The study involves 15 different time series: 11 related to stock markets, divided between advanced economies (USA, Canada, France, Germany, Japan) and developing economies (Brazil, Russia, India, Indonesia, China, and South Africa), and 4 related to commodity indices. The primary objective is to compare the main models (DCC-GARCH, VARMA-GARCH, VARMA-BEKK-GARCH, Diag-BEKK) used in the literature to analyze conditional correlation and its evolution over time, while also identifying the model that provides the best results relative to its complexity. Subsequently, the analysis will focus on the behavior of stock-commodity conditional correlations during 2 crisis periods: the financial crisis that began in 2007-2008 and the COVID-19 pandemic. The potential causes and reasons behind these correlation movements are then investigated.
L'elaborato coinvolge 15 differenti serie storiche: 11 riferite a mercati azionari, divise tra economie avanzate (USA, Canada, Francia, Germania, Giappone) ed economie in sviluppo (Brasile, Russia, India, Indonesia, Cina, e Sud Africa), e 4 riferite a indici di commodity. L'obiettivo è, in primo luogo, quello di ottenere un confronto tra i principali modelli (DCC-GARCH, VARMA-GARCH, VARMA-BEKK-GARCH, Diag-BEKK) usati in letteratura per analizzare la correlazione condizionale e il suo evolversi nel tempo, cercando inoltre di identificare il modello che mostra i risultati migliori, rapportati alla sua complessità. Successivamente, l'analisi si concentrerà sull'andamento delle correlazioni condizionali azioni-commodity durante 2 principali periodi di crisi: la crisi finanziaria scoppiata a partire dal 2007-2008 e la pandemia da COVID-19. Vengono indagate poi le possibili cause e ragioni di tali movimenti nelle correlazioni.
Evolution of the relationship between stock indices and commodity indices: are commodities a valid tool for diversification?
BOZZATO, NICOLA
2023/2024
Abstract
The study involves 15 different time series: 11 related to stock markets, divided between advanced economies (USA, Canada, France, Germany, Japan) and developing economies (Brazil, Russia, India, Indonesia, China, and South Africa), and 4 related to commodity indices. The primary objective is to compare the main models (DCC-GARCH, VARMA-GARCH, VARMA-BEKK-GARCH, Diag-BEKK) used in the literature to analyze conditional correlation and its evolution over time, while also identifying the model that provides the best results relative to its complexity. Subsequently, the analysis will focus on the behavior of stock-commodity conditional correlations during 2 crisis periods: the financial crisis that began in 2007-2008 and the COVID-19 pandemic. The potential causes and reasons behind these correlation movements are then investigated.File | Dimensione | Formato | |
---|---|---|---|
Tesi Bozzato Nicola 880863.pdf
accesso aperto
Dimensione
1.72 MB
Formato
Adobe PDF
|
1.72 MB | Adobe PDF | Visualizza/Apri |
I documenti in UNITESI sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/20.500.14247/24263