Skip to main content

Table 1 Measures used to assess the performance of SDMs in estimating βk

From: Performance of inhomogeneous Poisson point process models under different scenarios of uncertainty in species presence-only data

Measure

Formula

Role

Relative bias in \({\hat{\beta }}_{ki}\)

\({\frac{{\hat{\beta }}_{ki} - \beta _{ki}}{\beta _{ki}}}\times 100\)

Unbiasedness of \({\hat{\beta }}_{ki}\)

Standard deviation of \({\hat{\beta }}_k\)

\(\sqrt{\frac{1}{N-1}{\sum }_{i=1}^{N}({\hat{\beta }}_{ki} - \bar{{\hat{\beta }}}_k)^2}\)

Precision of \({\hat{\beta }}_k\)

RMSE of \({\hat{\beta }}_k\)

\(\sqrt{\frac{1}{N}{\sum }_{i=1}^{N}({\hat{\beta }}_{ki} - \beta _k)^2}\)

Accuracy of \({\hat{\beta }}_k\)

  1. With \({\hat{\beta }}_{k} (k = 0,1)\) the maximum likelihood estimates of the coefficients of \(\log (\lambda (s))\) (see Eq. 1); N is the number of the replications (runs) of the simulation process. In this study, N = 500