Non-normal Conditions Research Articles

Extracting Spurious Latent Classes in Growth Mixture Modeling With Nonnormal Errors.

Growth mixture modeling is generally used for two purposes: (1) to identify mixtures of normal subgroups and (2) to approximate oddly shaped distributions by a mixture of normal components. Often in applied research this methodology is applied to both of these situations indistinctly: using the same fit statistics and likelihood ratio tests. This can lead to the overextraction of latent classes and the attribution of substantive meaning to these spurious classes. The goals of this study are (1) to explore the performance of the Bayesian information criterion, sample-adjusted BIC, and bootstrap likelihood ratio test in growth mixture modeling analysis with nonnormal distributed outcome variables and (2) to examine the effects of nonnormal time invariant covariates in the estimation of the number of latent classes when outcome variables are normally distributed. For both of these goals, we will include nonnormal conditions not considered previously in the literature. Two simulation studies were conducted. Results show that spurious classes may be selected and optimal solutions obtained in the data analysis when the population departs from normality even when the nonnormality is only present in time invariant covariates.

Raw Data Maximum Likelihood Estimation for Common Principal Component Models: A State Space Approach.

The specifications of state space model for some principal component-related models are described, including the independent-group common principal component (CPC) model, the dependent-group CPC model, and principal component-based multivariate analysis of variance. Some derivations are provided to show the equivalence of the state space approach and the existing Wishart-likelihood approach. For each model, a numeric example is used to illustrate the state space approach. In addition, a simulation study is conducted to evaluate the standard error estimates under the normality and nonnormality conditions. In order to cope with the nonnormality conditions, the robust standard errors are also computed. Finally, other possible applications of the state space approach are discussed at the end.

Systemic health evaluation of RF generators using Gaussian mixture models

We propose an application of specific machine learning techniques capable of evaluating systemic health of a Radio Frequency (RF) power generator. System signatures or fingerprints are collected from multivariate time-series data samples of sensor values under typical operational loads. These fingerprints are transformed into feature vectors using standard scaling/translation methods and the Fast Fourier Transform (FFT). The number of features per fingerprint are reduced by banding neighboring features and Principal Component Analysis (PCA). The reduced feature vectors are used with the Expectation Maximization (EM) algorithm to learn parameters for a Gaussian Mixture Model (GMM) to represent normal operation. One-class classification of normal fingerprints is achieved by thresholding the likelihood of a fingerprint feature vectors. Fingerprints were collected from normal operational conditions and seeded non-normal conditions. Preprocessing methods and algorithmic parameters have been selected using an iterative grid search. Average robust true positive rate achieved was 94.76% and best specificity reported is 86.56%.

Nonparametric Modeling of Conditional Heterogeneity and Non-Normality of Stock Returns

Nonparametric Modeling of Conditional Heterogeneity and Non-Normality of Stock Returns

Application of MapGIS in Groundwater Solute Transport of Power Plants

This paper analyses the impact of unexpected diesel tank leak in the non-normal conditions on groundwater, on the basis of a detailed analysis of hydrogeological conditions of a power plant, using the analytical method of solute transport in groundwater,combining with the DTM module of MapGIS spatial analysis. The results show that if leakage of diesel tank lasts 5 years, the maximum influence range of pollution halo is 0.204 km2 and the farthest impact distance is 660m.

On the Performance of Likelihood-Based Difference Tests in Nonlinear Structural Equation Models

This article investigates likelihood-based difference statistics for testing nonlinear effects in structural equation modeling using the latent moderated structural equations (LMS) approach. In addition to the standard difference statistic TD, 2 robust statistics have been developed in the literature to ensure valid results under the conditions of nonnormality or small sample sizes: the robust TDR and the “strictly positive” TDRP. These robust statistics have not been examined in combination with LMS yet. In 2 Monte Carlo studies we investigate the performance of these methods for testing quadratic or interaction effects subject to different sources of nonnormality, nonnormality due to the nonlinear terms, and nonnormality due to the distribution of the predictor variables. The results indicate that TD is preferable to both TDR and TDRP. Under the condition of strong nonlinear effects and nonnormal predictors, TDR often produced negative differences and TDRP showed no desirable power.

