A S4 class to represent the results of MGWRSAR, TDS-MGWR and related spatial models.
Betavmatrix. The estimated varying coefficients, dimension (n, kv).
Betacnumeric. The estimated constant coefficients, length kc.
Modelcharacter. The type of model (e.g., "GWR", "MGWR", "SAR", "tds_mgwr").
fixed_varscharacter. A vector with names of spatially constant covariates.
Ynumeric. The dependent variable.
XCmatrix. The explanatory variables with constant coefficients.
XVmatrix. The explanatory variables with varying coefficients.
Xmatrix. All explanatory variables.
WMatrix. The spatial weight matrix for spatial dependence (row-standardized).
isgcvlogical. Indicates if Leave-One-Out Cross-Validation (LOOCV) has been computed.
edfnumeric. The estimated effective degrees of freedom.
formulaformula. The model formula.
datadata.frame. The dataframe used for computation.
Methodcharacter. The estimation technique for spatial dependence models ('2SLS' or 'B2SLS'). Default is '2SLS'.
coordsmatrix. The spatial coordinates of observations.
Hnumeric. The bandwidth vector (spatial).
Htnumeric. The bandwidth vector (temporal), if applicable.
kernelscharacter. The kernel type(s) used (e.g., 'gauss', 'bisq').
adaptivelogical. Indicates if an adaptive kernel (nearest neighbors) was used.
Typecharacter. The type of Generalized Kernel Product ('GD' for spatial, 'GDT' for spatio-temporal).
TPnumeric. Indices of target points (if a subset was used).
SSRtpnumeric. The residual sum of squares calculated only on target points.
SSRnumeric. The total residual sum of squares.
residualsnumeric. The vector of residuals.
fitnumeric. The vector of fitted values.
prednumeric. The vector of predicted values (out-of-sample).
sevmatrix. Local standard errors of varying coefficients.
senumeric. Standard errors of constant coefficients.
tSnumeric. The trace of the Hat matrix (effective number of parameters).
Shatmatrix. The Hat matrix (or approximation).
R_klist. List of partial Hat matrices by covariate (for MGWR inference).
h_wnumeric. The bandwidth value used for computing the spatial weight matrix W. Default is 0.
kernel_wcharacter. The kernel type used for computing W. Default is NULL.
RMSEnumeric. Root Mean Square Error (on training data).
RMSEtpnumeric. Root Mean Square Error computed on target points.
CVnumeric. Leave-One-Out Cross-Validation score.
AICnumeric. Akaike Information Criterion.
AICcnumeric. Corrected Akaike Information Criterion.
AICctpnumeric. Corrected AIC for target points.
BICnumeric. Bayesian Information Criterion.
R2numeric. R-squared.
R2_adjnumeric. Adjusted R-squared.
get_tslogical. Indicates if the trace of the Hat matrix (Tr(S)) was stored.
NNnumeric. The maximum number of neighbors used for weight computation (truncation parameter).
ncorenumeric. Number of CPU cores used.
mycallcall. The original function call.
ctimenumeric. Computation time in seconds.
HRMSEmatrix. History of RMSE values (for iterative algorithms like backfitting).
HBETAlist. History of estimated Beta coefficients at each iteration.
logliknumeric. Log-likelihood value.
Glist. List containing neighboring indices and distances (knn object).
Vnumeric. Sequence of spatial bandwidths tested (for TDS algorithms).
Vtnumeric. Sequence of temporal bandwidths tested (for TDS algorithms).
Znumeric. Temporal or auxiliary variable for GDT kernel type.
TSnumeric. Diagonal elements of the Hat Matrix.
alphanumeric. Ratio parameter for GDT kernels (balancing space and time).
HMmatrix. Matrix of optimal bandwidths per covariate (for TDS).
HKminnumeric. Minimum allowed bandwidth per covariate (for TDS).
HKMINlist. List of minimum bandwidths per covariate for spatio-temporal models (TDS).
isolated_idxnumeric. Indices of observations without sufficient neighbors.
my_crsANY. Coordinate Reference System (CRS) information.