Traditional Parametric Methods Research Articles

The heterogeneity of informal employment and segmentation in the Turkish labour market

This paper aims at investigating the heterogeneity of informal employment on the Turkish labour market. To circumvent the constraints imposed by the traditional parametric methods, finite mixture models are estimated in order to identify the optimal number of segments within the informal employment and their respective returns to individual characteristics. In particular, it sheds light on the potential voluntary nature of informal employment by comparing the estimated probabilities of segment membership with the theoretical probabilities that would result from a competitive labour market under the hypothesis of income maximization by workers. Results show that the classical self-employed versus informal wage-workers divide is not the best split of informal employment. Furthermore, the two estimated informal employment segments are both less desirable than formal employment. Thus, the hypothesis of labour-market segmentation, even after taking informal-sector heterogeneity into account, seems to hold, supporting the traditional dualistic view of informal employment in the Turkish context.

Reevaluación del comportamiento del curso temporal del efecto de propofol descrito por el modelo farmacocinético de Schnider

BackgroundThe first order plasma–effect-site equilibration rate constant (ke0) links the pharmacokinetics (PK) and pharmacodynamics (PD) of a given drug. This constant, calculated for each specific PK drug model, allowed us to predict the course of the effect in a target controlled infusion (TCI). The PK-PD model of propofol, published by Schnider et al., calculated a ke0 value of 0.456min−1 and a corresponding time to peak effect (t peak) of 1.6min. The aim of this study was to reevaluate the ke0 value for the predicted Schnider model of propofol, with data from a complete effect curve obtained by monitoring the bispectral index (BIS). MethodsThe study included 35 healthy adult patients (18-90 years) scheduled for elective surgery with standard monitoring and using the BIS XP® (Aspect), and who received a propofol infusion to reach a plasma target of 12 μg/ml in 4min. The infusion was then stopped, obtaining a complete effect curve when the patient woke up. The Anestfusor™ (University of Chile) software was used to control the infusion pumps, calculate the plasma concentration plotted by Schnider PK model, and to store the BIS data every second. Loss (LOC) and recovery (ROC) of consciousness was assessed and recorded. Using a traditional parametric method using the “ke0 Objective function” of the PK-PD tools for Excel, the individual and population ke0 was calculated. Predictive Smith tests (Pk) and Student t test were used for statistical analysis. A P<.05 indicated significance. ResultsThe evaluation included 21 male and 14 female patients (18 to 90 years). We obtained 1,001 (±182) EEG data and the corresponding calculated plasma concentration for each case. The population ke0 obtained was 0.144min−1 (SD±0.048), very different from the original model (P<.001). This value corresponds with a t peak of 2.45min. The predictive performance (Pk) for the new model was 0.9 (SD±0.03), but only 0.78 (SD±0.06) for the original (P<.001). With a baseline BIS of 95.8 (SD±2.34), the BIS at LOC was 77.48 (SD±9.6) and 74.65(SD±6.3) at ROC (P=.027). The calculated Ce in the original model at LOC and ROC were 5.9 (SD±1.35)/1.08 μg/ml (SD±0.32) (P<.001), respectively, and 2.3 (SD±0.63)/2.0 μg/ml (SD±0.65) (NS) for the new model. The values between LOC/ROC were significantly different between the 2 models (P<.001). No differences in ke0 value were found between males and females, but in the new model the ke0 was affected by age as a covariable (0.26-[age×0.0022]) (P<.05). ConclusionsThe dynamic relationship between propofol plasma concentrations predicted by Schnider's pharmacokinetic model and its hypnotic effect measured with BIS was better characterized with a smaller ke0 value (slower t½ke0) than that present in the original model, with an age effect also not described before.

Using BS-PSD-LDA approach to measure operational risk of Chinese commercial banks

The research of operational risk management among Chinese commercial banks is still in its preliminary stage. Operational risk events are rare and data is hard to collect. This leads to very small data samples. Besides, a large number of empirical researches show that the distributions of operational losses are often skewed with fat tails. To address these issues, this paper puts forward a loss distribution approach (LDA) based on bootstrap sampling and piecewise-defined severity distribution (BS-PSD-LDA). The approach divides data samples into two distinct parts (high-frequency low-severity losses and low-frequency high-severity losses), and fits the two parts by lognormal distribution and Generalized Pareto distribution respectively. Using hand-collected samples of 426 operational losses in Chinese commercial banks during 1994–2010, we estimate the magnitude of operational losses using the BS-PSD-LDA method. We show that our method provides a better fit than the traditional parametric methods. Besides, the method using historical simulation of nonparametric method seems to offer a good fit to the sample as well. However, we believe that the BS-PSD-LDA approach offers improvement from the perspective of satisfying risk control requirement of the regulatory authority and ensuring the efficiency of funds' utilization.

