Machakos University Digital RepositoryThe Machakos University digital repository system captures, stores, indexes, preserves, and distributes digital research material.http://ir.mksu.ac.ke:802019-08-17T01:48:13Z2019-08-17T01:48:13ZA Three-Step Nonparametric Estimation of Conditional Value-At-Risk Admitting a Location-Scale ModelTorsen, EmmanuelMwita, Peter N.Mung’atu, Joseph K.http://ir.mksu.ac.ke/handle/123456780/47382019-08-16T08:31:49Z2019-01-01T00:00:00ZA Three-Step Nonparametric Estimation of Conditional Value-At-Risk Admitting a Location-Scale Model
Torsen, Emmanuel; Mwita, Peter N.; Mung’atu, Joseph K.
Financial institutions owners and regulators are concerned majorly
about risk analysis, Value-at-Risk (VaR) is one of the most popular
and common measures of risk used in finance, measures the down-side
risk and is determined for a given probability level. In this paper, we
consider the problem of estimating conditional Value-at-Risk via the
nonparametric method and have proposed a three-step nonparametric
estimator for conditional Value-at-Risk. The returns are assumed to
have a location-scale model where the function of the error innovations is
assumed unknown. The asymptotic properties of the proposed estimator
were established, a simulation study was also conducted to confirm the
properties. Application to real data was carried out, TOTAL stocks
quoted on the Nigerian Stock Exchange using daily closing prices for
covering the period between January 02, 2008 to December 29, 2017
trading days was used to illustrate the applicability of the estimator.
2019-01-01T00:00:00ZConditional scale function estimate in the presence of unknown conditional quantile functionMwita, Peter N.Otieno, Romanus Odhiambohttp://ir.mksu.ac.ke/handle/123456780/47372019-08-16T08:26:21Z2005-01-01T00:00:00ZConditional scale function estimate in the presence of unknown conditional quantile function
Mwita, Peter N.; Otieno, Romanus Odhiambo
Standard approach for modeling and understanding the variability of statistical data or, generally, dependant data, is often based on the mean variance regression models. However, the assumptions employed on standardized residuals may be too restrictive, in particular, when the data follows heavy-tailed distribution with probably infinite variance. This paper considers the problem of nonparametric estimation of conditional scale function of time series, based on quantile regression methodology of Koenker and Bassett (1978). We use a flexible model introduced in Mwita (2003), that makes no moment assumptions, and discuss an estimate which we get by inverting a kernel estimate of the conditional distribution function. We finally prove the consistency and asymptotic normality for the estimate
2005-01-01T00:00:00ZPrediction of the Likelihood of Households Food Security in the Lake Victoria Region of KenyaMwita, Peter N.Otieno, Romanus OdhiamboMasanja, Verdiana GraceMuyanja, Charleshttp://ir.mksu.ac.ke/handle/123456780/47362019-08-16T08:12:13Z2011-01-01T00:00:00ZPrediction of the Likelihood of Households Food Security in the Lake Victoria Region of Kenya
Mwita, Peter N.; Otieno, Romanus Odhiambo; Masanja, Verdiana Grace; Muyanja, Charles
This paper considers the modeling and prediction of households food security status using a
sample of households in the Lake Victoria region of Kenya. A priori expected food security factors
and their measurements are given. A binary logistic regression model derived was fitted to
thirteen priori expected factors. Analysis of the marginal effects revealed that effecting the use of
the seven significant determinants: farmland size, per capita aggregate production, household
size, gender of household head, use of fertilizer, use of pesticide/herbicide and education of
household head, increase the likelihood of a household being food secure. Finally, interpretations
of predicted conditional probabilities, following improvement of significant determinants, are
given
2011-01-01T00:00:00ZNonparametric Estimates for Conditional Quantiles of Time SeriesFranke, JürgenMwita, Peter N.Wang, Weininghttp://ir.mksu.ac.ke/handle/123456780/47352019-08-16T07:06:42Z2014-01-01T00:00:00ZNonparametric Estimates for Conditional Quantiles of Time Series
Franke, Jürgen; Mwita, Peter N.; Wang, Weining
We consider the problem of estimating the conditional quantile of
a time series fYtg at time t given covariates Xt
, where Xt can either exogenous variables or lagged variables of Yt
. The conditional
quantile is estimated by inverting a kernel estimate of the conditional
distribution function, and we prove its asymptotic normality and uniform strong consistency. The performance of the estimate for light
and heavy-tailed distributions of the innovations are evaluated by a
simulation study. Finally, the technique is applied to estimate VaR
of stocks in DAX, and its performance is compared with the existing
standard methods using backtesting.
2014-01-01T00:00:00Z