## ----cran-check, include = FALSE---------------------------------------------- # CRAN limits the whole package check to about 10 minutes, so R CMD check # stops this vignette here, before the package loads, instead of running its # code. R CMD build, pkgdown, r-universe, and CI checks with NOT_CRAN=true run # the full vignette, and the installed vignette always shows the full results. if (nzchar(Sys.getenv("_R_CHECK_PACKAGE_NAME_")) && !identical(Sys.getenv("NOT_CRAN"), "true")) { knitr::knit_exit() } ## ----setup, include = FALSE--------------------------------------------------- library(multiScaleR) library(terra) knitr::opts_chunk$set( collapse = TRUE, comment = "#>", fig.width = 6.5, fig.height = 4.25, warning = FALSE, message = FALSE ) ## ----prepare------------------------------------------------------------------ data("landscape_counts") data("surv_pts") pts <- vect(surv_pts) land_rast <- rast(system.file("extdata", "landscape.tif", package = "multiScaleR")) # bin = TRUE (the default) stores distance-binned summaries for every route inputs <- kernel_prep(pts = pts, raster_stack = land_rast, max_D = 1700, kernel = "gaussian", bin = TRUE, verbose = FALSE) # Starting model: its formula and family carry through to the fit df <- data.frame(landscape_counts, inputs$kernel_dat) start <- glm(counts ~ site + land1 + land2, family = poisson(), data = df) ## ----two-routes--------------------------------------------------------------- # Default backend: refit the GLM at every candidate scale time_refit <- system.time( fit_refit <- multiScale_optim(start, inputs, verbose = FALSE) ) # Analytic backend: scales and coefficients in one likelihood time_profile <- system.time( fit_profile <- multiScale_optim(start, inputs, backend = "profile_glm", n_cores = 1, verbose = FALSE) ) # Sigma, its standard error, and the default 95% interval, in meters est_refit <- summary(fit_refit)$opt_scale est_profile <- summary(fit_profile)$opt_scale scale_table <- data.frame( backend = rep(c("refit", "profile_glm"), each = 2), covariate = c(rownames(est_refit), rownames(est_profile)), rbind(est_refit, est_profile), check.names = FALSE ) knitr::kable(scale_table, digits = 1, row.names = FALSE, col.names = c("Backend", "Covariate", "Sigma (m)", "SE", "Lower", "Upper")) # Seconds each fit took round(c(refit = time_refit[["elapsed"]], profile_glm = time_profile[["elapsed"]]), 2) ## ----predict-refit------------------------------------------------------------ # refit: standard errors that hold the estimated scales fixed se_refit <- predict(fit_refit, se.fit = TRUE, uncertainty = "conditional") round(head(data.frame(expected = se_refit$fit, se = se_refit$se.fit), 3), 2) ## ----predict-refit-joint, error = TRUE---------------------------------------- try({ # refit cannot return a joint interval predict(fit_refit, interval = "confidence", uncertainty = "joint") }) ## ----predict-profile---------------------------------------------------------- # profile_glm: scales and coefficients vary together joint <- predict(fit_profile, interval = "confidence", uncertainty = "joint") round(head(data.frame(expected = joint$fit, se = joint$se.fit, lower = joint$lower, upper = joint$upper), 3), 2) ## ----spline-models------------------------------------------------------------ # Recipe 1: knots and boundaries written out start_knots <- glm(counts ~ site + land1 + splines::ns(land2, knots = c(-0.5, 0.5), Boundary.knots = c(-4, 4)), family = poisson(), data = df) # Recipe 2: R chooses the knots from the data start_df <- glm(counts ~ site + land1 + splines::ns(land2, df = 3), family = poisson(), data = df) # Written-out knots work with the analytic backend fit_knots <- multiScale_optim(start_knots, inputs, backend = "profile_glm", n_cores = 1, verbose = FALSE) ## ----spline-df-error, error = TRUE-------------------------------------------- try({ # The df recipe does not multiScale_optim(start_df, inputs, backend = "profile_glm", n_cores = 1, verbose = FALSE) }) ## ----spline-df-refit---------------------------------------------------------- # The default backend accepts either recipe fit_df <- multiScale_optim(start_df, inputs, verbose = FALSE) # Compare the straight-line model with the two curved ones aic_tab(list(fit_profile, fit_knots, fit_df), mod_names = c("linear", "spline, fixed knots", "spline, df = 