One-day-ahead forecast of state of turbulence based on today's economic situation
Research background: In the literature little discussion was made about predicting state of time series in daily manner. The ability to recognize the state of a time series gives, for example, an opportunity to measure the level of risk in a state of tranquility and a state of turbulence independent...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Institute of Economic Research
2018-09-01
|
| Series: | Equilibrium. Quarterly Journal of Economics and Economic Policy |
| Subjects: | |
| Online Access: | http://economic-research.pl/Journals/index.php/eq/article/view/1056 |
| Summary: | Research background: In the literature little discussion was made about predicting state of time series in daily manner. The ability to recognize the state of a time series gives, for example, an opportunity to measure the level of risk in a state of tranquility and a state of turbulence independently, which can provide more accurate measurements of the market risk in a financial institution.
Purpose of the article: The aim of article is to find an appropriate tools to predict, based on today's economic situation, the state, in which time series of financial data will be tomorrow.
Methods: This paper proposes an approach to predict states (states of tranquillity and turbulence) for a current portfolio in a one-day horizon. The prediction is made using 3 different models for a binary variable (Logit, Probit, Cloglog), 4 definitions of a dependent variable (1%, 5%, 10%, 20% of worst realization of returns), 3 sets of independent variables (un-transformed data, PCA analysis and factor analysis). Additionally, an optimal cut-off point analysis is performed. The evaluation of the models was based on the LR test, Hosmer-Lemeshow test, Gini coefficient analysis and CROC criterion based on the ROC curve. The analyses were performed for 43 individual shares and 5 portfolios of shares quoted on the Warsaw Stock Exchange. The study has been conducted for the period from 1 January 2006 to 31 January 2012.
Findings & Value added: Six combinations of assumptions have been chosen as appropriate (any model for a binary variable, the dependent variable defined as 5% or 10% of worst realization of returns, untransformed data, 5% or 10% cut-off point respectively). Models built on these assumptions meet all the formal requirements and have a high predictive and discriminant ability to one-day-ahead forecast of state of turbulence based on today's economic situation. |
|---|---|
| ISSN: | 1689-765X 2353-3293 |