Replication data: the Extractive Industries Transparency Initiative (EITI) implementation progress

The files contain the replication data and replication instructions (as STATA do-file) that replicate the results in the article:

Lujala, Päivi 2018. An analysis of the Extractive Industries Transparency Initiative implementation process. World Development 107(July): 358–381.

It is an open access article and you can access it by copy-pasting this link: https://authors.elsevier.com/sd/article/S0305750X18300755

The dataset includes all independent countries that in 2012 had population of 500,000 or larger and covers the period 2003-2016. The dataset was composed using several register databases and also includes variables that were coded by the author. The details on the sources and coding can be found in the article. The data is structured so that it can be analyzed using the conditional risk-set model developed by Prentice, Williams, and Peterson (1981) (PWT), using the gap approach for calculating the time between the events. NOTE! In no circumstances should other recurrent event data analysis approaches be used to analyze the data as the data is set for this particular type of model.

The data was used to test a series of hypotheses on what factors influence how fast countries are implementing the EITI Standard.

该数据集包含了复制研究数据和复制指令（以 STATA do-file 格式），旨在复制 Lujala, Päivi 在 2018 年发表的论文《对 Extractive Industries Transparency Initiative 实施过程的分析》（World Development 107(July): 358–381）中的研究结果。该论文为开放获取，可通过以下链接访问：https://authors.elsevier.com/sd/article/S0305750X18300755。数据集涵盖了 2012 年人口达到或超过 50 万的所有独立国家，并覆盖了 2003-2016 年期间。数据集的构建采用了多个登记数据库，并包含了作者编码的变量。有关数据来源和编码的详细信息可在论文中找到。数据结构设计用于通过 Prentice, Williams, 和 Peterson（1981）开发的条件风险集模型（PWT）进行分析，并采用时间间隔方法计算事件之间的差距。请注意！在任何情况下，均不应使用其他循环事件数据分析方法来分析这些数据，因为数据是为该特定类型的模型专门设定的。数据被用于检验一系列假设，探讨哪些因素影响国家实施 EITI 标准的速度。