Changes in sedentary behavior among adolescent girls: a 2.5-Year prospective cohort study

Purpose: To describe longitudinal changes in leisure-time sedentary behavior among girls, during early to mid-adolescence. Methods: A 2.5-year prospective cohort study, comprising 5 data collections, 6 months apart, between 2000 and 2002. Girls aged 12–15 years (n = 200) from 8 high schools located in Sydney, Australia, self-reported the usual time spent each week in a comprehensive range of sedentary behaviors.  Results: Retention rate for the study was 82%. Girls aged 12.8 years spent approximately 45% of their discretionary time in sedentary behavior, which increased to 63% at age 14.9 years. Watching TV, videos, and playing video games (small screen recreation; SSR) was the most popular sedentary pastime, accounting for 33% of time spent in sedentariness, followed by homework and reading (25%). Sedentary behavior increased 1.4 and 3.3 hours on week and weekend days, respectively. On weekdays, increased time was spent on hobbies (27 min/day) and on weekend days, increased time was spent sitting around talking with friends (60 min/day), computer use (37 min/day), and television viewing (34 min/day). Conclusions: Among girls, the transition between early and mid-adolescence was accompanied by a significant increase in leisure-time sedentary behavior. Interventions to reduce sedentariness among adolescent girls are best to focus on weekend behaviors. Studies seeking to examine the association between inactivity and the development of chronic health problems need to examine a diverse range of activities that comprehensively measure sedentariness. This information will provide a better understanding of inactivity patterns among adolescent girls.

Comparing the small sample properties of two break Lagrange Multiplier unit root tests

In this note, we examine the size and power properties and the break date estimation accuracy of the Lee and Strazicich (LS, 2003) two break endogenous unit root test, based on two different break date selection methods: minimising the test statistic and minimising the sum of squared residuals (SSR). Our results show that the performance of both Models A and C of the LS test are superior when one uses the minimising SSR procedure.

Semi-supervised classification based on subspace sparse representation

Graph plays an important role in graph-based semi-supervised classification. However, due to noisy and redundant features in high-dimensional data, it is not a trivial job to construct a well-structured graph on high-dimensional samples. In this paper, we take advantage of sparse representation in random subspaces for graph construction and propose a method called Semi-Supervised Classification based on Subspace Sparse Representation, SSC-SSR in short. SSC-SSR first generates several random subspaces from the original space and then seeks sparse representation coefficients in these subspaces. Next, it trains semi-supervised linear classifiers on graphs that are constructed by these coefficients. Finally, it combines these classifiers into an ensemble classifier by minimizing a linear regression problem. Unlike traditional graph-based semi-supervised classification methods, the graphs of SSC-SSR are data-driven instead of man-made in advance. Empirical study on face images classification tasks demonstrates that SSC-SSR not only has superior recognition performance with respect to competitive methods, but also has wide ranges of effective input parameters.