A study on the dependence of PEMs acoustic properties on incidence angle

The objective of this paper is to study the variability of on-site acoustic measurements in non-normal conditions, as a function of the angle. A porous European mix was investigated. In order to reject the hypothesis that the cause of the variations in the acoustic properties is the surface inhomogeneity, texture properties were investigated according to the standard ISO 13473-1 and ISO/CD TS 13473-4. The acoustic absorption coefficient was measured according to ISO 13472-1. Results were compared and analysed in terms of averages and standard deviations. Result analyses may allow us to derive how absorption properties may vary as a function of the angle of incidence (under the hypothesis of homogeneous surface texture of the friction course). A tentative theoretical framework for explaining the dependence of acoustic absorption on incidence angle was formulated. The outcomes of this study are expected to benefit both practitioners and researchers.

A Comparison of Diagonal Weighted Least Squares Robust Estimation Techniques for Ordinal Data

This study compared diagonal weighted least squares robust estimation techniques available in 2 popular statistical programs: diagonal weighted least squares (DWLS; LISREL version 8.80) and weighted least squares–mean (WLSM) and weighted least squares—mean and variance adjusted (WLSMV; Mplus version 6.11). A 20-item confirmatory factor analysis was estimated using item-level ordered categorical data. Three different nonnormality conditions were applied to 2- to 7-category data with sample sizes of 200, 400, and 800. Convergence problems were seen with nonnormal data when DWLS was used with few categories. Both DWLS and WLSMV produced accurate parameter estimates; however, bias in standard errors of parameter estimates was extreme for select conditions when nonnormal data were present. The robust estimators generally reported acceptable model–data fit, unless few categories were used with nonnormal data at smaller sample sizes; WLSMV yielded better fit than WLSM for most indices.

Expanding the scope of inquiry: exploring accounts of childhood and family life among sex workers in London, Ontario

This article presents findings from a qualitative research project that sought to explore the organization of sex work and women's experiences in the trade in a medium-size Canadian city. Drawing upon 14 semi-structured life-history interviews with women between 24 and 60 years of age who have taken part in sex work, primarily street-based, this discussion examines the women's accounts of childhood and early family experiences. Findings related to childhood highlight the role of the women's mothers, fathers, and a range of non-normative conditions in shaping their social experience of childhood. Our participants' accounts of family dynamics feature discussions of loving familial relations, inter-generational involvement in the sex trade, and feelings of exclusion. These findings support existing studies on childhood and family experiences among street-based sex workers and contribute new data to this relatively under-developed area of study within the sex work literature. One of the most unique insights is that although the women's accounts reveal difficult experiences across the spheres of socialization related to childhood and family, they did not identify them as the root cause of their sex trade participation. We discuss the practical significance of this finding for health care and social service professionals (i.e., case worker, support staff, community clinic workers), who work with women in the sex trade but may be uncertain how to broach and/or navigate the sensitive issues of childhood and family in their work with these marginalized groups of women.

Hedging crude oil derivatives in GARCH-type models

We investigate the empirical performance of hedging strategies based on Greeks, such as Delta and Delta-Gamma, for (European-style) crude oil options in a GARCH model environment. Particular attention is paid to studying the impacts of the conditional heteroscedasticity and the conditional non-normality of the GARCH innovations on the option prices and the performance of these hedging strategies. To examine the empirical performance of the hedging strategies, we evaluate the Value at Risk (VaR) and the Expected Shortfall (ES) of the terminal values of the hedging portfolios using the NYMEX (WTI) data for the 1991 - 2011 period. Our hedging results show that GARCH with shifted gamma innovations systematically outperforms

Determinants of systematic risk in the US Restaurant industry

To compare previous studies, this study re-examines the determinants of systematic risk in the restaurant industry. To estimate systematic risk, the authors specify flexible models that take care of serial dependence, autoregressive conditional heteroskedasticity and non-normality of the time series data. Using the estimated systematic risk, they analyse the determinants of risk using a quantile regression approach. The empirical results show that a firm’s liquidity ratio, efficiency ratio, debt leverage ratio and size are the main determinants of systematic risk in the restaurant industry. Moreover, it turns out that the effects of liquidity, debt leverage and efficiency decrease as the considered risk levels increase.

