Gaussian Process Panel Modeling
Accuracy Estimates for Predictions
Point Estimates
Confidence Intervals
Covariance Function
Create Leave-persons-out Folds
Cross-validation.
Fit a Gaussian process panel model
Generic Method For Fitting a model
Person-specific mean vectors and covariance matrices
Data Set
Generic Extraction Function
Define a Gaussian process panel model
Define settings for a Gaussian process panel model
Log-Likelihood
Maximum Number of Observations per Person
Mean Function
Number of Observations
Number of Parameters
Number of persons
Number of Predictors
Essential Parameter Estimation Results
Parameter Names
Plotting predictions
Plot a Long Data Frame
GPPM predictions
Predictors Names
Standard Errors
Simulate from a Gaussian process panel model
Summarizing GPPM
Variance-Covariance Matrix
Provides an implementation of Gaussian process panel modeling (GPPM). GPPM is described in Karch, Brandmaier & Voelkle (2020; <DOI:10.3389/fpsyg.2020.00351>) and Karch (2016; <DOI:10.18452/17641>). Essentially, GPPM is Gaussian process based modeling of longitudinal panel data. 'gppm' also supports regular Gaussian process regression (with a focus on flexible model specification), and multi-task learning.