Solution method of overtopping risk model for earth dams

Hydrologic risk analysis relies on a series of probabilistic analyses, and it is a complex problem in estimating the probability distributions of multiple independent and random variables. The goal of this study is to presents the procedure and application of a probability-based risk analysis methodology to evaluate earth dam overtopping risk that induced by concurrent flood and wind. The uncertainty arising from initial water surface level, flood, wind velocity, and dam height are discussed in this research. The improved Monte Carlo simulation and mean-value first-order second-moment method are used to solve the proposed dam overtopping risk model, respectively. The nonparametric kernel density estimation method, which can better learn the complex multimodal characteristic of probability density function than that of traditional parametric estimation method, is employed to improve the probability density function of initial water surface level. The latin hypercube sampling is introduced to generate uniform random number, which improves the efficient and stability compared with simple random sampling. Afterward, an application to the Dongwushi Reservoir in China illustrates that the dam overtopping risk computed using the improved Monte Carlo simulation is lower than that using mean-value first-order second-moment method. Furthermore, the sensitivity analysis show that initial water surface level is more sensitive to overtopping risk than wind velocity.

Gene Variation in Resistant Hypertension: Multilocus Analysis of the Angiotensin 1-Converting Enzyme, Angiotensinogen, and Endothelial Nitric Oxide Synthase Genes

Resistant hypertension, a complex multifactorial hypertensive disease, is triggered by genetic and environmental factors and involves multiple physiological pathways. Single genetic variants may not reveal significant associations with resistant hypertension because their effects may be dependent on gene-gene or gene-environment interactions. We examined the interaction of angiotensin I-converting enzyme (ACE), angiotensinogen (AGT), and endothelial nitric oxide synthase (NOS3) polymorphisms with environmental factors (gender, age, body mass index, glycemia, total cholesterol, low-density lipoprotein cholesterol, high-density lipoprotein cholesterol, triglycerides, estimated glomerular filtration rate, and urinary sodium excretion) in 70 resistant, 80 well-controlled hypertensive patients, and 70 normotensive controls. All subjects were genotyped for ACE insertion/deletion (rs1799752); AGT M235T (rs699), and NOS3 Glu298Asp (rs 1799983). Multifactorial associations were tested using two statistical methods: the traditional parametric method (adjusted logistic regression analysis) and gene-gene and gene-environment interactions evaluated by multifactor dimensionality reduction analyses. While adjusted logistic regression found no significant association between the studied polymorphisms and controlled or resistant hypertension, the multifactor dimensionality reduction analyses showed that carriers of the AGT 235T allele were at increased risk for resistant hypertension, especially if they were older than 50 years. The AGT 235T allele constituted an independent risk factor for resistant hypertension.

Nonparametric Rank Regression for Analyzing Water Quality Concentration Data with Multiple Detection Limits

Environmental data usually include measurements, such as water quality data, which fall below detection limits, because of limitations of the instruments or of certain analytical methods used. The fact that some responses are not detected needs to be properly taken into account in statistical analysis of such data. However, it is well-known that it is challenging to analyze a data set with detection limits, and we often have to rely on the traditional parametric methods or simple imputation methods. Distributional assumptions can lead to biased inference and justification of distributions is often not possible when the data are correlated and there is a large proportion of data below detection limits. The extent of bias is usually unknown. To draw valid conclusions and hence provide useful advice for environmental management authorities, it is essential to develop and apply an appropriate statistical methodology. This paper proposes rank-based procedures for analyzing non-normally distributed data collected at different sites over a period of time in the presence of multiple detection limits. To take account of temporal correlations within each site, we propose an optimal linear combination of estimating functions and apply the induced smoothing method to reduce the computational burden. Finally, we apply the proposed method to the water quality data collected at Susquehanna River Basin in United States of America, which clearly demonstrates the advantages of the rank regression models.

