Skip to contents

Generalized additive model analysis for continuous data

Source: R/gam_cont.R
gam_cont.Rd

This function performs analysis using a generalized additive model taking into account all trial data until the arm under study leaves the trial and smoothing over the patient entry index.

Usage

gam_cont(
  data,
  arm,
  alpha = 0.025,
  ci = FALSE,
  smoothing_basis = "tp",
  basis_dim = -1,
  gam_method = "GCV.Cp",
  check = TRUE,
  ...
)

Arguments

data

Data frame with trial data, e.g. result from the datasim_cont() function. Must contain columns named 'treatment', 'response', 'period' and 'j'.

arm

Integer. Index of the treatment arm under study to perform inference on (vector of length 1). This arm is compared to the control group.

alpha

Double. Significance level (one-sided). Default=0.025.

ci

Logical. Indicates whether confidence intervals should be computed. Default=FALSE.

smoothing_basis

String indicating the (penalized) smoothing basis to use. Default="tp" for thin plate regression spline. Available strings are 'tp', 'ts', 'ds', 'cr', 'cs', 'cc', 'sos', 'ps', 'cp', 're', 'mrf', 'gp', and 'so'. For more information see https://stat.ethz.ch/R-manual/R-devel/library/mgcv/html/smooth.terms.html.

basis_dim

Integer. The dimension of the basis used to represent the smooth term. The default depends on the number of variables that the smooth is a function of. Default=-1. For more information see the description of the parameter 'k' in https://stat.ethz.ch/R-manual/R-devel/library/mgcv/html/s.html.

gam_method

String indicating the smoothing parameter estimation method. Default="GCV.Cp". Available strings are 'GCV.Cp', 'GACV.Cp', 'REML', 'P-REML', 'ML', and 'P-ML'. For more information see the description of the parameter 'method' in https://stat.ethz.ch/R-manual/R-devel/library/mgcv/html/gam.html.

check

Logical. Indicates whether the input parameters should be checked by the function. Default=TRUE, unless the function is called by a simulation function, where the default is FALSE.

...

Further arguments passed by wrapper functions when running simulations.

Value

List containing the following elements regarding the results of comparing arm to control:

  • p-val - p-value (one-sided)

  • treat_effect - estimated treatment effect in terms of the difference in means

  • lower_ci - lower limit of the (1-2*alpha)*100% confidence interval

  • upper_ci - upper limit of the (1-2*alpha)*100% confidence interval

  • reject_h0 - indicator of whether the null hypothesis was rejected or not (p_val < alpha)

  • model - fitted model

Author

Pavla Krotka

Examples


trial_data <- datasim_cont(num_arms = 3, n_arm = 100, d = c(0, 100, 250),
theta = rep(0.25, 3), lambda = rep(0.15, 4), sigma = 1, trend = "linear")

gam_cont(data = trial_data, arm = 3, ci = TRUE)
#> $p_val
#> [1] 5.3954e-05
#> 
#> $treat_effect
#> [1] 0.5093378
#> 
#> $lower_ci
#> [1] 0.2529761
#> 
#> $upper_ci
#> [1] 0.7656996
#> 
#> $reject_h0
#> [1] TRUE
#> 
#> $model
#> 
#> Family: gaussian 
#> Link function: identity 
#> 
#> Formula:
#> response ~ as.factor(treatment) + s(j, bs = smoothing_basis, 
#>     k = basis_dim)
#> 
#> Estimated degrees of freedom:
#> 1  total = 5 
#> 
#> GCV score: 0.963449     
#>