Measures of biomarker dependence using a copula-based multivariate epsilon–skew–normal family of distributions

In this note we develop a new multivariate copula model based on epsilon–skew–normal marginal densities for the purpose of examining biomarker dependency structures. We illustrate the flexibility and utility of this model via a variety of graphical tools and a data analysis example pertaining to salivary biomarker. The multivariate normal model is a sub-model of the multivariate epsilon–skew–normal distribution.     

The experience of sexual desire: Psychological correlates in a college sample

In order to elaborate on available models of sexual desire, we administered a sexual desire questionnaire to 144 college students, ages 18 to 54. Included in this measure were questions concerning the frequency of sexual desire, whether the respondent had participated in sexual activity without desire, or vice versa, experienced desire without sexual behavior, and a question assessing which cues are used by the subject to gauge sexual desire (e.g., frequency of intercourse, sexual dreams). Subjects also completed the Passionate Love Scale, Sexual Arousal Inventory, and Crowne‐Marlowe Social Desirability Scale. The results indicate that as a group, males report experiencing sexual desire more frequently than females. Males appeared to rely on similar indicators of desire as females, specifically genital arousal and sexual daydreams. For both males and females, sexual desire was significantly correlated with sexual arousal (r = 0.50, females; r = 0.44, males) while the correlation of desire and love was nonsignificant for both sexes. However, desire and sexual behavior did not necessarily co‐occur, as both males and females reported engaging in sexual behavior without desire. These data suggest that greater attention be paid to the definitional features of sexual desire in nonclinical samples, in an effort to clarify current diagnostic categories and to provide population base rates.     

Weighted ratio estimation in agricultural surveys

A major problem with satellite-sensed agricultural surveys is loss of data due to cloud cover. The Large Area Crop Inventory Ex¬periment (LACIE) run by three Federal agencies (NASA, NOAA, and USDA) in the years 1974-1977 used a ratioing approach to account for missing data. This approach is found to be reasonable in that it is unbiased with respect to a plausible crop acreage time series model. At the same time, the arbitrary nature of the LACIE proce¬dure's rules for ratioing suggests that improvements to it can be made, thus motivating the discussion of general linear estimators and the development of the 'weighted aggregation' (WAG) procedure. Estimated variances of the LACIE and WAG procedures for an actual LACIE data set indicate that the LACIE procedure, although somewhat heuristic, performs rather well, having an estimated variance 12% higher than that of the WAG, which is theoretically optimal     

Simple and Exact Empirical Likelihood Ratio Tests for Normality Based on Moment Relations

The empirical likelihood (EL) technique is a powerful nonparametric method with wide theoretical and practical applications. In this article, we use the EL methodology in order to develop simple and efficient goodness-of-fit tests for normality based on the dependence between moments that characterizes normal distributions. The new empirical likelihood ratio (ELR) tests are exact and are shown to be very powerful decision rules based on small to moderate sample sizes. Asymptotic results related to the Type I error rates of the proposed tests are presented. We present a broad Monte Carlo comparison between different tests for normality, confirming the preference of the proposed method from a power perspective. A real data example is provided.     

Another look at subset selection using linear least squares

The QR-factorization provides a set of orthogonal variables which has advantages over other orthogonal representations, such as principal components and the singular-value decomposition, in selecting subsets of regression variables by least squares methods. Stopping rules, in particular, are easily understood. A new stopping rule is derived for prediction. This is derived by approximately minimizing the mean squared error in estimating the squared error of prediction. A clear distinction is made between the kind of stopping rule which is relevant when the objective is prediction, and when the objective is asymptotic consistency. Progress with reducing the bias due to the model selection procedure is briefly summarized.     

Marital Well‐being and Religiousness as Mediated by Relational Virtue and Equality

This study investigated religiousness and couple well‐being as mediated by relational virtue and equality. Relational spiritual framework theory posits that religiousness is associated with couple well‐being through relational virtues (e.g., forgiveness, commitment, and sacrifice). Theories of relational inequality postulate that religion decreases couple well‐being and indirectly lessens couple well‐being. Data from a 3‐year longitudinal community sample of 354 married couples were used. The authors found that religiousness's relationship to couple well‐being was fully mediated by relational virtue but was not connected to relational inequality. They also found that relational inequality was associated with women's conflict, men's conflict, and marital instability. They did not find that higher religiousness benefits marital outcomes directly. Although these findings do not support the idea that religious activities are directly associated with stronger relationships, the data did show that religiousness can contribute to expressed relational virtue, and relational virtue in turn is associated with marital well‐being.     

Improved estimation of variance components in mixed models

Taking Albert's (1976) formulation of a mixed model ANOVA, we consider improved estimation of the variance components for balanced designs under squared error loss. Two approaches are presented. One extends the ideas of Stein (1964), The other is developed from the fact that variance components can be expressed as linear combinations of chi-square scale parameters. Encouraging simulation results are presented.     

Linearly Independent,Orthogonal, and Uncorrelated Variables

Linearly independent, orthogonal, and uncorrelated are three terms used to indicate lack of relationship between variables. This short didactic article compares these three terms in both an algebraic and a geometric framework. An example is used to illustrate the differences.