When a Truly Positive Correlation Turns Negative: How Different Approaches to Model Hierarchically Structured Constructs Affect Estimated Correlations to Covariates

Many constructs in personality psychology assume a hierarchical structure positing a general factor along with several narrower subdimensions or facets. Different approaches are commonly used to model such a structure, including higher-order factor models, bifactor models, single-factor models based on the responses on the observed items, and single-factor models based on parcels computed from the mean observed scores on the subdimensions. The present article investigates the consequences of adopting a certain approach for the validity of conclusions derived from the thereby obtained correlation of the most general factor to a covariate. Any of the considered approaches may closely approximate the true correlation when its underlying assumptions are met or when model misspecifications only pertain to the measurement model of the hierarchical construct. However, when misspecifications involve nonmodeled covariances between parts of the hierarchically structured construct and the covariate, higher-order models, single-factor representations, and facet-parcel approaches can yield severely biased estimates sometimes grossly misrepresenting the true correlation and even incurring sign changes. In contrast, a bifactor approach proved to be most robust and to provide rather unbiased results under all conditions. The implications are discussed and recommendations are provided.

LANGUAGE DICHOTOMY OF LANGUAGE AND WORD STYLISTICS

The study of language as a social phenomenon in its ontological, epistemological, and pragmatic aspects is considered important at a time when language is gaining special applied significance. One of the main directions of modern linguistics is to consider the language phenomenon as a means of communication used not only within the formal system, but also in the social environment. In the theory of communication, along with other types of language variability, there is a need for a systematic, comprehensive study of types of functional stylistics within the above-mentioned areas. Because in order to recognize the true correlation between the types of language activity and social consciousness, to distinguish between language and speech styles formed in accordance with the system of knowledge in the minds of the language personality and the collective, it is necessary to identify the linguistic and cognitive foundations of stylistics and make a new interpretation. This determines the correlation between the cultural-intellectual, communicative-pragmatic potential of the language and the metacognitive abilities of linguists, the linguistic-cognitive foundations of language and speech styles.

Choosing the frequency of follow-up in longitudinal studies: Is more necessarily better?

Background Follow-up frequency is an important design parameter in longitudinal studies. We quantified the impact of reducing follow-up frequency on the precision of estimated regression parameters, and investigated the impact of incorrectly assuming an exchangeable correlation structure on estimates of the loss of precision resulting from reduced follow-up. Methods We estimated the loss in precision on deleting every second observation from three longitudinal cohorts: patients with Childhood Systemic Lupus Erythematosus (cSLE), the Canadian Haemophilia Prophylaxis Study (CHPS), and patients with Juvenile Dermatomyositis (JDM). We compared these results with those from a theoretical formula assuming an exchangeable correlation structure. Results The increase in sample size needed to compensate for halving follow-up frequency was 9%, 6% and 28% for the cSLE, CHPS and JDM cohorts respectively. Under the assumption of an exchangeable correlation, the estimated increases in sample size were 22%, 11% and 10% respectively. Conclusions Reducing follow-up frequency can result in minimal loss of information, as seen in the CHPS cohort. While using a theoretical formula based on an exchangeable correlation structure is convenient, it can be inaccurate when the true correlation structure is not exchangeable.

Comparison of some correlation measures for continuous and categorical data

SummaryIn the literature there can be found a wide collection of correlation and association coefficients used for different structures of data. Generally, some of the correlation coefficients are conventionally used for continuous data and others for categorical or ordinal observations. The aim of this paper is to verify the performance of various approaches to correlation coefficient estimation for several types of observations. Both simulated and real data were analysed. For continuous variables, Pearson’s r2 and MIC were determined, whereas for categorized data three approaches were compared: Cramér’s V, Joe’s estimator, and the regression-based estimator. Two method of discretization for continuous data were used. The following conclusions were drawn: the regression-based approach yielded the best results for data with the highest assumed r2 coefficient, whereas Joe’s estimator was the better approximation of true correlation when the assumed r2 was small; and the MIC estimator detected the maximal level of dependency for data having a quadratic relation. Moreover, the discretization method applied to data with a non-linear dependency can cause loss of dependency information. The calculations were supported by the R packages arules and minerva.

