首页> 外文期刊>Communications in Statistics >Transformed Logit Confidence Intervals for Small Populations in Single Capture-Recapture Estimation
【24h】

Transformed Logit Confidence Intervals for Small Populations in Single Capture-Recapture Estimation

机译:单次捕获-重新捕获估计中小种群的变换Logit置信区间

获取原文
获取原文并翻译 | 示例

摘要

The good performance of logit confidence intervals for the odds ratio with small samples is well known. This is true unless the actual odds ratio is very large. In single capture-recapture estimation the odds ratio is equal to I because of the assumption of independence of the samples. Consequently, a transformation of the logit confidence intervals for the odds ratio is proposed in order to estimate the size of a closed population under single capture-recapture estimation. It is found that the transformed logit interval, after adding .5 to each observed count before computation, has actual coverage probabilities near to the nominal level even for small populations and even for capture probabilities near to 0 or 1, which is not guaranteed for the other capture-recapture confidence intervals proposed in statistical literature. Thus, given that the .5 transformed logit interval is very simple to compute and has a good performance, it is appropriate to be implemented by most users of the single capture-recapture method.
机译:对于小样本的比值比,对数置信区间的良好性能是众所周知的。除非实际几率非常大,否则这是正确的。在单次捕获-捕获估计中,由于样本的独立性,优势比等于I。因此,提出了针对比值比的对数置信区间的变换,以便在单次捕获-再捕获估计下估计封闭种群的大小。发现在对计算前的每个观察到的计数加.5之后,变换后的对数间隔具有的实际覆盖概率甚至接近标称水平,即使对于小种群而言,甚至对于捕获概率都接近于0或1,这都不保证。统计文献中提出的其他捕获-捕获置信区间。因此,鉴于.5转换后的logit间隔非常易于计算且性能良好,因此适合大多数采用单一捕获-捕获方法的用户实施。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号