Methods for gam_influence objects
Usage
# S3 method for class 'gam_influence'
print(x, n = 5, ...)
# S3 method for class 'gam_influence'
summary(object, ...)
# S3 method for class 'summary.gam_influence'
print(x, ...)
# S3 method for class 'gam_influence'
as.data.frame(x, row.names = NULL, optional = FALSE, ...)
top_units(x, by = "total", n = 10)Value
print(): thegam_influenceobjectx, unchanged and invisibly. It is called for its side effect of printing the sites with the largest changes and the largest hyperparameter changes.summary(): an object of classsummary.gam_influence, a list withquantiles(a matrix: minimum, median, 90th percentile and maximum offixed,addedandtotal, and the number of missing values),hyper(a data frame: for each hyperparameter, its full-data value and the range of its ratios when a site is removed;NULLif the model has no estimated hyperparameters),n_sites(the number of sites),status(a table of site statuses) andinfo(as ingam_influence()).print()for asummary.gam_influenceobject:x, unchanged and invisibly. It is called for its side effect of printing the summary.as.data.frame(): the site tablex$sites, a data frame with one row per site and columnsid,n_obs,fixed,added,total,statusandnote(seegam_influence()).top_units(): a data frame with the same columns asx$sites, holding thensites with the largestby, largest first.
Examples
library(mgcv)
#> Loading required package: nlme
#> This is mgcv 1.9-4. For overview type '?mgcv'.
set.seed(1)
d <- data.frame(site = factor(rep(1:12, each = 6)), x = runif(72))
d$y <- sin(2 * pi * d$x) + rnorm(12, 0, 0.4)[d$site] + rnorm(72, 0, 0.5)
m <- gam(y ~ s(x) + s(site, bs = "re"), data = d, method = "REML")
infl <- gam_influence(m, cluster = "site", progress = FALSE)
print(infl, n = 3)
#> gamfluence: fixed vs re-estimated deletion, 12 sites
#> model: gaussian (identity), 72 rows
#>
#> Largest total change in the other sites' fitted values (RMS, link scale):
#> id n_obs fixed added total
#> 8 6 0.0576 0.0109 0.0635
#> 9 6 0.0274 0.0467 0.0579
#> 2 6 0.0413 0.0116 0.0442
#>
#> Largest hyperparameter changes when a site is removed:
#> id parameter full deleted ratio
#> 9 s(site) 0.351 0.2500 0.710
#> 8 s(x) 0.021 0.0161 0.767
#> 5 s(x) 0.021 0.0264 1.260
#>
#> fixed = hyperparameters held; added = what re-estimating them adds.
#> No null reference: compare sites with each other.
summary(infl)
#> gamfluence summary: 12 sites
#>
#> min median 90% max NA
#> fixed 0.01510 0.03340 0.0409 0.0576 0
#> added 0.00307 0.00867 0.0116 0.0467 0
#> total 0.01510 0.03830 0.0565 0.0635 0
#>
#> Hyperparameters: full-data value and range of ratios when a site is removed
#> parameter type full min_ratio max_ratio
#> s(site) sd 0.351 0.710 1.07
#> s(x) lambda 0.021 0.767 1.26
#>
#> Status:
#>
#> ok
#> 12
top_units(infl, by = "added", n = 3)
#> id n_obs fixed added total status note
#> 1 9 6 0.02743580 0.04668035 0.05787634 ok <NA>
#> 2 4 6 0.03659087 0.01157631 0.03866023 ok <NA>
#> 3 2 6 0.04125977 0.01155479 0.04416793 ok <NA>
head(as.data.frame(infl))
#> id n_obs fixed added total status note
#> 1 1 6 0.03816118 0.003070984 0.03879776 ok <NA>
#> 2 2 6 0.04125977 0.011554789 0.04416793 ok <NA>
#> 3 3 6 0.01768985 0.003806297 0.01815013 ok <NA>
#> 4 4 6 0.03659087 0.011576310 0.03866023 ok <NA>
#> 5 5 6 0.03147895 0.009073134 0.03789261 ok <NA>
#> 6 6 6 0.03802231 0.008275617 0.04041229 ok <NA>