Skip to main content
. 2014 Oct 30;9(10):e111436. doi: 10.1371/journal.pone.0111436

Table 2. Estimated parameter values from a hierarchical logistic regression relating covariates (taxa, parameter estimated, year, journal type, and experimental scale) on the probability a given study accounted for imperfect detection.

Parameter Estimate 95% Credible Interval f b
Year 0.45 a (0.23, 0.66) 0.99
Fish 1.01 (0.01, 2.13) 0.97
Mammals 0.38 (−0.51, 1.49) 0.75
Herps 0.53 (−0.38, 1.50) 0.85
Birds 0.33 (−0.70, 1.22) 0.76
Invertebrates –0.83 (−1.83, 0.16) 0.95
Plants –1.70 (−2.95, −0.35) 0.99
Abundance 0.49 (−0.26, 1.18) 0.90
Occurrence –0.60 (−1.42, 0.14) 0.95
Survival 0.91 (0.23, 1.65) 1.00
Richness –1.10 (−1.81, −0.25) 0.99
Range –0.92 (−2.17, 0.22) 0.94
Scale (1 = community) –0.51 (−1.10, 0.08) 0.95
Spatial extent (1 = landscape) –0.12 (−0.69, 0.45) 0.67
Journal type (1 = single taxon) –0.60 (−1.12, −0.03) 0.98
Detection Covariates
Observer (1 = RKS) 1.33 (0.16, 2.51) 0.98
Fish –0.02 (−1.37, 1.51) 0.52
Mammals –0.68 (−2.02, 0.52) 0.85
Herps 0.83 (−0.52, 2.36) 0.85
Birds –0.62 (−1.80, 0.64) 0.84
Invertebrates –0.14 (−1.70, 1.48) 0.57
Plants –0.21 (−2.35, 1.77) 0.55
a

Bolded parameters had 95% credible intervals that did not overlap 0 and are considered statistically important.

b

Proportion of the parameter’s posterior distribution with same sign as the mean value; values approaching 1 reflect increasing certainty that the parameter is different from 0.