The analysis of social network data: an exciting frontier for statisticians

The catalyst for this paper is the recent interest in the relationship between social networks and an individual's health, which has arisen following a series of papers by Nicholas Christakis and James Fowler on person‐ to‐person spread of health behaviors. In this issue, they provide a detailed explanation of their methods that offers insights, justifications, and responses to criticisms [1]. In this paper, we introduce some of the key statistical methods used in social network analysis and indicate where those used by Christakis and Fowler (CF) fit into the general framework. The intent is to provide the background necessary for readers to be able to make their own evaluation of the work by CF and understand the challenges of research involving social networks. We entertain possible solutions to some of the difficulties encountered in accounting for confounding effects in analyses of peer effects and provide comments on the contributions of CF. Copyright © 2012 John Wiley & Sons, Ltd.     

Clinical assessment of freezing of gait in Parkinson's disease from computer-generated animation

The current ‘gold standard’ for clinical evaluation of freezing of gait (FOG) in Parkinson's disease (PD) is determination of the number of FOG episodes from video by independent raters. We have previously described a robust technique for objective FOG assessment from lower-limb acceleration. However, there is no existing method for validation of autonomous FOG measures in the absence of video documentation. In this study we compared the results of clinical evaluation of FOG from computer-generated animations (derived from body-mounted inertial sensors) during a timed up and go test with the ‘gold standard’ of clinical video assessment, utilizing a cohort of 10 experienced raters from four PD centers. Agreement between the 10 clinical observers for scoring of FOG from computer animations was more robust for the relative duration of freeze events (percent time frozen; intraclass correlation coefficient of 0.65) than number of FOG episodes, and was comparable with clinical evaluation of the patient from video (intraclass correlation coefficient 0.73). This result suggests that percent time frozen should be considered (along with number of FOG events) to better convey FOG severity. The ability of clinical observers to quantify FOG from computer-generated animation derived from lower-limb motion data provides a potential approach to validation of accelerometry-based FOG identification outside of the clinic.     

“Spontaneously” hypertensive mice: A potential genetic model for the study of the relationship between heart size and blood pressure

Abstract

Mice selected genetically for high and low blood pressure (BP) were compared with regard to heart weight and heart/body ratios. Two experiments were performed with mice ranging in age from 1.3 to 9 months and 11 to 23 months respectively. In a third experiment C57BL/6J mice were compared to the high and low BP mice. Heart/body ratios and heart weights, adjusted for body weight via covariance analysis, were significantly greater for the high BP mice, but no Age x BP Genotype interaction was observed. Results were discussed in terms of a possible relationship between heart weight and BP via genetic linkage or pleiotropy. The possibility was also raised that compensatory mechanisms for high blood pressure, e.g., cardiac hypertrophy, may operate very early in development for animals who are hypertensive by virtue of selective breeding for blood pressure extremes.