Package 'BJM'

Plot conditional mean trajectories (CMT)

Description

This function generates the Conditional Mean Trajectories (CMT) plot. All patients in this plot experience events at the same time point, specified by condi_time2event. Several evenly spaced time points between the baseline and condi_time2event are selected for plotting. Each point is calculated using the mean value of all patients' biomarker values at that time point. The interval between two time points is defined by interval_time

Usage

cmtPlot(
  data.plot.all,
  condi_time2event,
  event_type_variable,
  event_type,
  bio_variable,
  time_variable,
  survival_variable,
  interval_time = 1/12,
  id_variable = "id"
)

Arguments

data.plot.all	A data.frame that includes the biomarker used for plotting. It is utilized to plot conditional mean trajectories (CMT).
condi_time2event	Conditional event time, indicating that all patients should have events at this time in the plot
event_type_variable	Competing risks variable indicator name. Set to NULL if there are no competing risks.
event_type	A vector containing the names of all event types.
bio_variable	Name of the biomarker variable used for plotting.
time_variable	The name of time variable in linear mixed model.
survival_variable	Name of the time-to-event outcomes variable.
interval_time	The time interval between two time points. Time points are plotted within the baseline to event time.
id_variable	Name of the patient ID column in data.plot.all. Default is "id".

Value

Conditional mean trajectories plot.

Examples

# example without competing risks

data(pbc3)

pbc.cmt <- cmtPlot(data.plot.all = pbc3, condi_time2event = 5, 
   event_type_variable = NULL, event_type = NULL,
   bio_variable = "serBilir", time_variable = "year", 
   survival_variable = "years", 
   interval_time = 1/12
)

pbc.cmt


# example with competing risks

data(pbc3)

data.plot.all = pbc3[!is.na(pbc3$status4),]

pbc.cmt.cr <- cmtPlot(data.plot.all, condi_time2event = 5, 
   event_type_variable = 'status4', event_type = c("0", "1"),
   bio_variable = "albumin", time_variable = "year", 
   survival_variable = "years", 
   interval_time = 1/4
)

pbc.cmt.cr

---

Dynamic prediction function

Description

The time values in the prediction data subset must be less than the specified prediction.time which is the prediction time. The time points for longitudinal repeated measurements must not surpass the prediction time.

Usage

dynamicPrediction(
  data.predict.all,
  long_fit_all,
  survival_fit_all,
  prediction.time,
  horizon,
  time_variable,
  survivalVariableAll,
  survivalTransFunction,
  bandcount1 = 10,
  bandcount2 = 40
)

Arguments

data.predict.all	This involves a collection of data.frame objects for dynamic prediction, each corresponding to a distinct longitudinal outcome. These data frames should contain the variables specified in LongSubFixed and LongSubRandom. Utilizing a list structure allows for the incorporation of multiple longitudinal outcomes, each potentially following different measurement protocols. In instances where all longitudinal outcomes are recorded at identical time points across patients, a singular data.frame object may be used in a list. It is presumed that each data frame is structured in a long format.
long_fit_all	Outputs from the model fitting process using the nlme package, encompassing the results and parameters obtained from the analysis.
survival_fit_all	Results and parameters generated from the model fitting procedure, utilizing the coxph function. These outputs include the comprehensive findings and variables derived from the analysis.
prediction.time	Time used to make the prediction.
horizon	Prediction horizon.
time_variable	The name of time variable in linear mixed model.
survivalVariableAll	The name of the transformed time-to-event outcomes variable.
survivalTransFunction	The transformation function used for time-to-event outcomes, in the order of survivalVariableAll.
bandcount1	The number of points used to perform the numerical integral, from the prediction time to the prediction time plus the horizon.
bandcount2	The number of points used to perform the numerical integral, from the prediction time to infinity.

Value

A probability matrix, where the rows (l_i) correspond to specific time points and the columns to individual patients. Each element within the matrix signifies the probability of a future event occurring, as dynamically predicted for each patient at each time point.

