IT" models under constant or time-variable exposure.

It provides the simulated number of survivors for "SD" or "IT" models under constant or time-variable exposure.

This is a method to replace function predict_Nsurv used on survFit object when computing issues happen. predict_nsurv_ode uses the deSolve library to improve robustness. However, time to compute may be longer.

Usage

## S3 method for class 'survFit'
predict(
  object,
  data_predict = NULL,
  spaghetti = FALSE,
  mcmc_size = NULL,
  hb_value = TRUE,
  ratio_no.NA = 0.95,
  hb_valueFORCED = NA,
  extend_time = 100,
  ...
)

predict_Nsurv(object, ...)

## S3 method for class 'survFit'
predict_Nsurv(
  object,
  data_predict = NULL,
  spaghetti = FALSE,
  mcmc_size = NULL,
  hb_value = TRUE,
  hb_valueFORCED = NA,
  extend_time = 100,
  ...
)

predict_Nsurv_ode(
  object,
  data_predict,
  spaghetti,
  mcmc_size,
  hb_value,
  hb_valueFORCED,
  extend_time,
  interpolate_length,
  interpolate_method,
  ...
)

Arguments

`object`	An object of class `survFit`.
`data_predict`	A dataframe with three columns `time`, `conc` and `replicate` used for prediction. If `NULL`, prediction is based on `x` object of class `survFit` used for fitting.
`spaghetti`	If `TRUE`, return a set of survival curves using parameters drawn from the posterior distribution.
`mcmc_size`	Can be used to reduce the number of mcmc samples in order to speed up the computation. `mcmc_size` is the number of selected iterations for one chain. Default is 1000. If all MCMC is wanted, set argument to `NULL`.
`hb_value`	If `TRUE`, the background mortality `hb` is taken into account from the posterior. If `FALSE`, parameter `hb` is set to 0. The default is `TRUE`.
`ratio_no.NA`	A numeric between 0 and 1 standing for the proportion of non-NA values required to compute quantile. The default is 0.95.
`hb_valueFORCED`	If `hb_value` is `FALSE`, it fix `hb`.
`extend_time`	Length of time points interpolated with variable exposure profiles.
`...`	Further arguments to be passed to generic methods
`interpolate_length`	Length of the time sequence for which output is wanted.
`interpolate_method`	The interpolation method for concentration. See package `deSolve` for details. Default is `linear`.

Value

The function returns an object of class survFitPredict_Nsurv, which is a list with the two following data.frame:

df_quantile

A data.frame with 10 columns, time, conc, replicate, Nsurv (observed number of survivors) and other columns with median and 95% credible interval of the number of survivors computed with 2 different way refers as check and valid: Nsurv_q50_check, Nsurv_qinf95_check, Nsurv_qsup95_check, Nsurv_q50_valid, Nsurv_qinf95_valid, Nsurv_qsup95_valid. The _check refers to the number of survivors at time t predicted using the observed number of survivors at time t-1, while the _valid refers to the number of survivors predicted at time t based on the predicted number of survivors at time t-1.

df_spaghetti

NULL if arguement spaghetti = FALSE. With spaghetti = TRUE, it returns a dataframe with all simulations based on MCMC parameters from a survFit object.

Examples

# (1) Load the survival data
data("propiconazole_pulse_exposure")

# (2) Create an object of class "survData"
dataset <- survData(propiconazole_pulse_exposure)

## Not run: 
# (3) Run the survFit function
out <- survFit(dataset , model_type = "SD")

# (4) Create a new data table for prediction
data_4prediction <- data.frame(time = 1:10,
                               conc = c(0,5,30,30,0,0,5,30,15,0),
                               replicate= rep("predict", 10))

# (5) Predict on a new dataset
predict_out <- predict(object = out, data_predict = data_4prediction, spaghetti = TRUE)


## End(Not run)



# (1) Load the survival data
data("propiconazole_pulse_exposure")

# (2) Create an object of class "survData"
dataset <- survData(propiconazole_pulse_exposure)

## Not run: 
# (3) Run the survFit function
out <- survFit(dataset , model_type = "SD")

# (4) Create a new data table for prediction
data_4prediction <- data.frame(time = 1:10,
                               conc = c(0,5,30,30,0,0,5,30,15,0),
                               replicate= rep("predict", 10),
                               Nsurv = c(20,20,17,16,15,15,15,14,13,12))

# (5) Predict Nsurv on a new data set
predict_out <- predict_Nsurv(object = out, data_predict = data_4prediction, spaghetti = TRUE)


## End(Not run)

morse

Modelling Tools for Reproduction and Survival Data in Ecotoxicology

v3.3.1

GPL (>= 2)

Authors

Virgile Baudrot [aut], Sandrine Charles [aut], Marie Laure Delignette-Muller [aut], Wandrille Duchemin [ctb], Benoit Goussen [ctb], Nils Kehrein [ctb], Guillaume Kon-Kam-King [ctb], Christelle Lopes [ctb], Philippe Ruiz [aut], Alexander Singer [ctb], Philippe Veber [aut]

Initial release