Table 5 Linear regression models for the CNS dataset. For each model, we show the coefficients (coeff) calculated by the regression model, the probability (p val) that the variable is not relevant, and the relative importance (LMG) of each regressor computed using the Lindeman, Merenda and Gold method [79]. Gender is a binary variable taking value 1 for females and 2 for males. For this dataset, age is not relevant as all participants have similar age. For each model, we report the \(R^{2}\) goodness of fit, the F-test statistics with the corresponding p-value \(p_{F}\)
From: Understanding the interplay between social and spatial behaviour
| Â | coeff | p val | LMG |
|---|---|---|---|
Model M1: Activity space size, C | |||
 Social circle size, k | 4 ± 0 | <10−50 | 0.94 |
 Gender | −0.4 ± 0.2 | 0.05 | 0.05 |
 Time coverage | 0.4 ± 0.2 | 0.06 | 0.01 |
 [\(R^{2}=0.32\), F = 100.44, \(p_{F}=0.0\) ] | |||
Model M2: Activity space entropy, \(H_{\mathrm{AS}}\) | |||
 Social circle entropy, \(H_{\mathrm{SC}}\) | 0.07 ± 0.01 | <10−6 | 0.42 |
 Gender | −0.06 ± 0.01 | <10−4 | 0.22 |
 Time coverage | −0.07 ± 0.01 | <10−5 | 0.36 |
 [\(R^{2}=0.11\), F = 27.30, \(p_{F}=0.0\)] | |||
Model M3: New locations/week, \(n_{\mathrm{loc}}\) | |||
 New ties/week, \(n_{\mathrm{tie}}\) | 0.60 ± 0.05 | <10−32 | 0.9 |
 Gender | −0.16 ± 0.05 | <10−3 | 0.08 |
 Time coverage | 0.001 ± 0.047 | 1.0 | 0.01 |
 [\(R^{2}=0.22\), F = 61.99, \(p_{F}=0.0\)] | |||
Model M4: Activity space stability, \(J_{\mathrm{AS}}\) | |||
 Social circle stability, \(J_{\mathrm{SC}}\) | 0.024 ± 0.004 | <10−10 | 0.6 |
 Gender | 0.007 ± 0.003 | 0.05 | 0.04 |
 Time coverage | 0.017 ± 0.004 | <10−5 | 0.36 |
 [\(R^{2}=0.16\), F = 33.36, \(p_{F}=0.0\)] | |||
Model M5: Activity space rank turnover, \(R_{\mathrm{AS}}\) | |||
 Social circle rank turnover, \(R_{\mathrm{SC}}\) | 1 ± 0 | <10−56 | 0.98 |
 Gender | 0.12 ± 0.07 | 0.06 | 0.01 |
 Time coverage | −0.12 ± 0.07 | 0.07 | 0.01 |
 [\(R^{2}=0.36\), F = 108.31, \(p_{F}=0.0\)] | |||