Examples

data(pbc3)

data.survival.fitting =  pbc3[!duplicated(pbc3$id), ]

formMarginalSurv = Surv(years, status3) ~ age + sex
formConditionalCR = NULL

survival_fit_all = survivalSub(data.survival.fitting, formMarginalSurv, 
                               formConditionalCR)

LongSubFixed = list(
  "long1" = serBilir ~ year + age + sex +  (years) + (years) * year,  
  "long2" = prothrombin ~ year + age + sex + (years) + (years) * year,  
  "long3" = albumin ~ year + age + age * year + sex + (years) + (years) * year,  
  "long4" = alkaline ~ year + age + sex + (years) + (years) * year, 
  "long5" = SGOT ~ year + age + sex + (years) + (years) * year, 
  "long6" = platelets ~ year + age + sex + (years)  + (years) * year)

LongSubRandom =list(
  "long1" =  ~ year| id,   
  "long2" =  ~ year| id,    
  "long3" =  ~ year| id,    
  "long4" =  ~ year| id,    
  "long5" =  ~ year| id,    
  "long6" =  ~ year| id)

survivalVariableAll = list(
  "Tyears1",  "Tyears2", "Tyears3", "Tyears4"
)

survivalTransFunction = list(
  fun1 = function(x){abs(x - 1)}, 
  fun2 = function(x){abs(x - 3)}, 
  fun3 = function(x){abs(x - 5)}, 
  fun4 = function(x){abs(x - 7)}
)

# Complete case analysis
data.fit.all = list()
for(i in 1:length(LongSubFixed)){
  data.fit.all[[i]] = pbc3[pbc3$status3 == 1, ]
}

# fitting longitudinal submodel
long_fit_all = longitudinalSub(data.fit.all, LongSubFixed, LongSubRandom)

i_PID = 2
data.raw.predict.1 = pbc3[pbc3$id == i_PID, ]

data.predict.all = list()
for(i in 1:length(LongSubFixed)){
  data.predict.all[[i]] = data.raw.predict.1[data.raw.predict.1$year <= 3,]
}

# predict risk probability
risk.prob = dynamicPrediction(data.predict.all, long_fit_all, survival_fit_all, 
                              prediction.time = 3, 
                              horizon = 3, time_variable = "year",
                              survivalVariableAll, survivalTransFunction,
                              bandcount1 = 10, bandcount2 = 10)

---

Dynamic prediction function for future biomarker

Description

The time values in the prediction data subset must be less than the specified prediction.time which is the prediction time. The time points for longitudinal repeated measurements must not surpass the prediction time.

Usage

dynamicPredictionBio(
  bio_i,
  data.predict.all,
  long_fit_all,
  survival_fit_all,
  prediction.time,
  horizon,
  time_variable,
  survivalVariableAll,
  survivalTransFunction,
  bandcount2 = 40,
  bandcount3 = 300
)

Arguments

bio_i	Biomarker used to do prediction
data.predict.all	This involves a collection of data.frame objects for dynamic prediction, each corresponding to a distinct longitudinal outcome. These data frames should contain the variables specified in LongSubFixed and LongSubRandom. Utilizing a list structure allows for the incorporation of multiple longitudinal outcomes, each potentially following different measurement protocols. In instances where all longitudinal outcomes are recorded at identical time points across patients, a singular data.frame object may be used in a list. It is presumed that each data frame is structured in a long format.
long_fit_all	Outputs from the model fitting process using the nlme package, encompassing the results and parameters obtained from the analysis.
survival_fit_all	Results and parameters generated from the model fitting procedure, utilizing the coxph function. These outputs include the comprehensive findings and variables derived from the analysis.
prediction.time	Time used to make the prediction
horizon	Prediction horizon
time_variable	The name of time variable in linear mixed model.
survivalVariableAll	The name of the transformed time-to-event outcomes variable.
survivalTransFunction	The transformation function used for time-to-event outcomes, in the order of survivalVariableAll.
bandcount2	The number of points used to perform the numerical integral, from the prediction time to infinity.
bandcount3	The number of points used to calculate the probability density function.

