Training Risk Measure Models To Ascertain Which Continents Equity Has The Highest Risk For Investment Based On Randomly Selected Individual Continents Equities Listed On The New York Stock Exchange

Autor: Augustine Kwabena Osei-Fosu, Anthony Kofi Osei-Fosu, Evelyn Dela Gbadago
Jazyk: angličtina
Rok vydání: 2023
Předmět:
DOI: 10.5281/zenodo.7793190
Popis: Countries, institutions, and people from all walks of life, including Africans, have carried the notion that it is riskier to invest in African countries than countries in other continents. The purpose of this study was to affirm/refute this notion as being empirically established or merely born out of imagination and unfounded belief. One metal mining company listed on the New York stock exchange was selected from every continent using a systematic random sampling of period five. All daily stock data was obtained from Yahoo Finance for the period 6/2003 thru 6/2020.The Generalized Autoregressive Conditionally Heteroscedastic (GARCH) model was used for randomly varying volatility. However, the study trained several GARCH for a different order of the GARCH terms σ2, and the ARCH terms ε2, and for different distributions. Based on the AIC and BIC, the GARCH model that best fit the data was GARCH (1,1) based on student-t innovation. Risk measure was estimated using the following three approaches: risk metrics, Block Maxima Method under extreme value situations, and Generalized Pareto Distribution (GPD) for the tail ends of the distribution. None of the approaches or methods used in calculating VaR or conditional VaR (ES) of the stock supported the conventional beliefs and age-long-held purported gospel that African countries are the riskiest in which to invest on earth. The study proceeded to verify if these findings were statistically significant. Analysis of variance (ANOVA) was applied and found that none of the differences established above were statistically significant.
Databáze: OpenAIRE