Statistical Analysis of Recurrent Birth Data Subject to Truncation and Censoring
碩士 === 國立交通大學 === 統計學研究所 === 106 === In the thesis, we study the birth patterns for women in Bangladesh which is notorious for its custom of child marriage. In particular, we focus on serial birth intervals which can reflect how frequent a woman gives births, another sign of women’s right. We find t...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | zh-TW |
| Published: |
2018
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/7d7m58 |
| Summary: | 碩士 === 國立交通大學 === 統計學研究所 === 106 === In the thesis, we study the birth patterns for women in Bangladesh which is notorious for its custom of child marriage. In particular, we focus on serial birth intervals which can reflect how frequent a woman gives births, another sign of women’s right. We find that Kaplan-Meier estimator actually underestimates the true survival function due to the mixed effects of right truncation and right censoring. We figure out the bias term after some mathematical derivations and propose a modified estimator which is shown to be a valid estimator based on simulations. The modified method is then applied to analyze the data. The result shows that there are obvious generation and regional differences.
|
|---|