3")) ## ----mixed-types-------------------------------------------------------------- # Name each covariate and how to summarize its source layer features <- msr_vars( land1 = kernel_var("land1"), # mean, scale estimated land2 = kernel_var("land2"), # mean, scale estimated rough3 = surface_var("land3", "sa", radius = 300) # roughness within 300 m ) inputs_mix <- kernel_prep(pts = pts, raster_stack = land_rast, max_D = 1700, kernel = "gaussian", scale_vars = features, bin = TRUE, verbose = FALSE) df_mix <- data.frame(landscape_counts, inputs_mix$kernel_dat) start_mix <- glm(counts ~ site + land1 + land2 + rough3, family = poisson(), data = df_mix) # Either backend accepts the fixed-radius metric fit_mix_refit <- multiScale_optim(start_mix, inputs_mix, verbose = FALSE) fit_mix_profile <- multiScale_optim(start_mix, inputs_mix, backend = "profile_glm", n_cores = 1, verbose = FALSE) round(fit_mix_profile$scale_est, 1) # estimated scales (m) round(coef(summary(fit_mix_profile$opt_mod)), 3) # regression table ## ----mixed-types-values, include = FALSE-------------------------------------- beta_mix <- coef(summary(fit_mix_profile$opt_mod)) ## ----bayes-prepare------------------------------------------------------------ # Validate the formula, rows, priors, and bins. Nothing is sampled. bayes_check <- multiScale_bayes(counts ~ site + land1 + land2, inputs = inputs, data = landscape_counts, family = "poisson", method = "prepare") bayes_check ## ----bayes-prepare-error, error = TRUE---------------------------------------- try({ # A term the Bayesian route rejects fails at once multiScale_bayes(counts ~ site + land1 + splines::ns(land2, df = 3), inputs = inputs, data = landscape_counts, family = "poisson", method = "prepare") }) ## ----quick-reference, eval = FALSE-------------------------------------------- # library(multiScaleR) # library(terra) # # # 1. Prepare once. Binned inputs serve every route. # data("landscape_counts"); data("surv_pts") # pts <- vect(surv_pts) # land_rast <- rast(system.file("extdata", "landscape.tif", # package = "multiScaleR")) # inputs <- kernel_prep(pts = pts, raster_stack = land_rast, max_D = 1700, # kernel = "gaussian", bin = TRUE) # df <- data.frame(landscape_counts, inputs$kernel_dat) # start <- glm(counts ~ site + land1 + land2, family = poisson(), data = df) # # # 2. Same model, two routes # fit_refit <- multiScale_optim(start, inputs) # any model class # fit_profile <- multiScale_optim(start, inputs, backend = "profile_glm", # n_cores = 1) # joint intervals # summary(fit_refit)$opt_scale # sigma, SE, symmetric 95% interval (m) # summary(fit_profile)$opt_scale # sigma, SE, 95% interval on the log scale # # # 3. Prediction uncertainty by route # predict(fit_refit, se.fit = TRUE, uncertainty = "conditional") # scales fixed # predict(fit_profile, interval = "confidence", uncertainty = "joint") # scales uncertain # # # 4. Splines: written-out knots for profile_glm, either recipe for refit # start_knots <- glm(counts ~ site + land1 + # splines::ns(land2, knots = c(-0.5, 0.5), # Boundary.knots = c(-4, 4)), # family = poisson(), data = df) # start_df <- glm(counts ~ site + land1 + splines::ns(land2, df = 3), # family = poisson(), data = df) # fit_knots <- multiScale_optim(start_knots, inputs, backend = "profile_glm", # n_cores = 1) # fit_df <- multiScale_optim(start_df, inputs) # aic_tab(list(fit_profile, fit_knots, fit_df), # mod_names = c("linear", "spline, fixed knots", "spline, df = 3")) # # # 5. Mixed covariate types: two estimated scales and one fixed-radius metric # features <- msr_vars( # land1 = kernel_var("land1"), # land2 = kernel_var("land2"), # rough3 = surface_var("land3", "sa", radius = 300) # ) # inputs_mix <- kernel_prep(pts = pts, raster_stack = land_rast, max_D = 1700, # kernel = "gaussian", scale_vars = features, # bin = TRUE) # df_mix <- data.frame(landscape_counts, inputs_mix$kernel_dat) # start_mix <- glm(counts ~ site + land1 + land2 + rough3, # family = poisson(), data = df_mix) # fit_mix_refit <- multiScale_optim(start_mix, inputs_mix) # fit_mix_profile <- multiScale_optim(start_mix, inputs_mix, # backend = "profile_glm", n_cores = 1) # # # 6. Check a Bayesian model without fitting it # bayes_check <- multiScale_bayes(counts ~ site + land1 + land2, # inputs = inputs, data = landscape_counts, # family = "poisson", method = "prepare")