get_bias

root_mean_squared

mean_absolute_error

Functions to calculate different performance metrics.
In the case of get_bias: Calculate the bias b, i.e. the average
difference between predicted y and observed z values:
<div class="sourceCode"></div><pre><code> bias = mean(y - z)
</code></pre>

Run grass growth simulations using a grass growth model based
on ModVege (Jouven, M., P. Carrère, and R. Baumont "Model Predicting
Dynamics of Biomass, Structure and Digestibility of Herbage in Managed
Permanent Pastures. 1. Model Description." (2006)
<doi:10.1111/j.1365-2494.2006.00515.x>). The implementation in
this package contains a few additions to the above cited version of ModVege,
such as simulations of management decisions, and influences of snow cover.
As such, the model is fit to simulate grass growth in mountainous
regions, such as the Swiss Alps. The package also contains routines for
calibrating the model and helpful tools for analysing model outputs and
performance.

Kevin Kramer

growR

Implementation of the Vegetation Model ModVege

get_bias function

<dl><dt>predicted</dt>
<dd>Vector containing the predictions y.</dd>
<dt>observed</dt>
<dd>Vector containing the observations z.</dd>
<dt>...</dt>
<dd>relative Boolean. If true give the result as a ratio to the
average observation <code>mean(ovserved)</code>.</dd></dl>

Arguments

<ul>
<li><code>root_mean_squared()</code>: Calculate the square root of the average squared difference between
prediction and observation:
<div class="sourceCode"></div><pre><code>RMSE = sqrt(sum(predicted - observed)^2) / length(predicted)
</code></pre></li>
<li><code>mean_absolute_error()</code>: Calculate the average of the absolute differences between
prediction and observation:
<div class="sourceCode"></div><pre><code>MAE = mean(abs(predicted - observed))
</code></pre></li>
</ul>

Functions

Functions to calculate different performance metrics.
In the case of get_bias: Calculate the bias b, i.e. the average
difference between predicted y and observed z values:
<div class="sourceCode"><pre><code> bias = mean(y - z)
</code></pre></div>

Metric Functions — get_bias

<dl>

<dt>predicted</dt>
<dd>Vector containing the predictions y.</dd>


<dt>observed</dt>
<dd>Vector containing the observations z.</dd>


<dt>...</dt>
<dd>relative Boolean. If true give the result as a ratio to the
average observation <code>mean(ovserved)</code>.</dd>

</dl>

<ul>
<li><code>root_mean_squared()</code>: Calculate the square root of the average squared difference between
prediction and observation:
<div class="sourceCode"><pre><code>RMSE = sqrt(sum(predicted - observed)^2) / length(predicted)
</code></pre></div></li>
<li><code>mean_absolute_error()</code>: Calculate the average of the absolute differences between
prediction and observation:
<div class="sourceCode"><pre><code>MAE = mean(abs(predicted - observed))
</code></pre></div></li>
</ul>

get_bias: Metric Functions

Description

Usage

Value

Arguments

Functions

See Also

Examples