Exploring Nonresponse Bias in the Department of Veterans Affairs' Bereaved Family Survey
Exploring Nonresponse Bias in the Department of Veterans Affairs' Bereaved Family Survey
复制标题
DOI：
10.1089/jpm.2015.0050
复制
发表时间：
2015-10-01
影响因子：
2.8
通讯作者：
Ersek, Mary
中科院分区：
文献类型：
--
作者：
Smith, Dawn;Kuzla, Natalie;Ersek, Mary
背景：患者和家属对医疗服务（包括姑息治疗）的评价被广泛用作绩效评估。调查分数可能会受到无回答偏差的影响，从而导致不准确的绩效评估。目的：我们的目的是检查邮寄版本的退伍军人事务部（VA）丧亲家庭调查绩效指标（BFS-PM）的无应答偏倚，并评估无应答偏倚对设施的BFS-PM评分的影响。方法：对全国样本进行横断面分析。样本包括20，540名退伍军人，他们在2012年10月至2013年9月期间在146个VA医疗中心（VAMC）之一死亡。要求近亲（NOK）完成并返回调查。BFS-PM被定义为在生命的最后一个月内将退伍军人的整体护理评为优秀的NOK的比例。在创建了一个模型来预测基于患者和临床特征的响应可能性之后，我们应用逆概率权重来检查它们对设施得分的影响。我们还评估了设施的性能之前和之后的加权无响应相对于不同的基准。结果：我们收到了8912份调查（45%的回复率）。加权后机构BFS-PM评分的平均变化为-2%（范围：-10%至+11%）。31%的设施得分变化在2%以上。满足60%、70%和80%假设基准的设施数量也因无响应加权而发生变化。结论：我们的研究结果强调了在使用基于丧亲家庭调查（BFS）数据的护理质量指标时适当解决无应答的重要性。
Background: Patients' and families' evaluations of health care, including palliative care, are widely used as performance measures. Survey scores may be affected by nonresponse bias, resulting in inaccurate performance evaluation. Objectives: Our aim was to examine nonresponse bias for the mailed version of the Department of Veterans Affairs (VA) Bereaved Family Survey Performance Measure (BFS-PM) and evaluate the effect of nonresponse bias on facilities' BFS-PM scores. Methods: A cross-sectional analysis of a national sample was conducted. The sample consisted of 20,540 veterans who died in one of 146 VA Medical Centers (VAMCs) between October 2012 and September 2013. Next of kin (NOK) were asked to complete and return the survey. The BFS-PM is defined as the proportion of NOK who rated overall care for the veteran during the last month of life as excellent. After creating a model to predict the likelihood of response based on patient and clinical characteristics, we applied inverse probability weights to examine their effect on facilities' scores. We also evaluated facility performance before and after weighting for nonresponse vis-a-vis varying benchmarks. Results: We received 8912 surveys (45% response rate). The mean change in facility BFS-PM scores after weighting was -2%, (range: -10% to+11%). The scores of 31% of facilities changed more than2%. The number of facilities meeting hypothetical benchmarks of 60%, 70%, and 80% also changed as a result of weighting for nonresponse. Conclusion: Our results underscore the importance of appropriately addressing nonresponse in the use of quality-of-care metrics based on Bereaved Family Survey (BFS) data.