Learn R Programming

INDperform

Overview

INDperform is an R package for validating the performance of ecological state indicators and assessing the ecological status based on a suite of indicators.

Installation

Install the CRAN version:

install.packages("INDperform")

Or install the development version from GitHub:

# install.packages("devtools")
devtools::install_github("saskiaotto/INDperform")

If you encounter a clear bug, please file a minimal reproducible example on github. For questions email me any time.

Usage

For more information, documentation and examples of use, please see INDperform website at https://saskiaotto.github.io/INDperform/

For guidance on how to apply the functions step-by-step see also the INDperform cheatsheet. We are currently working on the Vignette but if you want more information on the framework for quantifying IND performances and its statistical tools implemented in this package see

Otto, S.A., Kadin, M., Casini, M., Torres, M.A., Blenckner, T. (2018): A quantitative framework for selecting and validating food web indicators. Ecological Indicators, 84: 619-631, doi: https://doi.org/10.1016/j.ecolind.2017.05.045

Important News

In Version 0.2.1, a minor bug with different internal test results under different R versions was fixed by modifying some tests. But this bug did not affect the modelling results or performance of the previous version.

Version 0.2.0 has been released on CRAN 2019-02-10! The new version includes a few internal changes as adjustments to updated packages it depends on. Major changes changes include a new NRMSE calculation based on the standard deviation and back-transformation (see https://www.marinedatascience.co/blog/2019/01/07/normalizing-the-rmse/ for the motivation), an NRMSE stand-alone function (nrmse()) and a function that allows the calculation of the distance matrix averaged across groups (i.e. a weighted distance matrix) (dist_sc_group()). For more information see the news file.

Copy Link

Version

Install

install.packages('INDperform')

Monthly Downloads

23

Version

0.2.2

License

GPL

Issues

Pull Requests

Stars

Forks

Repository

https://github.com/saskiaotto/INDperform

Maintainer

Saskia A. Otto

Last Published

January 9th, 2020

Functions in INDperform (0.2.2)

Calculate the derivatives of the IND response functions and the proportion of pressure range in which the response is significant

cooks_dist_gamm

Calculates the Cook`s distance for Generalized Additive Mixed Models (GAMM)

crit_scores_tmpl

Template of (sub-)criteria and corresponding scoring information

Conditional bootstraps

compare_thresholds

Compare changes in t_var based on different threshold levels.

get_signif_code

Create a code indicating the significance of values given by p_val.

Extract specific outputs from the GAM(M) summary

Extracts the IND~pressure IDs in the tibble.

Score adjustments for sub-criterion 10.1

Distance matrix averaged across group scores

merge_models_ex

Output tibble from the merge_models function

Output tibble from the ind_init function

Score-based distance matrix

Modeling of indicator responses to single pressures with GAMMs

Model output tibble from the model_gam function

Modeling of indicator responses to single pressures with GAMs

Returns a logical vector whether input

Initialization of indicator-pressure models

Food web indicators of the Central Baltic Sea (Bornholm Basin).

loocv_thresh_gam

Leave-One-Out Cross-Validation (LOOCV) procedure for (threshold-)GAMs

Merging two model output tibbles.

Helper functions for plot_model

Visualization of all IND~pressure-model results relevant for the scoring

Modeling of indicator trends

Model output tibble from the model_gamm function

plot_diagnostics

Diagnostic plots for a fitted GAM, GAMM or threshold-GAM(M)

Dendrogram of the cluster analysis.

Place annotations to a specified position

Environmental variables representing pressures for pelagic food webs in the Central Baltic Sea (Bornholm Basin).

Create score-based spie chart

Helper function for plot_spiechart

Pressure variables and their associated pressure types from our example data

select_interaction

Create tibble of all potential pressure combinations to test for interactions.

Scoring of indicator performance

Helper functions for plot_model

Create indicator trend plot

Model output tibble from the model_trend function

Normalized Root Mean Square Error

Summary of indicator performance scores

test_interaction

Test for interactions between 2 pressure variables

plot_statespace_ch

Convex hull plot

Fits a GAM with a threshold-formulation

Compute (partial) autocorrelation functions and test for significance

sort_output_tbl

Rearrange columns in output tibble from IND~pressure modeling functions

plot_statespace_ed

Time series plot of Euclidean distance

Select the best correlation structure in the GAMM

Convex hull in 2-dimensional space

Euclidean distance in state space

INDperform-package

INDperform: Performance validation of ecological state indicators

check_input_vec

Check class and data type of input vector

check_ind_press

Check class and variable names and types of ind and press data

Calculate predicted values and their confidence intervals for GAM(M)s

Alternative method for confidence interval approximations of derivatives

Output tibble after applying all IND~pressure modeling functions

Calculates the Normalized Root Mean Square Error (NRMSE) for a list of models

Score-based cluster analysis

check_input_tbl

Check class, existing variables and data types of input objects