Value

A probability matrix, where the rows (l_i) correspond to specific time points and the columns to individual patients. Each element within the matrix signifies the probability of a future event occurring, as dynamically predicted for each patient at each time point.

Examples

data(pbc3)

data.survival.fitting =  pbc3[!duplicated(pbc3$id), ]

formMarginalSurv = Surv(years, status3) ~ age + sex
formConditionalCR = NULL

survival_fit_all = survivalSub(data.survival.fitting, formMarginalSurv, 
                               formConditionalCR)

LongSubFixed = list(
  "long1" = serBilir ~ year + age + sex +  (years) + (years) * year,  
  "long2" = prothrombin ~ year + age + sex + (years) + (years) * year,  
  "long3" = albumin ~ year + age + age * year + sex + (years) + (years) * year,  
  "long4" = alkaline ~ year + age + sex + (years) + (years) * year, 
  "long5" = SGOT ~ year + age + sex + (years) + (years) * year, 
  "long6" = platelets ~ year + age + sex + (years)  + (years) * year)

LongSubRandom =list(
  "long1" =  ~ year| id,   
  "long2" =  ~ year| id,    
  "long3" =  ~ year| id,    
  "long4" =  ~ year| id,    
  "long5" =  ~ year| id,    
  "long6" =  ~ year| id)

survivalVariableAll = list(
  "Tyears1",  "Tyears2", "Tyears3", "Tyears4"
)

survivalTransFunction = list(
  fun1 = function(x){abs(x - 1)}, 
  fun2 = function(x){abs(x - 3)}, 
  fun3 = function(x){abs(x - 5)}, 
  fun4 = function(x){abs(x - 7)}
)

# Complete case analysis
data.fit.all = list()
for(i in 1:length(LongSubFixed)){
  data.fit.all[[i]] = pbc3[pbc3$status3 == 1, ]
}

# fitting longitudinal submodel
long_fit_all = longitudinalSub(data.fit.all, LongSubFixed, LongSubRandom)

i_PID = 2
data.raw.predict.1 = pbc3[pbc3$id == i_PID, ]

data.predict.all = list()
for(i in 1:length(LongSubFixed)){
  data.predict.all[[i]] = data.raw.predict.1[data.raw.predict.1$year <= 3,]
}

Y_predict = dynamicPredictionBio(bio_i = 1, data.predict.all, long_fit_all, 
                                 survival_fit_all, prediction.time = 3, 
                                 horizon = 3, time_variable = "year",
                                 survivalVariableAll, survivalTransFunction,
                                 bandcount2 = 40, bandcount3 = 400)

---

The process involves estimating parameters for a multivariate linear mixed-effects model, which simultaneously analyzes multiple dependent variables that may be correlated. This approach incorporates both fixed effects, which are consistent across the population, and random effects, accounting for variations within groups or subjects. By fitting this model, one can assess the influence of predictor variables on several longitudinal outcomes while considering the inherent variability in the data due to random effects.

Description

The process involves estimating parameters for a multivariate linear mixed-effects model, which simultaneously analyzes multiple dependent variables that may be correlated. This approach incorporates both fixed effects, which are consistent across the population, and random effects, accounting for variations within groups or subjects. By fitting this model, one can assess the influence of predictor variables on several longitudinal outcomes while considering the inherent variability in the data due to random effects.

Usage

longitudinalSub(data.fit.all, LongSubFixed, LongSubRandom)

Arguments

data.fit.all	This process requires a set of data.frame objects designated for model fitting, with each data.frame representing a separate longitudinal outcome. These data.frame objects must include the variables identified in LongSubFixed and LongSubRandom. The use of a list arrangement facilitates the inclusion of various longitudinal outcomes, which may adhere to different measurement protocols. When all longitudinal outcomes are measured at the same time points for every patient, a single data.frame object can be in a list. It is assumed that every data.frame is organized in a long format.
LongSubFixed	This refers to a collection of formulas detailing the fixed effects portion for each longitudinal outcome. On the left side of each formula, the response variable is defined, while the right side outlines the fixed effect terms. Should only a single formula be provided—whether as a list with one item or as a standalone formula—it is inferred that a conventional univariate joint model is being constructed.
LongSubRandom	A list of one-sided formulas that define the model for the random effects of each longitudinal outcome. The number of items in this list should match the length of formLongFixed.

