Ayatollahi S M
Department of Biostatistics, School of Medicine, Shiraz University of Medical Sciences, Islamic Republic of Iran.
J Trop Pediatr. 1995 Jun;41(3):169-73. doi: 10.1093/tropej/41.3.169.
Analysis of data from the Shiraz (Iran) growth study requires to take age into account when assessing weight-for-height of school children aged 6-12. A unified structure standard score method for construction of weight-for-height is designed to overcome the age dependence problem. This method first applies Healy-Rasbash-Yang (HRY) distribution-free estimation method of age-related centiles to calculate log (weight) and height-for-age centiles, and convert them to their standard scores. These scores are age and sex independent, and are called weight index (WI) and height index (HI), respectively. Then WI is regressed on HI and age-adjusted centiles of weight-for-height are derived at each age of weight and height to their respective zeta-scores. Finally, weight-for-height centiles are drawn for each age-sex category of children. This zeta-score method is shown to be efficient, simple, and stable, and may generally be applied to other data.
对设拉子(伊朗)生长研究数据进行分析时,在评估6至12岁学龄儿童身高别体重时需要考虑年龄因素。为克服年龄依赖性问题,设计了一种统一的身高别体重结构标准分方法。该方法首先应用希利-拉斯巴什-杨(HRY)与年龄相关百分位数的无分布估计方法来计算对数(体重)和年龄别身高百分位数,并将它们转换为标准分。这些分数与年龄和性别无关,分别称为体重指数(WI)和身高指数(HI)。然后将WI对HI进行回归,并在体重和身高的每个年龄将年龄调整后的身高别体重百分位数推导为各自的zeta分数。最后,为每个年龄-性别类别的儿童绘制身高别体重百分位数。结果表明,这种zeta分数方法高效、简单且稳定,并且通常可应用于其他数据。