Effect of sample size on habitat suitability estimation using random forests: a case of bluegill, Lepomis macrochirus

Free Access

Table 1

The Pearson's correlation coefficient between the averaged habitat suitability and the observed ratio of the presence in all the sample size categories. Statistical significance is indicated by ^* p < 0.05, ^** p < 0.01 and ^*** p < 0.001.

Sample size	Depth	Slope	Temperature	Velocity
50	0.61	0.93^*	0.50	0.79^***
60	0.62	0.93^*	0.51	0.79^***
70	0.62	0.93^*	0.53	0.79^***
80	0.63	0.94^*	0.51	0.79^***
90	0.62	0.93^*	0.53	0.79^***
100	0.63	0.93^*	0.53	0.80^***
200	0.65^*	0.93^*	0.53	0.80^***
300	0.67^*	0.93^*	0.57	0.80^***
400	0.67^*	0.93^*	0.61	0.80^***
500	0.67^*	0.93^*	0.63	0.80^***
600	0.66^*	0.93^*	0.70	0.80^***
700	0.67^*	0.93^*	0.73	0.79^***
800	0.68^*	0.92^*	0.75	0.77^***
900	0.69^*	0.91^*	0.80^*	0.76^***
1000	0.71^*	0.90^*	0.83^*	0.74^**

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.