A function to evaluate the generalized cross-validation (GCV) values associated with derivative estimates via Bsplines at a range of specified smoothing parameter (lambda) values
A function to evaluate the generalized cross-validation (GCV) values associated with derivative estimates via Bsplines at a range of specified smoothing parameter (lambda) values
plotGCV(theTimes, norder, roughPenaltyMax, dataMatrix, lowLambda, upLambda, lambdaInt, isPlot)
theTimes |
The time points at which derivative estimation are requested |
norder |
Order of Bsplines - usually 2 higher than roughPenaltyMax |
roughPenaltyMax |
Penalization order. Usually set to 2 higher than the highest-order derivatives desired |
dataMatrix |
Data of size total number of time points x total number of subjects |
lowLambda |
Lower limit of lambda values to be tested. Here, lambda is a positive smoothing parameter, with larger values resulting in greater smoothing) |
upLambda |
Upper limit of lambda |
lambdaInt |
The interval of lambda values to be tested. |
isPlot |
A binary flag on whether to plot the gcv values (0 = no, 1 = yes) |
A data frame containing: 1. lambda values; 2. edf (effective degrees of freedom); 3. GCV (Generalized cross-validation value as averaged across units (e.g., subjects))
Chow, S-M. (2019). Practical Tools and Guidelines for Exploring and Fitting Linear and Nonlinear Dynamical Systems Models. Multivariate Behavioral Research. https://www.nihms.nih.gov/pmc/articlerender.fcgi?artid=1520409
Chow, S-M., *Bendezu, J. J., Cole, P. M., & Ram, N. (2016). A Comparison of Two- Stage Approaches for Fitting Nonlinear Ordinary Differential Equation (ODE) Models with Mixed Effects. Multivariate Behavioral Research, 51, 154-184. Doi: 10.1080/00273171.2015.1123138.
#outMatrix = plotGCV(theTimes,norder,roughPenaltyMax,out2,lambdaLow, #lambdaHi,lambdaBy,isPlot)
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.