Table 5 Forward-looking content of satellite imagery data.

From: Eye in outer space: satellite imageries of container ports can predict world stock returns

 

h = 1

h = 2

h = 3

h = 4

Panel A: Predictive regression for ∆RWI_ISLt+h

∆GNCt

0.037 (0.27)

−0.285** (−2.128)

0.132 (0.99)

−0.052 (−0.376)

∆RWI_ISLt

−0.167 (−1.222)

0.075 (0.558)

0.299** (2.249)

−0.243* (−1.756)

Adjusted R2

2.76%

8.12%

11.85%

6.55%

Panel B: Predictive regression for ∆BDIt+h

∆GNCt

−0.188 (−1.405)

−0.271** (−2.095)

0.163 (1.228)

0.097 (0.716)

∆BDIt

0.092 (0.691)

−0.039 (−0.302)

0.157 (1.183)

−0.151 (−1.128)

Adjusted R2

4.27%

8.05%

5.69%

3.29%

  1. This table provides evidence that growth in the number of containers in the global ports (GNC) predicts a decrease in global container throughput (RWI) and the decrease of freight rate (BDI). The sample period covers from 2017:01 to 2021:10. We report t-statistics based on heteroscedasticity robust standard errors in parentheses. The asterisks ***, **, and * indicate statistical significance at the 1%, 5%, and 10% levels, respectively.
Back to article page