Although the prevalence of insomnia and the association of insomnia with menopause have been well reported, not much work has been conducted in population-based research on insomnia and menopause in Korea. The purpose of the present report was to determine overall and different prevalence of insomnia by menopausal status, and the relationship between insomnia and menopause in a population-based sample of middle-aged Korean women. A total of 96.1% of 2497 randomly selected middle-aged Korean women participated. Insomnia was defined as occurring three times a week or more in the previous month. Subjects were categorized into three groups: premenopaues, perimenopause, and postmenopause. The overall prevalence of insomnia in middle-aged Korean women was 14.3%. The most common symptom of insomnia was difficulty maintaining sleep (9.7%), followed by difficulty initiating sleep (7.9%), and early morning awakening (7.5%). Multiple logistic regression analysis revealed that menopause was independently associated with insomnia after adjusting for confounding factors such as age, income, and depression. Perimenopause was significantly associated with a dramatic increase in the risk of insomnia, but there was no significant association for postmenopause. The major finding is that insomnia is significantly associated with the menopausal transition. The prevalence of insomnia increases significantly by the transition from premenopause to perimenopause, but not to postmenopause. A further prospective study is needed to investigate the influence of menopause on insomnia.

No abstract

The generalized autoregressive conditional heteroscedastic (GARCH) model has been popular in the analysis of financial time series data with high volatility. Conventionally, the parameter estimation in GARCH models has been performed based on the Gaussian quasi-maximum likelihood. However, when the innovation terms have either heavy-tailed or skewed distributions, the quasi-maximum likelihood estimator (QMLE) does not function well. In order to remedy this defect, we propose the normal mixture QMLE (NM-QMLE), which is obtained from the normal mixture quasi-likelihood, and demonstrate that the NM-QMLE is consistent and asymptotically normal. Finally, we present simulation results and a real data analysis in order to illustrate our findings. Copyright (c) 2008 Board of the Foundation of the Scandinavian Journal of Statistics.