A double-exponential GARCH model for stochastic mortality

In this paper, a generalized GARCH-based stochastic mortality model is developed, which incorporates conditional heteroskedasticity and conditional non-normality. First, a detailed empirical analysis of the UK mortality rates from 1922 to 2009 is provided, where it was found that both the conditional heteroskedasticity and conditional non-normality are important empirical long-term structures of mortality. To describe conditional non-normality, a double-exponential distribution that allows conditional skewness and the heavy-tailed features found in the datasets was selected. For the practical implementation of the proposed model, a two-stage scheme was introduced to estimate the unknown parameters. First, the Quasi-Maximum Likelihood Estimation (QMLE) method was employed to estimate the GARCH structure. Next, the MLE was adopted to estimate the unknown parameters of the double-exponential distribution using residuals as input data. The model was then back-tested against the previous 10 years of mortality data to assess its forecasting ability, before Monte Carlo simulation was carried out to simulate and produce a table of forecast mortality rates from the optimal distribution.

The Research on 200 Liters Large Material Barrels with Double L-Rings Drop Analysis

Using CAD / CAE / CAM softwaresolidworks obtain material barrels three-dimensional model. The analysis date of dropping simulation, the material barrel filled with heavy objects, free-fall from the height of 1.2 meter on non-normal condition, is got by the function of dropping test and the method of equivalent load setting. The result of analysis is very close to the results of the theoretical calculations. It shows that the design to improve product quality and efficiency has a very important theoretical and practical value.

A Comparison of Strategies for Forming Product Indicators for Unequal Numbers of Items in Structural Equation Models of Latent Interactions

This Monte Carlo simulation study investigated different strategies for forming product indicators for the unconstrained approach in analyzing latent interaction models when the exogenous factors are measured by unequal numbers of indicators under both normal and nonnormal conditions. Product indicators were created by (a) multiplying parcels of the larger scale by items of the smaller scale, and (b) matching items according to reliability to create several product indicators, ignoring those items with lower reliability. Two scaling approaches were compared where parceling was not involved: (a) fixing the factor variances, and (b) fixing 1 loading to 1 for each factor. The unconstrained approach was compared with the latent moderated structural equations (LMS) approach. Results showed that under normal conditions, the LMS approach was preferred because the biases of its interaction estimates and associated standard errors were generally smaller, and its power was higher than that of the unconstrained approach. Under nonnormal conditions, however, the unconstrained approach was generally more robust than the LMS approach. It is recommended to form product indicators by using items with higher reliability (rather than parceling) in the matching and then to specify the model by fixing 1 loading of each factor to unity when adopting the unconstrained approach.

On the Optimal Estimating Function Method for Conditional Correlation Models

We consider applying the optimal estimating function (OptEF) method to conditional correlation (CC) models for parameter estimation. This method is asymptotically more efficient than the Gaussian QML method under conditional nonnormality. This relative efficiency is obtained by exploiting the information of the multivariate conditional third and fourth moments, and is important because conditional nonnormality is a stylized fact of financial returns. We also demonstrate how to implement the OptEF method by updating the two-step variant of the Gaussian QML method under an independence assumption. This assumption requires that the true model be a constant CC model. Without this assumption, the updated statistic is still asymptotically valid, but can only be viewed as an approximation to the OptEF estimator. By focusing on the constant CC models with different dimensions, we also conduct a simulation study to confirm our theoretical results, and provide two empirical examples of dynamic spot-futures hedging and dynamic variance-minimum portfolios.

