A New S.D.E. and Instantaneous Mean Reversion Rate Formula (Presented via a Numerical Empirical Model Comparison)

This study examines the stock returns series using Symmetric and Asymmetric GARCH models with structural breaks in the presence of some varying distribution assumptions. Volatility models of Symmetric GARCH (1,1), Asymmetric Power GARCH (1,1) and GJR-GARCH(1,1) models were considered in estimating and measuring shock persistence, leverage effects and mean reversion rate with structural breaks considering dummy variable for these structural changes and varying distributions . The skewed student-t distribution is considered best distribution for the models; moreover findings showed the high persistence of shock in returns series for the estimated models. However, when structural breaks were incorporated in the estimated models by including dummy variable in the conditional variance equations of all the models, there was significant reduction of shock persistence parameter and mean reversion rate. The study found the GJR-GARCH (1,1) with skewed student-t distribution best fit the series. The volatility was forecasted for 12 months period using GJR-GARCH (1,1) model and the values are compared with the actual values and the results indicates a continuous increase in unconditional variance.

Download Full-text

SPEED OF MEAN REVERSION: AN EMPIRICAL ANALYSIS OF KSE, LSE AND ISE INDICES

Technological and Economic Development of Economy ◽

10.3846/20294913.2017.1342286 ◽

2018 ◽

Vol 24 (4) ◽

pp. 1435-1452 ◽

Cited By ~ 2

Author(s):

Rana Imroze Palwasha ◽

Nawaz Ahmad ◽

Rizwan Raheem Ahmed ◽

Jolita Vveinhardt ◽

Dalia Štreimikienė

Keyword(s):

Empirical Analysis ◽

Stock Markets ◽

Research Study ◽

Mean Reversion ◽

Reversion Rate ◽

Trade Off ◽

Stock Indices ◽

Daily Data ◽

The Mean

The purpose of this study is to determine the presence of mean reversion in the stock markets indices of Pakistan, moreover, to measure, and compare the speed of mean reversion of the stock markets indices across Pakistan. In order to carry out the research study, the daily data of three stock indices of Pakistan such as: KSE-100, LSE-25 and ISE-10 are collected from 2003 to 2014. After the application of tests such as ARCH and GARCH, it was found that returns series of KSE-100, LSE-25 and ISE-10 indices exhibit mean reversion, indicating that the returns revert back to their historical value after reaching an extreme value. Further, the mean reversion rate shows that KSE-100 index has the slowest mean reversion, however, the ISE-10 index has the fastest mean reversion among the three indices. Therefore, the results of the study concluded that KSE-100 index, due to the slowest mean reversion rate has higher volatility over a longer period of time. On the contrary, since, ISE-10 index has exhibited the fastest mean reversion with the lowest volatility as compared to others. But due to fast mean reversion rate, it will help investors to gain profits over a shorter period of time. Thus, it can be recommended that the investor willing to bear the risk of time and looking for long-term investment should invest in KSE-100 index. However, investors looking for higher profits in a shorter period can invest in the ISE-10 index but with higher risk-returns trade-off.

Download Full-text

An Empirical Model Comparison for Valuing Crack Spread Options

SSRN Electronic Journal ◽

10.2139/ssrn.1557006 ◽

2011 ◽

Author(s):

Steffen Mahringer ◽

Marcel Prokopczuk

Keyword(s):

Empirical Model ◽

Model Comparison ◽

Spread Options

Download Full-text

A new S.D.E. and instantaneous mean reversion rate formula (presented via a numerical empirical model comparison)

International Journal of Financial Engineering ◽

10.1142/s2424786317500293 ◽

2017 ◽

Vol 04 (02n03) ◽

pp. 1750029

Author(s):

Yedidya Rabinovitz

Keyword(s):

Exchange Rates ◽

Stochastic Models ◽

Goodness Of Fit ◽

Variance Reduction ◽

Model Comparison ◽

Mean Reversion ◽

Rate Model ◽

Empirical Comparison ◽

Variance Reduction Techniques ◽

Reduction Techniques

A new short-rate model and a new explicit instantaneous mean reversion formula are introduced. The introduction is presented via a comparison of various short-rate one factor models, which are calibrated and analyzed numerically via a Monte Carlo simulation. Two variance reduction techniques, Stratified Sampling and the Sobol Algorithm, are compared. An empirical comparison is constructed using criteria of goodness-of-fit, in five exchange rates. The data is ex-ante ultimately measuring the predictability of the stochastic models and variance reduction.

Download Full-text

Empirical model comparison and model tuning for estimating aCDOM in a tropical reservoir in Brazil

2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) ◽

10.1109/igarss.2015.7325865 ◽

2015 ◽

Author(s):

Fernanda Watanabe ◽

Enner Alcantara ◽

Marcelo Curtarelli ◽

Renata Nascimento ◽

Jose Stech ◽

...

Keyword(s):

Empirical Model ◽

Model Comparison ◽

Tropical Reservoir ◽

Model Tuning

Download Full-text

Identifying suboptimalities with factorial model comparison

Behavioral and Brain Sciences ◽

10.1017/s0140525x18001541 ◽

2018 ◽

Vol 41 ◽

Cited By ~ 2

Author(s):

Wei Ji Ma

Keyword(s):

Experimental Design ◽

Model Comparison ◽

Process Models ◽

Multiple Forms ◽

Factorial Experimental Design ◽

Factorial Model ◽

Multiple Components ◽

The Many

AbstractGiven the many types of suboptimality in perception, I ask how one should test for multiple forms of suboptimality at the same time – or, more generally, how one should compare process models that can differ in any or all of the multiple components. In analogy to factorial experimental design, I advocate for factorial model comparison.

Download Full-text