Skip to main content

Table 1 Predictor variables in the random forest model

From: Predicting moose behaviors from tri-axial accelerometer data using a supervised classification algorithm

Predictor variable

Number of variables per interval

Mean (X, Y, Z, pitch, MSA)

5

Median (X, Y, Z, pitch, MSA)

5

SD (X, Y, Z, pitch, MSA)

5

Min (X, Y, Z, pitch, MSA)

5

Max (X, Y, Z, pitch, MSA)

5

Range (X, Y, Z, pitch, MSA)

5

Interquartile range (X, Y, Z, pitch, MSA)

5

Absolute value of skew (X, Y, Z, pitch, MSA)

5

Kurtosis (X, Y, Z, pitch, MSA)

5

Girth

1

Length

1

Season

1

Sex

1

Subspecies

1

  1. Predictor variables described either the 3-s interval accelerometer data or the time and location of data collection and morphometrics of the collared moose and were used in the random forest model to predict behaviors from the accelerometer data