24小时热门版块排行榜

返回列表

本帖产生 1 个翻译EPI ，点击这里进行查看

听涛月雨

金虫 (小有名气)

翻译EPI: 6
应助: 3 (幼儿园)
金币: 2217.9
散金: 161
红花: 5
沙发: 1
帖子: 211
在线: 91.4小时
虫号: 1271994
注册: 2011-04-20
专业: 天然药物化学

[求助] 一小段数据统计分析的描述，欢迎应助

A geometric mean provides a better estimate of central tendency for data that are distributed with a long tail at the upper end of the distribution. This
type of distribution is common in the measurement of  environmental chemicals in blood or urine. The geometric mean is influenced less by high values than is the arithmetic mean. Geometric means were calculated by taking the log of each concentration and then computing the weighted mean
of those log-transformed values using SUDAAN software. Ninety-five  percent  confidence  intervals  around  this weighted mean were calculated by adding and subtracting an amount equal to the product of a Student’s t-statistic and the standard error of the weighted mean estimate. The degrees
of freedom of the t-statistic were determined by subtracting the number of strata from the number of primary sampling units  (PSUs)  according  to  the  data  available  from  the complex survey design. The standard error was computed with SUDAAN’s Proc Descript (design=WR), which uses
Taylor series linearization for variance estimation. The weighted geometric mean and its confidence limits were then obtained by taking the antilogs of this weighted mean and its upper and lower confidence limits.

[ 来自科研家族快乐检索 ]

[ Last edited by 听涛月雨 on 2012-11-12 at 11:11 ]

回复此楼

» 猜你喜欢

遇见更好的自己

1楼 2012-11-12 10:34:54

已阅回复此楼关注TA 给TA发消息送TA红花 TA的回帖

fanliang1389

荣誉版主 (文坛精英)

有爱的二哥

翻译EPI: 57
应助: 18 (小学生)
贵宾: 1.989
金币: 13044.6
散金: 18540
红花: 123
沙发: 243
帖子: 18237
在线: 2429.4小时
虫号: 620773
注册: 2008-10-09
性别: GG
专业: 食品加工学基础
管辖: 博后之家

【答案】应助回帖

★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★
听涛月雨: 金币+10, 翻译EPI+1, ★有帮助, 有帮助，谢谢！但翻译的不是很好，很多统计术语没有翻译出来 2012-11-12 14:25:31
sltmac: 金币+20 2012-11-13 11:00:03

对于在顶端处有长间隔分布的数据，几何平均值可较好的估计该类数据的集中趋势。通常，这类分布用来测量血液和尿液中的环境化学物。与算术平均值相比，几何平均数更不易受大数值的影响。几何平均数计算方法如下：取各浓度的log值，然后采用SUDAAN软件计算经log转化后数值的加权平均数。通过加减学生t检验结果和加权平均数标准误差的平均数来计算加权平均数的95%置信区间。依据复杂取样设计中所取有效数据，初级抽样单位（PSUs）减去层数即为t-检验的自由度。采用SUDDAN Pro Descript(design=WR)计算标准误差，其原理为泰勒级数线性方差估计。加权平均数的反对数值即为加权几何平均数，加权平均数的上部和下部界限即为其置信界限。