Exploration of the Factor Structure of the Kirton Adaption–Innovation Inventory Using Bootstrapping Estimation

Exploratory factor analyses of the Kirton Adaption-Innovation Inventory (KAI), which serves to measure individual cognitive styles, generally indicate three factors: sufficiency of originality, efficiency, and rule/group conformity. In contrast, a 2005 study by Im and Hu using confirmatory factor analysis supported a four-factor structure, dividing the sufficiency of originality dimension into two subdimensions, idea generation and preference for change. This study extends Im and Hu's (2005) study of a derived version of the KAI by providing additional evidence of the four-factor structure. Specifically, the authors test the robustness of the parameter estimates to the violation of normality assumptions in the sample using bootstrap methods. A bias-corrected confidence interval bootstrapping procedure conducted among a sample of 356 participants--members of the Arkansas Household Research Panel, with middle SES and average age of 55.6 yr. (SD = 13.9)--showed that the four-factor model with two subdimensions of sufficiency of originality fits the data significantly better than the three-factor model in non-normality conditions.

Effect of Step-Change Radiation Flux on Dynamic Characteristics in Tower Solar Cavity Receiver

The heat flux on the inner surface of the tower solar thermal power plant system will show the characteristics of noncontinuous step change, especially in nonnormal and transient weather conditions, which may result in a continuous dynamic variation of the characteristic parameters. Therefore, the research of dynamic characteristics plays a very important role in the operation and the control safely in solar cavity receiver system. In this paper, based on the noncontinuous step change of radiation flux, a non-linear dynamic model is constructed to obtain the effects of the non-continuous step change radiation flux and step change feed water flow on the receiver performance by sequential modular approach. The subject investigated in our study is a 1 MW solar power station constructed in Yanqing county, Beijing, China. This study has obtained the dynamic responses of the characteristic parameters in the cavity receiver such as drum pressure, drum water level, main steam flow, and main steam enthalpy under step change radiation flux. And the influence of step-change feed water flow to the dynamic characteristics has also been analyzed. The results could provide general guidance for security operation and control in solar cavity receiver system.

Estimating Latent Variable Interactions With Nonnormal Observed Data: A Comparison of Four Approaches

A Monte Carlo simulation was conducted to investigate the robustness of 4 latent variable interaction modeling approaches (Constrained Product Indicator [CPI], Generalized Appended Product Indicator [GAPI], Unconstrained Product Indicator [UPI], and Latent Moderated Structural Equations [LMS]) under high degrees of nonnormality of the observed exogenous variables. Results showed that the CPI and LMS approaches yielded biased estimates of the interaction effect when the exogenous variables were highly nonnormal. When the violation of nonnormality was not severe (normal; symmetric with excess kurtosis < 1), the LMS approach yielded the most efficient estimates of the latent interaction effect with the highest statistical power. In highly nonnormal conditions, the GAPI and UPI approaches with maximum likelihood (ML) estimation yielded unbiased latent interaction effect estimates, with acceptable actual Type I error rates for both the Wald and likelihood ratio tests of interaction effect at N ≥ 500. An empirical example illustrated the use of the 4 approaches in testing a latent variable interaction between academic self-efficacy and positive family role models in the prediction of academic performance.

Establishing the cut-off value of a screening method

Generally, the cut-off point of a screening assay is defined through a one-sided prediction limit obtained from a given sample of blanks. Depending on the assumptions one is willing to make about the underlying data distribution, different types of prediction limits can be employed. In this paper, Monte Carlo simulations are used to illustrate the coverage performance of normal, lognormal and nonparametric prediction limits under normal and non-normal conditions.

A simple approach to standardized-residuals-based higher-moment tests

Abstract We propose a new approach to the higher-moment tests for evaluating the standardized error distribution hypothesis of a conditional mean-and-variance model (such as a GARCH-type model). Our key idea is to purge the effect of estimating the conditional mean-and-variance parameters on the estimated higher moments by suitably using the first and second moments of the standardized residuals. The resulting higher-moment tests have a simple invariant form for various conditional mean-and-variance models, and are also applicable to the symmetry or independence hypothesis that does not involve a complete standardized error distribution. Thus, our tests are simple and flexible. Using our approach, we establish a class of skewness–kurtosis tests, characteristic-function-based moment tests, and Value-at-Risk tests for exploring the standardized error distribution and higher-order dependence structures. We also conduct a simulation to show the validity of our approach in purging the estimation effect, and provide an empirical example to show the usefulness of our tests in exploring conditional non-normality.