Value

This structure comprises a list with four components. The initial element, labeled lfit, consists of a collection of outcomes from fitting multiple univariate linear mixed models, where each entry within lfit corresponds to the results obtained through the application of the lme function from the nlme package. The second element is the estimated variance-covariance matrix derived from the random effects in a multivariate linear mixed model. The third and fourth elements, LongSubFixed and LongSubRandom, respectively, mirror the inputs provided to the model.

Examples

LongSubFixed = list(
  "long1" = serBilir ~ year + age + sex +  (years) + (years) * year,  
  "long2" = prothrombin ~ year + age + sex + (years) + (years) * year,  
  "long3" = albumin ~ year + age + age * year + sex + (years) + (years) * year,  
  "long4" = alkaline ~ year + age + sex + (years) + (years) * year, 
  "long5" = SGOT ~ year + age + sex + (years) + (years) * year, 
  "long6" = platelets ~ year + age + sex + (years)  + (years) * year)

LongSubRandom =list(
  "long1" =  ~ year| id,   
  "long2" =  ~ year| id,    
  "long3" =  ~ year| id,    
  "long4" =  ~ year| id,    
  "long5" =  ~ year| id,    
  "long6" =  ~ year| id)

survivalVariableAll = list(
  "Tyears1",  "Tyears2", "Tyears3", "Tyears4"
)

survivalTransFunction = list(
  fun1 = function(x){abs(x - 1)}, 
  fun2 = function(x){abs(x - 3)}, 
  fun3 = function(x){abs(x - 5)}, 
  fun4 = function(x){abs(x - 7)}
)

# Complete case analysis
data.fit.all = list()
for(i in 1:length(LongSubFixed)){
  data.fit.all[[i]] = pbc3[pbc3$status3 == 1, ]
}

# fitting longitudinal submodel
long_fit_all = longitudinalSub(data.fit.all, LongSubFixed, LongSubRandom)

---

Mayo Clinic primary biliary cirrhosis data

Description

The dataset originates from the Mayo Clinic trial on primary biliary cirrhosis (PBC) of the liver, carried out from 1974 to 1984. It includes data from 424 PBC patients who were referred to the Mayo Clinic within this decade and met the eligibility requirements for a randomized placebo-controlled trial of D-penicillamine. However, only the initial 312 cases from the dataset were enrolled in the randomized trial. Thus, the dataset specifically pertains to these 312 patients, for whom the data is largely complete.

Usage

data(pbc2)

Format

A data frame with 1945 observations on the following 20 variables:

id

patients identifier; in total there are 312 patients.

years

number of years between registration and the earlier of death, transplantation, or study analysis time.

status

a factor with levels alive, transplanted and dead.

drug

a factor with levels placebo and D-penicil.

age

at registration in years.

sex

a factor with levels male and female.

year

number of years between enrollment and this visit date, remaining values on the line of data refer to this visit.

ascites

a factor with levels No and Yes.

hepatomegaly

a factor with levels No and Yes.

spiders

a factor with levels No and Yes.

edema

a factor with levels No edema (i.e. no edema and no diuretic therapy for edema), edema no diuretics (i.e. edema present without diuretics, or edema resolved by diuretics), and edema despite diuretics (i.e. edema despite diuretic therapy).

serBilir

serum bilirubin in mg/dl.

serChol

serum cholesterol in mg/dl.

albumin

albumin in mg/dl.

alkaline

alkaline phosphatase in U/liter.

SGOT

SGOT in U/ml.

platelets

platelets per cubic ml/1000.

prothrombin

prothrombin time in seconds.

histologic

histologic stage of disease.

status2

a numeric vector with the value 1 denoting if the patient was dead, and 0 if the patient was alive or transplanted.

Source

pbc.

