L-moments based regional flood frequency analysis has been carried out on the seven sites of Punjab, Pakistan. Discordancy measure in terms of L-moments has been used to screen the data on each of the seven sites. Homogeneity of the region has been tested using the L-moments based heterogeneity measure (H). H has been calculated using four parameter Kappa distribution with 500 simulations. In order to find the most suitable distribution for quantile estimates, a number of L-moments based frequency distributions, such as, generalized logistic (GLO), generalized extreme-value (GEV), generalized normal (GNO), Pearson type III (PE3), generalized Pareto (GPA) and five parameter Wakeby (WAK) distribution, have been used. Based on the L-moment ratio diagram and Z DIST statistic, three distributions; GNO, GPA and GEV have been identified as the suitable candidates for regional distribution. Accuracy measures for the estimated regional growth curves and quantiles have been calculated for the three candidate distributions, using Monte Carlo simulations. Simulations study showed that GNO distribution is the robust distribution with GPA as suitable alternative but GEV is not an appropriate distribution for the study area.

An improved husband-wife educational level results in greater reproductive autonomy of the women and an increased use of contraception. The husband's desire for more children, a preference for the sex of the next child, and the woman's poor education attainment level are the main barriers to contraceptive use.

Calculations of local influence curvatures have been well developed when the ordinary least squares method is applied. In this article, we discuss the assessment of local influence under the modified ridge regression. Using a pseudo-likelihood function, we express the normal curvatures of local influence for three useful perturbation schemes in interpretable forms. Two illustrative examples are analyzed by the methodology developed in the article.

No abstract

No abstract

For the problem of estimation of Money demand model of Pakistan, money supply (M 1 ) shows heteroscedasticity of the unknown form. For estimation of such model we compare two adaptive estimators with ordinary least squares estimator and show the attractive performance of the adaptive estimators, namely, nonparametric kernel estimator and nearest neighbour regression estimator. These comparisons are made on the basis standard errors of the estimated coefficients, standard error of regression, Akaike Information Criteria (AIC) value, and the Durban-Watson statistic for autocorrelation. We further show that nearest neighbour regression estimator performs better when comparing with the other nonparametric kernel estimator.

In this paper we compare the performance of different GARCH models such as GARCH, EGARCH, GJR and APARCH models, to characterize and forecast financial time series volatility in Pakistan. The comparison is carried out by comparing symmetric and asymmetric GARCH models with normal and fat-tailed distributions for the innovations, over short and long forecast horizons. The forecasts are evaluated according to a set of statistical loss functions. Daily data on the Karachi Stock Exchange (KSE) 100 index are analyzed. The empirical results demonstrate that the use of asymmetry in the GARCH models and the assumption of fat-tail distributions for the innovations improve the volatility forecasts. Overall, EGARCH fits the best while the GJR model, with both normal and non-normal innovations, seems to provide superior forecasting ability over short and long horizons.

adaptive estimator is presented by using probability weighted moments as weights rather than conventional estimates of variances for unknown heteroscedastic errors while estimating a heteroscedastic linear regression model. Empirical studies of the data generated by simulations for normal, uniform, and logistically distributed error terms support our proposed estimator to be quite efficient, especially for small samples.