The permutation testing approach: a review

In recent years permutation testing methods have increased both in number of applications and in solving complex multivariate problems. A large number of testing problems may also be usefully and effectively solved by traditional parametric or rank-based nonparametric methods, although in relatively mild conditions their permutation counterparts are generally asymptotically as good as the best ones. Permutation tests are essentially of an exact nonparametric nature in a conditional context, where conditioning is on the pooled observed data as a set of sufficient statistics in the null hypothesis. Instead, the reference null distribution of most parametric tests is only known asymptotically. Thus, for most sample sizes of practical interest, the possible lack of efficiency of permutation solutions may be compensated by the lack of approximation of parametric counterparts. There are many complex multivariate problems (quite common in biostatistics, clinical trials, engineering, the environment, epidemiology, experimental data, industrial statistics, pharmacology, psychology, social sciences, etc.) which are difficult to solve outside the conditional framework and outside the nonparametric combination (NPC) method for dependent permutation tests. In this paper we review this method along with a number of applications in different experimental and observational situations (e.g. multi-sided alternatives, zero-inflated data and testing for a stochastic ordering) and we present properties specific to this methodology, such as: for a given number of subjects, when the number of variables diverges and the noncentrality of the combined test diverges accordingly, then the power of combination-based permutation tests converges to one.

Two New Covariate Adjustment Methods for Non-Inferiority Assessment of Binary Clinical Trials Data

In clinical trials, examining the adjusted treatment difference has become the preferred way to establish non-inferiority (NI) in cases involving a binary endpoint. However, current methods are inadequate in the area of covariate adjustment. In this paper, we introduce two new methods, nonparametric and parametric, of using the probability and probability (P-P) curve to address the issue of unadjusted categorical covariates in the traditional assessment of NI in clinical trials. We also show that the area under the P-P curve is a valid alternative for assessing NI using the adjusted treatment difference, and we compute this area using Mann–Whitney nonparametric statistics. Our simulation studies demonstrate that our proposed methods can not only control type I error at a predefined significance level but also achieve higher statistical power than those of traditional parametric and nonparametric methods that overlook covariate adjustment, especially when covariates are unbalanced in the two treatment groups. We illustrate the effectiveness of our methodology with data from clinical trials of a therapy for coronary heart disease.

Evidence for epistatic interactions in antiepileptic drug resistance

To investigate the epistatic interactions involved in antiepileptic drug (AED) resistance, 26 coding single-nucleotide polymorphisms (SNPs) were selected from 16 candidate genes. A total of 200 patients with drug-resistant localization-related epilepsy and 200 patients with drug-responsive localization-related epilepsy were genotyped individually for the SNPs. Rather than using the traditional parametric statistical method, a new statistical method, multifactor dimensionality reduction (MDR), was used to determine whether gene-gene interactions increase the risk of AED resistance. The MDR method indicated that a combination of four SNPs (rs12658835 and rs35166395 from GABRA1, rs2228622 from EAAT3 and rs2304725 from GAT3) was the best model for predicting susceptibility to AED resistance with a statistically significant testing accuracy of 0.625 (P < 0.001) and cross-validation consistency of 10/10. This best model had an odds ratio of 3.68 with a significant 95% confidence interval of 2.32-5.85 (P < 0.0001). Our results may provide meaningful information on the mechanism underlying AED resistance and, to the best of our knowledge, this is the first report of evidence for gene-gene interactions underlying AED resistance.

Maintainability analysis considering time-dependent and time-independent covariates

Traditional parametric methods for assessing maintainability most often only consider time to repair (TTR) as a single explanatory variable. However, to predict availability more precisely for high availability systems, a better model is needed to quantify the effect of operational environment on maintainability. The proportional repair model (PRM), which is developed based on proportional hazard model (PHM), may be used to analyze maintainability in the present of covariates. In the PRM, the effect of covariates is considered to be time independent. However this assumption may not be valid for some situations. The aim of this paper is to develop the Cox regression model and its extension in the presence of time-dependent covariates for determining maintainability. A simple case study is used to demonstrate how the model can be applied in a real case.

Testing the Homogeneity of Two Survival Functions Against a Mixture Alternative Based on Censored Data

When the survival distribution in a treatment group is a mixture of two distributions of the same family, traditional parametric methods that ignore the existence of mixture components or the nonparametric methods may not be very powerful. We develop a modified likelihood ratio test (MLRT) for testing homogeneity in a two sample problem with censored data and compare the actual type I error and power of the MLRT with that nonparametric log-rank test and parametric test through Monte-Carlo simulations. The proposed test is also applied to analyze data from a clinical trial on early breast cancer.

