Back to search

University of Peloponesse

Essays on the econometrics of agricultural subsidies and the forecasting of agricultural time series

Abstract

dc:description

In this thesis, we make a three-fold contribution. First, we introduce a new forecasting methodology, referred to as adaptive learning forecasting, that allows for both forecast averaging and forecast error learning. We analyze its theoretical properties and demonstrate that it provides a priori MSE improvements under certain conditions. The learning rate based on past forecast errors is shown to be non-linear. This methodology is of wide applicability and can provide MSE improvements even for the simplest benchmark models. We illustrate the method’s application using data on agricultural prices for several agricultural products, as well as on real GDP growth for several of the corresponding countries. The time series of agricultural prices are short and show an irregular cyclicality that can be linked to economic performance and productivity, and we consider a variety of forecasting models, both univariate and bivariate, that are linked to output and productivity. Our results support both the efficacy of the new method and the forecastability of agricultural prices. Continuing our research in the agricultural sector, we focus our analysis on the distributional characteristics of Greek agricultural subsidies. The economic impact of agricultural subsidies during and after the time of the 2008 economic crisis appears to be an important issue that merits a particular examination, as subsidies are part of fiscal spending and we are in times of fiscal restraint. Since agricultural subsidies are now decoupled from output or productivity they are a direct income transfer, and their amounts can be staggering. We examine the impact of agricultural subsidies for Greece, using a detailed, micro-panel dataset for four years, 2008, 2010, 2012 and 2014. The fact that Greece went into the worse GDP recession ever, and is on the tightest fiscal policy ever as well, we ask whether these subsidies are meaningful for the generation of growth in the years to come – particularly when in many other areas of the economy European funding has been drastically cut-out. Our analysis is illuminating on at least two aspects of subsidies: first, it suggests that an incentive scheme for promoting larger land size would have a probable positive effect on agricultural value-added; second, that subsidies today produce the larger impact on future value-added for the top two percentiles of the subsidy distribution (i.e. on larger farm-sizes) and thus the first two points combined suggest an “increasing returns to scale” for Greek agricultural via some subsidy incentive scheme. As they stand now, agricultural subsidies are of dubious value, in magnitude and effect, for the Greek economy as it tries to recover from the crisis. In the last part of the thesis, we suggest an intuitive, computationally fast and expedient way of forecasting non-stationary time series using distance-based nearest neighbors (NN); although NN is not a new approach, our application of model-specific distances and the way of implementing the forecasts in this thesis is. Forecasting non-stationary time series in their levels, such as those coming from data generating processes that resemble random walks or unit-roots, is a difficult and sometimes impossible task. The path and scale dependence of such series suggest that transformations to some form of stationarity should be used prior to applying forecasting methods more suitable to stationary time series – but even then we find that many times, such methods cannot beat the simplest benchmark, the naive forecast: the last observation of the time series. We provide a number of theoretical results on the distances used and the properties of the resulting forecasts, and illustrate the efficacy of our method via a comprehensive empirical application on time series of exchange rates and commodities; we show both the forecasting performance enhancements but also the importance of such results in a decision-making context, linking forecasting in levels with management mathematics and predictive analytics problems.

Degree

thesis:*
Grantor dc:publisher
University of Peloponesse
Year dc:date
2019

Author and committee

dc:creator, dc:contributor.*
Authors dc:creator
  • Kyriazi, Foteini
  • Κυριαζή, Φωτεινή

Subjects

dc:subject × 20

Rights

Language dc:language
eng

Identifiers

dc:identifier.*
Identifier
10.12681/eadd/46586

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

Kyriazi, Foteini; Κυριαζή, Φωτεινή. Essays on the econometrics of agricultural subsidies and the forecasting of agricultural time series. University of Peloponesse, 2019. http://hdl.handle.net/10442/hedi/46586