Getting Help and Troubleshooting2 days ago
1. Quick Support Matrix | 2. Frequently Asked Questions (FAQ) | Q1: My empirical coverage is slightly below $1 - \alpha$ (e.g. 88.5% instead of 90%). Is my model invalid? | Q2: Should I use scp_geostatistical() or scp_areal()? | Q3: How do spatial bandwidth and $k$-NN affect interval widths? | Q4: Does spconform support spatio-temporal data? | 3. Interpreting the Diagnostic Suite (diagnose()) | 1. Marginal Coverage & Interval Width | 2. Winkler Interval Score (WIS) | 3. Spatial Quadrant Stratification | 4. Convex Hull Boundary Proximity | 5. Spatial Autocorrelation (Moran's $I$) | 4. Model Integration Recipes (pred_fun) | Recipe 1: Random Forest (ranger) | Recipe 2: Generalized Additive Model (mgcv::gam) | Recipe 3: Ordinary Spatial Kriging (gstat) | 5. Troubleshooting Common Errors & Warnings | 1. Coordinate & Dimension Mismatches | Error: s_train and s0 must have the same number of coordinate columns | Issue: Single-point query vector treated as 1D vector instead of 1-row matrix | 2. Missing & Non-Finite Values (NA, NaN, Inf) | Error: s_train cannot contain NA or non-finite values or y_train contains missing values | 3. Custom Predictor (pred_fun) Return Types & Single-Row Drops | Error: pred_fun must return a numeric vector of length nrow(s_new) | 4. Coordinate Reference System (CRS) & Distance Scale Discrepancies | Symptom: Prediction intervals are excessively wide or bandwidth estimation is degenerate | 5. Areal Adjacency Matrix Structural Errors | Error: adjacency must be a square numeric matrix | Warning: Effective neighbourhood weight vanishingly small; falling back to unweighted quantile | 6. Calibration Sample Size vs. Nominal Miscoverage ($\alpha$) | Symptom: Conformal quantile returns the maximum nonconformity score or upper bound is uninformative | 7. Evaluation & Diagnostic Alignment | Error: y_true must have the same length as object$pred | Error: s_test is required for spatial stratification and boundary audits | 8. Graphics Layout & Multi-Panel Plot Devices | Warning: Plot margins too large or layout display clipped in RStudio | 6. Submitting a Minimal Reproducible Example (reprex) | 7. Citation & Academic Reference | 8. Maintainer Contact