Comparison of bootstrap and generalized bootstrap methods for estimating high quantiles

The generalized bootstrap is a parametric bootstrap method in which the underlying distribution function is estimated by fitting a generalized lambda distribution to the observed data. In this study, the generalized bootstrap is compared with the traditional parametric and non-parametric bootstrap methods in estimating the quantiles at different levels, especially for high quantiles. The performances of the three methods are evaluated in terms of cover rate, average interval width and standard deviation of width of the 95% bootstrap confidence intervals. Simulation results showed that the generalized bootstrap has overall better performance than the non-parametric bootstrap in high quantile estimation.

Estimated breeding values and association mapping for persistency and total milk yield using natural cubic smoothing splines

BackgroundFor dairy producers, a reliable description of lactation curves is a valuable tool for management and selection. From a breeding and production viewpoint, milk yield persistency and total milk yield are important traits. Understanding the genetic drivers for the phenotypic variation of both these traits could provide a means for improving these traits in commercial production.MethodsIt has been shown that Natural Cubic Smoothing Splines (NCSS) can model the features of lactation curves with greater flexibility than the traditional parametric methods. NCSS were used to model the sire effect on the lactation curves of cows. The sire solutions for persistency and total milk yield were derived using NCSS and a whole-genome approach based on a hierarchical model was developed for a large association study using single nucleotide polymorphisms (SNP).ResultsEstimated sire breeding values (EBV) for persistency and milk yield were calculated using NCSS. Persistency EBV were correlated with peak yield but not with total milk yield. Several SNP were found to be associated with both traits and these were used to identify candidate genes for further investigation.ConclusionNCSS can be used to estimate EBV for lactation persistency and total milk yield, which in turn can be used in whole-genome association studies.

Evaluating state tax revenue variability: a portfolio approach

This article develops a volatility model based on portfolio theory to examine state tax revenue variability. Unlike traditional parametric methods used to analyse state tax revenue variability, the portfolio approach allows the computation of a tax's share of total tax revenue that minimizes the overall variability in total state tax revenue given a state's portfolio of tax revenue sources. The model can thus be used to evaluate how closely a state's revenue portfolio is constructed to minimize variability in total state tax revenue. An empirical application of the model is conducted on a sample of US states. The volatility model presented here serves as a useful complement to parametric techniques that have been used to estimate tax revenue variability.

A new method for solving the problem of the mean estimation when the underlying regression function is discontinuous

In the context of finite population survey sampling, we propose a new model-based mean estimator, when the function that links the variables is discontinuous. The available estimators of the mean based on nonparametric regression are derived under the assumption that the regression function is continuous. We propose a new approach to adjust for the effect of discontinuity on regression estimation of the mean. The performance of the proposed estimator is analysed through a simulation study because the theoretic study of asymptotics is not possible. In the literature, the new estimator requires more computational cost than others, but the simulation experiments indicate that the proposed method has higher efficiency than other traditional parametric and nonparametric regression methods.

Estimation of the plasma–effect-site equilibration rate constant (ke0) of rocuronium by the time of maximum effect: a comparison with non-parametric and parametric approaches

The first order plasma-effect-site equilibration rate constant (k(e0)) links the pharmacokinetics (PK) and pharmacodynamics (PD) of a given drug. For the calculation of the k(e0), one method uses a single point of the response curve corresponding to the time to peak effect of a drug (t(peak)); however, it has not been validated. This study compares the k(e0) calculated with the method of t(peak) and the k(e0) calculated with traditional non-parametric and parametric methods. Fifteen adult patients receiving total intravenous anaesthesia (TIVA) were studied. All patients were monitored with an NMT Monitor 221 (GE Healthcare, Helsinki, Finland) to obtain the evoked compound EMG of the adductor pollicis to a train-of-four stimuli at 10 s intervals. During TIVA, rocuronium 0.15 mg kg(-1) was given i.v. as a bolus, and the neuromuscular response was recorded until recovery from block. Using the t(peak) and the complete response curve, k(e0) of rocuronium was calculated with the three methods using the predicted plasma concentrations of rocuronium from a PK model. Values of k(e0) are median (range). The k(e0)s obtained were 0.19 min(-1) (0.09-0.72) with the 't(peak)' method, 0.20 min(-1) (0.14-0.44) with the non-parametric method, and 0.19 min(-1) (0.11-0.38) [typical value (range)] with the parametric method (NS). If the t(peak) can be adequately estimated from the data, the 't(peak) method' is a valid alternative to traditional methods to calculate the k(e0).

