Table 2 Associations between individual GSV features and log-transformed walk-to-work rates, all cities combined.
From: Predicting walking-to-work using street-level imagery and deep learning in seven Canadian cities
Predictors | Linear model* | Bayesian random intercepts* |
|---|---|---|
Estimates (95% CrI) | Estimates (95% CrI) | |
Person 1500 OD | 0.44 (0.43 to 0.45) | 0.44 (0.44 to 0.45) |
Person 1500 OD*2 | − 0.03 (− 0.03 to − 0.03) | − 0.03 (− 0.03 to − 0.03) |
Building 1500 IS | − 0.01 (− 0.01 to − 0.01) | − 0.01 (− 0.01 to − 0.01) |
Building 1500 IS*2 | 0.00 (− 0.00 to − 0.00) | 0.00 (− 0.00 to − 0.00) |
Sky 1500 IS | 0.02 (0.02 to 0.03) | 0.02 (0.02 to 0.03) |
Sky 1500 IS*2 | 0.00 (− 0.00 to − 0.00) | 0.00 (− 0.00 to − 0.00) |
Random effects | ||
σ2 | 0.07 | |
τ00 | 0.00 DA_uid | |
ICC | 0 | |
N | 14,330 DA_uid | |
Observations | 191,581 | 191,581 |
R2/R2 adjusted | 0.488/0.488 | 0.488/0.488 |
