Decoding economic forecasts: A novel approach to predict trends through long-term time series analysis of transportation data and GDP causal relationships

Variables	Measurements	Source = World Bank Group URL
GDP	In constant US dollars (US$)	https://data.worldbank.org/indicator/NY.GDP.MKTP.KD
AIR	In a million-ton-kilometers	https://data.worldbank.org/indicator/IS.AIR.GOOD.MT.K1
Maritime (SEA)	In TEU	https://data.worldbank.org/indicator/IS.SHP.GOOD.TU

1 TEU = Twenty - Foot Equivalent unit.

The growth rate of air and maritime cargo volume and GDP (Original Data Series).

Table 3.

The results of ADF tests and PP tests for air transport and GDP

ADF test	World		USA		China		Japan		India
ADF test	p-value	Lag	p-value	Lag	p-value	Lag	p-value	Lag	p-value	Lag
GDP	0.943	3	0.356	3	0.981	3	0.946	3	0.99	3
GDP Diff1*	0.015	3	0.055	3	0.631	3	0.045	3	0.052	3
AIR	0.353	3	0.637	3	0.725	3	0.769	3	0.717	3
AIR Diff1	0.021	3	0.354	3	0.058	3	0.01	3	0.364	3
PP test	World		USA		China		Japan		India
GDP	0.976	3	0.485	3	0.99	3	0.987	3	0.99	3
GDP Diff1	0.01	3	0.01	3	0.01	3	0.01	3	0.01	3
AIR	0.250	3	0.633	3	0.849	3	0.340	3	0.492	3
AIR Diff1	0.01	3	0.01	3	0.01	3	0.01	3	0.01	3

1 ADF, augmented Dickey–Fuller; PP, Phillips–Perron.

1 * Diff1 = 1 Sequence of difference.

Table 4.

The results of ADF tests and PP tests for maritime transport and GDP

ADF test	World		USA		China		Japan		India
ADF test	p-value	Lag	p-value	Lag	p-value	Lag	p-value	Lag	p-value	Lag
GDP	0.362	2	0.494	2	0.022	2	0.323	2	0.620	2
GDP Diff1	0.146	2	0.426	2	0.720	2	0.426	2	0.734	2
Maritime	0.850	2	0.735	2	0.444	2	0.541	2	0.99	2
Ma. Diff1	0.020	2	0.574	2	0.077	2	0.032	2	0.429	2
PP test	World		USA		China		Japan		India
GDP	0.075	2	0.388	2	0.924	2	0.41	2	0.655	2
GDP Diff1	0.01	2	0.01	2	0.01	2	0.013	2	0.014	2
Maritime	0.466	2	0.592	2	0.332	2	0.553	2	0.897	2
Ma. Diff1*	0.033	2	0.027	2	0.01	2	0.014	2	0.082	2

1 ADF, augmented Dickey–Fuller; PP, Phillips–Perron.

1 * Ma.Diff1 = 1 Sequence of difference, all data series except for China, where the p-value is <0.05.

The scatter plot of air transport and GDP for Japan.
*Note*: The black dot shows outliers.

Table 5.

The correlation coefficients for the first differences between air transport and GDP

	R	p-value	N
World total	0.679	<0.001	45
USA	0.693	<0.001	45
China	0.405	<0.001	45
Japan	–0.081	<0.001	45
India	0.500	<0.001	45

Table 6.

The correlation coefficient for the first difference between air transport and GDP.

Country	R	p-value	N
Japan	0.2142	0.1627	43

1 After the deduction of outliers’ data.

1 Note: The correlation coefficient is considered insignificant when p-value >0.05.

Table 7.

The correlation coefficients for the first differences of maritime transport and GDP

	R	p-value	N
World Total	0.746	< 0.001	19
USA	0.869	< 0.001	19
China	0.403	*0.070*	19
Japan	0.869	< 0.001	19

1 Note: The correlation coefficient is considered insignificant when the p-value exceeds 0.05.

Table 8.

The results of Granger causality tests for the first differences between air transport and GDP

Area/country	AIR to GDP		GDP to AIR
Area/country	F-value	p-value	F-value	p-value
World total	0.08	0.778	4.841	0.030
USA	3.776	0.055	5.112	0.026
China	0.733	0.572	1.661	0.169
Japan	8.693	0.004	0.566	0.454
India	9.396	4.17E–06	3.634	0.009

Table 9.

The results of Granger causality test for the first differences between maritime transport and GDP

Area/country	Maritime to GDP		GDP to maritime
Area/country	F-value	p-value	F-value	p-value
World total	6.951	<0.001	1.294	0.340
China	1.976	0.147	2.078	0.132
Japan	0.496	0.739	0.794	0.546
India	0.880	0.528	0.237	0.937

Table 10.

IRF between air and maritime traffic volume and GDP for world total

Shock GDP to air	Shock air to GDP	Shock GDP to maritime	Shock maritime to GDP

1 IRF, impulse response function.

References

Authors

Metrics

Articles in this issue

DOI: https://doi.org/10.2478/ijme-2024-0038 | Journal eISSN: 2543-5361 (formerly 2299-9701) | Journal ISSN: 2299-9701

Journal RSS Feed

Language: English

Page range: 174 - 186

Submitted on: Apr 27, 2024

Accepted on: Oct 12, 2024

Published on: Feb 14, 2025

Published by: SGH Warsaw School of Economics

In partnership with: Paradigm Publishing Services

Publication frequency: 4 issues per year

Keywords:

causality,

correlation analysis,

logistics data,

prediction of economic growth

JEL:

F14,

M20,

O18

Related subjects:

Business and economics,

Business management,

Management accounting, financial controlling, cost calculation, investment

© 2025 Makoto Saito, Tetsuaki Oda, Kiminori Gemba, Keiko Kubota, published by SGH Warsaw School of Economics
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Volume 61 (2025): Issue 3 (September 2025)

Decoding economic forecasts: A novel approach to predict trends through long-term time series analysis of transportation data and GDP causal relationships

Figures & Tables

Table 1.

Figure 1.