Back to search

University of the Aegean

Εφαρμοσμένες τεχνικές οικονομετρικής προβλεψιμότητας στις ναυτιλιακές αγορές

Abstract

dc:description

Econometrics constitutes a modern science, which has as aim to study, analyze and to interpret complicated economical phenomena, through sophisticated models and applications. Shipping, as science and as a field of economic activation is considered as one of the most dynamic and complicated industries in the world economy. Many researchers have dealt with the decipherment of shipping markets. More specifically, the growth of applied econometrics provides many tools the recent years, in order to analyse the dynamics of shipping industry in more rational way. However, there are many studies, where each researcher is only focused in a limited number of models, without the examination and the interpretation of remaining econometric models. Still, each model is applied in a limited sample of data and consequently it isn’t consistent to use the estimated results in order to draw general conclusions. This doctoral thesis examines analytically the most important models of applied econometrics, which are summarised in three basic categories, dynamic multiple regressions, multiple equation models and univariate time-series models. This extensive research realises a completed and systematic econometric analysis, using a lot of various models in order to compare and to propose specific quantitative economic relations, which are developed among the four shipping markets (freight market, second-hand market, newbuilding market and scrap market). Analysis also uses the estimates and the results of models in order to generate forecasts so much in the sample as beyond the original estimation period. The estimation sample includes monthly observations from the beginning of 70’s until the beginning of 2011. Forecasts are the cornerstone of econometric analysis, where they presuppose the precise and equitable determination of quantitative relations per shipping market. For this reason, the forecasts, which are examined, are separated in three basic categories, historical simulation, ex post and ex ante. Thus, the models are evaluated according to their forecasting accuracy and also are categorized according to their predicting errors. In this way, it can be determined which models are more suitable for rational decision-making policy and especially for policy analysis from participants in the shipping industry. More specifically, this econometric analysis and the generated forecasts are not limited in one shipping market or a type of vessel, but they extend according to a disaggregated analysis in all shipping markets in both the markets of tankers and bulk carriers. In this way, it is presented the whole picture of shipping industry with the particular characteristics that each market and each type of vessel develops during the years. The results of estimation show that in most of cases, multiple equation models give more precise forecasts concerning the other categories of econometric models. This conclusion reveals the relation of interdependence and feedback which exists among the shipping markets. Also, the univariate time-series models give better forecasting performance only in cases where there is intense volatility of variables. All these conclusions give critical information about the future development of each shipping market, which is also examined also by the ex ante forecasts. Apart from the previous analysis of the three categories of forecasts, the research achieves through the theory of combining forecasts to decrease even more the forecast errors. Consequently, the thesis proposes an exploitable methodology and a practical forecasting tool for the prices of shipping markets in case of bulk shipping market.

Degree

thesis:*
Grantor dc:publisher
University of the Aegean
Year dc:date
2012

Author and committee

dc:creator, dc:contributor.*
Authors dc:creator
  • Γεόμελος, Νικόλαος
  • Geomelos, Nikolaos

Subjects

dc:subject × 18

Rights

Language dc:language
gre

Identifiers

dc:identifier.*
Identifier
10.12681/eadd/27656

Chain of custody

source
Harvested from
Greek National Archive of PhD Theses
Base URL
phdtheses.ekt.gr/eadd_oai/request
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Γεόμελος, Νικόλαος; Geomelos, Nikolaos. Εφαρμοσμένες τεχνικές οικονομετρικής προβλεψιμότητας στις ναυτιλιακές αγορές. University of the Aegean, 2012. http://hdl.handle.net/10442/hedi/27656