References

Fleming T, Harrington D. Counting Processes and Survival Analysis. 1991; New York: Wiley.

Therneau T, Grambsch P. Modeling Survival Data: Extending the Cox Model. 2000; New York: Springer-Verlag.

---

Mayo Clinic primary biliary cirrhosis data used as example code

Description

The dataset originates from the Mayo Clinic trial on primary biliary cirrhosis (PBC) of the liver, carried out from 1974 to 1984. It includes data from 424 PBC patients who were referred to the Mayo Clinic within this decade and met the eligibility requirements for a randomized placebo-controlled trial of D-penicillamine. However, only the initial 312 cases from the dataset were enrolled in the randomized trial. Thus, the dataset specifically pertains to these 312 patients, for whom the data is largely complete.

Usage

data(pbc2)

Format

A data frame with 1945 observations on the following 20 variables:

id

patients identifier; in total there are 312 patients.

years

number of years between registration and the earlier of death, transplantation, or study analysis time.

status

a factor with levels alive, transplanted and dead.

drug

a factor with levels placebo and D-penicil.

age

at registration in years.

sex

a factor with levels male and female.

year

number of years between enrollment and this visit date, remaining values on the line of data refer to this visit.

ascites

a factor with levels No and Yes.

hepatomegaly

a factor with levels No and Yes.

spiders

a factor with levels No and Yes.

edema

a factor with levels No edema (i.e. no edema and no diuretic therapy for edema), edema no diuretics (i.e. edema present without diuretics, or edema resolved by diuretics), and edema despite diuretics (i.e. edema despite diuretic therapy).

serBilir

serum bilirubin in mg/dl.

serChol

serum cholesterol in mg/dl.

albumin

albumin in mg/dl.

alkaline

alkaline phosphatase in U/liter.

SGOT

SGOT in U/ml.

platelets

platelets per cubic ml/1000.

prothrombin

prothrombin time in seconds.

histologic

histologic stage of disease.

status2

a numeric vector with the value 1 denoting if the patient was dead, and 0 if the patient was alive or transplanted.

status3

a numeric vector with the value 1 denoting if the patient was dead or transplanted, and 0 if the patient was alive.

status4

a numeric vector with the value 1 denoting if the patient was transplanted, and 0 if the patient was dead. Used for competing risks.

status5

a numeric vector with the value 2 if the patient was transplanted, 1 denoting if the patient was dead, and 0 if the patient was alive. Used for competing risks with censored.

Tyears1

a numeric vector with a transformed value of time-to-event outcome.

Tyears2

a numeric vector with a transformed value of time-to-event outcome.

Tyears3

a numeric vector with a transformed value of time-to-event outcome.

Tyears4

a numeric vector with a transformed value of time-to-event outcome.

Source

pbc.

References

Fleming T, Harrington D. Counting Processes and Survival Analysis. 1991; New York: Wiley.

Therneau T, Grambsch P. Modeling Survival Data: Extending the Cox Model. 2000; New York: Springer-Verlag.

---

Plot of risk and future biomarker with density using dynamic prediction

Description

This function gives the risk and biomarker prediction plot.

Usage

predictPlot(
  data.predict.all.one,
  long_fit_all,
  survival_fit_all,
  prediction.time = 4,
  horizon = seq(0, 3, 0.5),
  time_variable,
  survivalVariableAll,
  survivalTransFunction,
  bandcount1 = 10,
  bandcount2 = 10,
  bandcount3 = 200,
  bio_his = 1,
  bio_pred = 1,
  density = 1
)