Comparing cost prediction models by resampling techniques

The accurate software cost prediction is a research topic that has attracted much of the interest of the software engineering community during the latest decades. A large part of the research efforts involves the development of statistical models based on historical data. Since there are a lot of models that can be fitted to certain data, a crucial issue is the selection of the most efficient prediction model. Most often this selection is based on comparisons of various accuracy measures that are functions of the model’s relative errors. However, the usual practice is to consider as the most accurate prediction model the one providing the best accuracy measure without testing if this superiority is in fact statistically significant. This policy can lead to unstable and erroneous conclusions since a small change in the data is able to turn over the best model selection. On the other hand, the accuracy measures used in practice are statistics with unknown probability distributions, making the testing of any hypothesis, by the traditional parametric methods, problematic. In this paper, the use of statistical simulation tools is proposed in order to test the significance of the difference between the accuracy of two prediction methods: regression and estimation by analogy. The statistical simulation procedures involve permutation tests and bootstrap techniques for the construction of confidence intervals for the difference of measures. Four known datasets are used for experimentation in order to validate the results and make comparisons between the simulation methods and the traditional parametric and non-parametric procedures.

A basin wide stochastic salinity model

Summary In the western United States many rivers experience high salinity resulting from natural and anthropogenic sources. This impacts the water quality and hence, is closely monitored. The salinity is closely linked with streamflow quantity in that, a higher flow brings with it more salt but also provides substantial dilution to reduce the salt concentration and vice-versa during low flow regimes. Decision makers typically plan strategies for salinity mitigation and evaluate impacts of water management policy options on salinity in the basin using decision support models. These models require statistically consistent basin wide scenarios of streamflow and salinity. Recognizing this need, we develop a basin wide stochastic generator of salinity that is consistent with the flows. The framework integrates a nonparametric space–time disaggregation model, applied to both flow and salt, and a nonparametric regression model, which simulates natural salt magnitude for a given natural flow. The nonparametric techniques do not require prior assumptions about the underlying functional relationship unlike traditional parametric methods, are data driven, and robust at capturing any functional form present in the data. They are also easily portable across sites. Within this integrated framework we propose two representative approaches, from several possible variations, for generating salt scenarios, each capturing different aspects of the flow and salt statistics. We demonstrate the performance of these approaches by applying them to flow and salt data from four gauges in the Upper Colorado River Basin. The spatial and temporal statistics of salt and their relationship with flows are well captured. This framework has utility in a variety of applications such as, short term salinity forecast conditioned on streamflow forecast, long term salinity scenarios conditioned on climate change projections, and also in reconstructing paleo salinity from paleo streamflows.

A novel recurrent neural network-based prediction system for option trading and hedging

In order to reduce their exposure to the erratic fluctuations of the financial markets, traders are nowadays increasingly dealing with options and other derivative securities instead of directly trading in the underlying assets. This paradigm shift has attracted the attention of many researchers, and there has been a tremendous increase in the awareness and activities of derivative securities. In particular there is a need to devise new techniques to address the limitations of traditional parametric pricing methods, which rely on assumptions and approximations to capture the complex dynamics of pricing processes. This paper proposes a novel non-parametric method using an ad-hoc recurrent neural network for estimating the future prices of war commodities such as gold and crude oil as well as currencies, which are increasingly gaining importance in the financial markets. The price predictions from the network, shown to be accurate and computationally efficient, are used in a hedging system to avoid unnecessary risks. Experiments with actual gold and currency trading data show that our system using the proposed network and strategy can construct portfolios yielding a return on investment of about 4.76%.

New methodology for long term creep data generation for power plant components

AbstractUsing stress rupture results openly available for grade 91 steel, three features of a new methodology for creep data analysis are summarised. First, in contrast to traditional power law and parametric methods, 100 000 h creep strengths of power plant steels are predicted accurately by extended extrapolation of creep lives from tests lasting a maximum of 5000 h. Second, related approaches rationalise creep ductility measurements in a manner which provides information relevant to creep damage evolution in operational plant. Finally, reference is made to a set of new relationships developed to offer a physically meaningful foundation not only for rationalisation and extrapolation but also for interpretation of the creep and creep fracture properties of metals and alloys.