The Milky Way’s disc of classical satellite galaxies in light of Gaia DR2

ABSTRACT We study the correlation of orbital poles of the 11 classical satellite galaxies of the Milky Way, comparing results from previous proper motions with the independent data by Gaia DR2. Previous results on the degree of correlation and its significance are confirmed by the new data. A majority of the satellites co-orbit along the Vast Polar Structure, the plane (or disc) of satellite galaxies defined by their positions. The orbital planes of eight satellites align to <20° with a common direction, seven even orbit in the same sense. Most also share similar specific angular momenta, though their wide distribution on the sky does not support a recent group infall or satellites-of-satellites origin. The orbital pole concentration has continuously increased as more precise proper motions were measured, as expected if the underlying distribution shows true correlation that is washed out by observational uncertainties. The orbital poles of the up to seven most correlated satellites are in fact almost as concentrated as expected for the best-possible orbital alignment achievable given the satellite positions. Combining the best-available proper motions substantially increases the tension with ΛCDM cosmological expectations: <0.1 per cent of simulated satellite systems in IllustrisTNG contain seven orbital poles as closely aligned as observed. Simulated systems that simultaneously reproduce the concentration of orbital poles and the flattening of the satellite distribution have a frequency of <0.1 per cent for any number of k > 3 combined orbital poles, indicating that these results are not affected by a look-elsewhere effect. This compounds the Planes of Satellite Galaxies Problem.

Ultrasound elastography in the evaluation of thyroid nodules: evolution of a promising diagnostic tool for predicting the risk of malignancy

The elastic properties of tissue have always been of interest in clinical practice. In the past, the identification of structures that were stiffer on physical palpation would raise the suspicion that “there was something wrong”. With the development and advancement of medicine, there proved to be a true correlation in the prediction of malignancy of a lesion: malignant disease tends to stiffen the affected tissue, either by increased cell proliferation or fibrosis. Palpation is the oldest method for the detection of thyroid nodules, which is informed by the knowledge that malignant thyroid lesions tend to be much harder than benign ones. Unfortunately, palpation is a highly subjective method that is dependent on the size and location of the lesion, as well as on the skill of the physician. In cases where these nodules are very small or are located in deep regions, their detection by palpation is difficult or even impossible. In addition, although a malignant lesion differs in terms of elasticity, it may not have echogenic properties, preventing its detection by conventional ultrasound. Imaging that indicates the stiffness or deformation of tissues, through the use of ultrasound elastography techniques, adds new information related to their structural formation. In this article, we review the basic physical principles of elastography and the evolution of the method for the evaluation of thyroid nodules, as well as the limitations of and future perspectives for its use.

Harga Diri dan Adiksi Internet: Tinjauan Meta-Analisis

The aim of this meta-analysis study is to figure out the true correlation between self-esteem and internet addiction. This meta-analysis uses 159 studies from 40 scientific articles from the year of 2005-2018 and involved in 120.825 participants. Correction for the two artifacts studied in this meta-analysis first is sampling error, and the second one is measurement error. The results support the hypothesis and show some similar findings whereas the true correlations from the groups confirm previous researches that self-esteem has a negative correlation to internet addiction. The strongest correlation found in adolescence group followed by men and women, all participant, also students and college students groups. However, these findings show that the internet accommodates individuals with negative self-esteem to build online social relationships and fulfilling their communication and pleasure needs and makes them easier committed to deviant behavior such as internet addiction.

Differentially Private Ordinary Least Squares

Linear regression is one of the most prevalent techniques in machine learning; however, it is also common to use linear regression for its explanatory capabilities rather than label prediction. Ordinary Least Squares (OLS) is often used in statistics to establish a correlation between an attribute (e.g. gender) and a label (e.g. income) in the presence of other (potentially correlated) features. OLS assumes a particular model that randomly generates the data, and derives t-values - representing the likelihood of each real value to be the true correlation. Using t-values, OLS can release a confidence interval, which is an interval on the reals that is likely to contain the true correlation; and when this interval does not intersect the origin, we can reject the null hypothesis as it is likely that the true correlation is non-zero.Our work aims at achieving similar guarantees on data under differentially private estimators. First, we show that for well-spread data, the Gaussian Johnson-Lindenstrauss Transform (JLT) gives a very good approximation of t-values; secondly, when JLT approximates Ridge regression (linear regression with l2-regularization) we derive, under certain conditions, confidence intervals using the projected data; lastly, we derive, under different conditions, confidence intervals for the "Analyze Gauss" algorithm of Dwork et al (STOC 2014).

Considering the Effects of Nonresponse on Correlations Between Surveyed Variables

Nonresponse to organizational surveys is a vexing problem. Although scholars have a reasonable understanding of how systematic nonresponse influences estimates of population means, they are likely to have less context for understanding how it impacts correlations. We present the results of a simulation study designed to provide a frame of reference for understanding the extent to which systematic nonresponse can bias observed correlations between surveyed variables. Although there were cases where notable levels of bias were observed in the correlations, the majority of situations simulated resulted in mean observed correlations that were within .05 of the true correlation. The variety of situations simulated allows researchers to evaluate the external validity of observed correlations in their data – a critical goal for survey researchers in practice and academics.