Arguments

data.predict.all.one	This involves a collection of data.frame one object for dynamic prediction and making plots, each corresponding to a distinct longitudinal outcome. These data frames should contain the variables specified in LongSubFixed and LongSubRandom. Utilizing a list structure allows for the incorporation of multiple longitudinal outcomes, each potentially following different measurement protocols. In instances where all longitudinal outcomes are recorded at identical time points across patients, a singular data.frame object may be used in a list. It is presumed that each data frame is structured in a long format.
long_fit_all	Outputs from the model fitting process using the nlme package, encompassing the results and parameters obtained from the analysis.
survival_fit_all	Results and parameters generated from the model fitting procedure, utilizing the coxph function. These outputs include the comprehensive findings and variables derived from the analysis.
prediction.time	Time used to make the prediction.
horizon	Prediction horizon.
time_variable	The name of time variable in linear mixed model.
survivalVariableAll	The name of the transformed time-to-event outcomes variable.
survivalTransFunction	The transformation function used for time-to-event outcomes, in the order of survivalVariableAll.
bandcount1	The number of points used to perform the numerical integral, from the prediction time to the prediction time plus the horizon.
bandcount2	The number of points used to perform the numerical integral, from the prediction time to infinity.
bandcount3	The number of points used to calculate the probability density function.
bio_his	Which biomarker history will be plotted
bio_pred	Indicator, predict future biomarker or not, if NULL do not predict
density	Indicator, plot future biomarker density or not, if NULL do not plot

Value

Plot of risk and future biomarker with density using dynamic prediction.

Examples

data(pbc3)

data.survival.fitting =  pbc3[!duplicated(pbc3$id), ]

formMarginalSurv = Surv(years, status3) ~ age + sex
formConditionalCR = NULL

survival_fit_all = survivalSub(data.survival.fitting, formMarginalSurv, 
                               formConditionalCR)

LongSubFixed = list(
  "long1" = serBilir ~ year + age + sex +  (years) + (years) * year,  
  "long2" = prothrombin ~ year + age + sex + (years) + (years) * year,  
  "long3" = albumin ~ year + age + age * year + sex + (years) + (years) * year,  
  "long4" = alkaline ~ year + age + sex + (years) + (years) * year, 
  "long5" = SGOT ~ year + age + sex + (years) + (years) * year, 
  "long6" = platelets ~ year + age + sex + (years)  + (years) * year)

LongSubRandom =list(
  "long1" =  ~ year| id,   
  "long2" =  ~ year| id,    
  "long3" =  ~ year| id,    
  "long4" =  ~ year| id,    
  "long5" =  ~ year| id,    
  "long6" =  ~ year| id)

survivalVariableAll = list(
  "Tyears1",  "Tyears2", "Tyears3", "Tyears4"
)

survivalTransFunction = list(
  fun1 = function(x){abs(x - 1)}, 
  fun2 = function(x){abs(x - 3)}, 
  fun3 = function(x){abs(x - 5)}, 
  fun4 = function(x){abs(x - 7)}
)

# Complete case analysis
data.fit.all = list()
for(i in 1:length(LongSubFixed)){
  data.fit.all[[i]] = pbc3[pbc3$status3 == 1, ]
}

# fitting longitudinal submodel
long_fit_all = longitudinalSub(data.fit.all, LongSubFixed, LongSubRandom)

i_PID = 2
data.raw.predict.plot = pbc3[pbc3$id == i_PID, ]
data.predict.all.pre = list(data.raw.predict.plot, data.raw.predict.plot, data.raw.predict.plot,
                            data.raw.predict.plot, data.raw.predict.plot, data.raw.predict.plot)

# plot biomarker 1 history,  predict future biomarker

predictPlot(data.predict.all.pre, long_fit_all, survival_fit_all, 
            prediction.time = 5, bio_his = 1, bio_pred = 1,
            horizon = seq(0.5, 3.0, 0.5), time_variable = "year",
            survivalVariableAll, survivalTransFunction,
           bandcount1 = 10, bandcount2 = 10, bandcount3 = 200)

---

Combined print summary for a fitted BJM

Description

Combined print summary for a fitted BJM

Usage

print_BJM(long_fit_all, survival_fit_all, digits = 4)

Arguments

long_fit_all	Output from longitudinalSub.
survival_fit_all	Output from survivalSub.
digits	Number of significant digits. Default is 4.

Value

Invisibly returns a named list with both fit objects.

---

Print method for dynamicPrediction.BJM objects

Description

Automatically called when you type the result of dynamicPrediction() at the console.

