Run Scalar on Function Regression — run

Fit a scalar-on-function regression model. Uses refund::pfr under the hood for computations, and stores results in the mxfda object.

Usage

run_sofr(
  mxFDAobject,
  model_name,
  formula,
  family = "gaussian",
  metric = "uni k",
  r = "r",
  value = "fundiff",
  smooth = FALSE,
  filter_cols = NULL,
  ...,
  knots = NULL
)

Arguments

mxFDAobject: Dataframe of spatial summary functions from multiplex imaging data, in long format. Can be estimated using the function extract_summary_functions or provided separately.
model_name: character string to give the fit model
formula: Formula to be fed to mgcv in the form of outcome ~ x1 + x2. Does not contain functional predictor. Character valued.
family: Exponential family distribution to be passed to mgcv::gam. Defaults to "gaussian". Select "binomial" for binary outcome.
metric: Name of calculated spatial metric to use
r: Character string, the name of the variable that identifies the function domain (usually a radius for spatial summary functions). Default is "r".
value: Character string, the name of the variable that identifies the spatial summary function values. Default is "fundiff".
smooth: Option to smooth data using FPCA. Defaults to FALSE.
filter_cols: a named vector of factors to filter summary functions to in c(Derived_Column = "Level_to_Filter") format
...: Optional other arguments to be passed to fpca.face
knots: Number of knots for defining spline basis.

Value

A list which is a linear or additive functional Cox model fit. See mgcv::gam for more details.

Details

Author

Julia Wrobel julia.wrobel@emory.edu

Alex Soupir alex.soupir@moffitt.org

Examples

#load ovarian mxFDA object
data('ovarian_FDA')

# run scalar on function regression model with a continuous outcome (age)
ovarian_FDA = run_sofr(ovarian_FDA,
                       model_name = "fit_sofr",
                       formula = age~stage,
                       metric = "uni g", r = "r", value = "fundiff")
#> 128 sample have >= 4 values for FPCA; removing 0 samples

# run scalar on function regression model with a binary outcome (stage)
# also known as functional logistic regression
ovarian_FDA = run_sofr(ovarian_FDA,
                       model_name = "fit_sofr",
                       formula = stage~age,
                       family = "binomial",
                       metric = "uni g", r = "r", value = "fundiff")
#> 128 sample have >= 4 values for FPCA; removing 0 samples