Usage

## S3 method for class 'dynamicPrediction.BJM'
print(
  x,
  prediction.time = NULL,
  horizon = NULL,
  subject_ids = NULL,
  digits = 4,
  ...
)

print_dynamicPrediction(
  x,
  prediction.time = NULL,
  horizon = NULL,
  subject_ids = NULL,
  digits = 4,
  ...
)

Arguments

x	A dynamicPrediction.BJM object.
prediction.time	Landmark time (for display). Default NULL.
horizon	Prediction horizon (for display). Default NULL.
subject_ids	Optional subject ID labels.
digits	Decimal places. Default 4.
...	Additional arguments (currently unused).

Value

Invisibly returns x.

---

Print method for dynamicPredictionBio.BJM objects

Description

Automatically called when you type the result of dynamicPredictionBio() at the console.

Usage

## S3 method for class 'dynamicPredictionBio.BJM'
print(
  x,
  bio_i = NULL,
  long_fit_all = NULL,
  prediction.time = NULL,
  horizon = NULL,
  subject_ids = NULL,
  digits = 4,
  ...
)

print_dynamicPredictionBio(
  x,
  bio_i = NULL,
  long_fit_all = NULL,
  prediction.time = NULL,
  horizon = NULL,
  subject_ids = NULL,
  digits = 4,
  ...
)

Arguments

x	A dynamicPredictionBio.BJM object.
bio_i	Biomarker index (for label lookup). Default NULL.
long_fit_all	longitudinalSub.BJM object for name lookup.
prediction.time	Landmark time (for display). Default NULL.
horizon	Prediction horizon (for display). Default NULL.
subject_ids	Optional subject ID labels.
digits	Decimal places. Default 4.
...	Additional arguments (currently unused).

Value

Invisibly returns x.

---

Print method for longitudinalSub.BJM objects

Description

Automatically called when you type long_fit_all at the console.

Usage

## S3 method for class 'longitudinalSub.BJM'
print(x, digits = 4, ...)

print_longitudinalSub(x, digits = 4, ...)

Arguments

x	A longitudinalSub.BJM object returned by longitudinalSub.
digits	Number of significant digits. Default is 4.
...	Additional arguments (currently unused).

Value

Invisibly returns x.

---

Print method for survivalSub.BJM objects

Description

Automatically called when you type survival_fit_all or print(survival_fit_all) at the console. Displays a JMbayes2-style formatted summary of the survival sub-model.

Usage

## S3 method for class 'survivalSub.BJM'
print(x, digits = 4, ...)

print_survivalSub(x, digits = 4, ...)

Arguments

x	A survivalSub.BJM object returned by survivalSub.
digits	Number of significant digits. Default is 4.
...	Additional arguments (currently unused).

Value

Invisibly returns x.

Examples

data(pbc3)
data.survival.fitting <- pbc3[!duplicated(pbc3$id), ]
formMarginalSurv  <- Surv(years, status3) ~ age + sex
formConditionalCR <- status4 ~ years + age + sex
survival_fit_all  <- survivalSub(data.survival.fitting,
                                 formMarginalSurv, formConditionalCR)
survival_fit_all   # triggers print.survivalSub.BJM automatically

---

Plot of risk using dynamic prediction

Description

This function gives the risk prediction plot.

Usage

riskPlot(
  data.predict.all.pre,
  long_fit_all,
  survival_fit_all,
  prediction.time = NULL,
  bio_i = NULL,
  horizon,
  time_variable,
  survivalVariableAll,
  survivalTransFunction,
  bandcount1 = 10,
  bandcount2 = 10
)

Arguments

data.predict.all.pre	This involves a collection of data.frame objects for
long_fit_all	Outputs from the model fitting process using the nlme package, encompassing the results and parameters obtained from the analysis.
survival_fit_all	Results and parameters generated from the model fitting procedure, utilizing the coxph function. These outputs include the comprehensive findings and variables derived from the analysis.
prediction.time	Time used to make the prediction.
bio_i	Biomarker used to do prediction.
horizon	Prediction horizon.
time_variable	The name of time variable in linear mixed model.
survivalVariableAll	The name of the transformed time-to-event outcomes variable.
survivalTransFunction	The transformation function used for time-to-event outcomes, in the order of survivalVariableAll.
bandcount1	The number of points used to perform the numerical integral, from the prediction time to the prediction time plus the horizon.
bandcount2	The number of points used to perform the numerical integral, from the prediction time to infinity.

Value

Plot of risk using dynamic prediction.

---

Summary method for dynamicPrediction.BJM objects

Description

Like print but also shows mean, SD, and range of predicted risks.

Usage

## S3 method for class 'dynamicPrediction.BJM'
summary(
  object,
  prediction.time = NULL,
  horizon = NULL,
  subject_ids = NULL,
  digits = 4,
  ...
)

Arguments

object	A dynamicPrediction.BJM object.
prediction.time	Landmark time (for display). Default NULL.
horizon	Prediction horizon (for display). Default NULL.
subject_ids	Optional subject ID labels.
digits	Decimal places. Default 4.
...	Additional arguments (currently unused).

Value

Invisibly returns object.

---

Summary method for dynamicPredictionBio.BJM objects

Description

Like print but also shows distribution-level summaries across subjects.

Usage

## S3 method for class 'dynamicPredictionBio.BJM'
summary(
  object,
  bio_i = NULL,
  long_fit_all = NULL,
  prediction.time = NULL,
  horizon = NULL,
  subject_ids = NULL,
  digits = 4,
  ...
)

Arguments

object	A dynamicPredictionBio.BJM object.
bio_i	Biomarker index (for label lookup). Default NULL.
long_fit_all	longitudinalSub.BJM object for name lookup.
prediction.time	Landmark time (for display). Default NULL.
horizon	Prediction horizon (for display). Default NULL.
subject_ids	Optional subject ID labels.
digits	Decimal places. Default 4.
...	Additional arguments (currently unused).

Value

Invisibly returns object.

---

Summary method for longitudinalSub.BJM objects

Description

Like print but adds per-outcome random-effects variance components and the full correlation matrix of D.

Usage

## S3 method for class 'longitudinalSub.BJM'
summary(object, digits = 4, ...)

Arguments

object	A longitudinalSub.BJM object.
digits	Number of significant digits. Default is 4.
...	Additional arguments (currently unused).

Value

Invisibly returns a list of per-outcome summary.lme objects.

---

Summary method for survivalSub.BJM objects

Description

Called via summary(survival_fit_all). Returns (and prints) an extended summary including baseline hazard range, BIC, and McFadden R2 for the competing-risks GLM.

Usage

## S3 method for class 'survivalSub.BJM'
summary(object, digits = 4, ...)

Arguments

object	A survivalSub.BJM object returned by survivalSub.
digits	Number of significant digits. Default is 4.
...	Additional arguments (currently unused).

Value

Invisibly returns a list with components cox_summary and (if competing risks) glm_summary.

Examples

data(pbc3)
data.survival.fitting <- pbc3[!duplicated(pbc3$id), ]
formMarginalSurv  <- Surv(years, status3) ~ age + sex
formConditionalCR <- status4 ~ years + age + sex
survival_fit_all  <- survivalSub(data.survival.fitting,
                                 formMarginalSurv, formConditionalCR)
summary(survival_fit_all)

---

Fitting survival sub-model

Description

Fitting survival sub-model

Usage

survivalSub(data.survival.fitting, formMarginalSurv, formConditionalCR)

Arguments

data.survival.fitting	Input data containing survival outcomes and baseline covariates.
formMarginalSurv	Survival input formats.
formConditionalCR	Competing risks input formats.

Value

Model fitting results of survival sub-model with or without competing risks.

Examples

data(pbc3)

data.survival.fitting =  pbc3[!duplicated(pbc3$id), ]

formMarginalSurv = Surv(years, status3) ~ age + sex
formConditionalCR = NULL

survival_fit_all = survivalSub(data.survival.fitting, formMarginalSurv, 
                               formConditionalCR)

---