Department of Emergency Medicine, University of Colorado Denver School of Medicine, Aurora, CO, USA.
Ann Emerg Med. 2012 Aug;60(2):139-45.e1. doi: 10.1016/j.annemergmed.2012.01.016. Epub 2012 Mar 7.
We evaluate the ability of 4 sampling methods to generate representative samples of the emergency department (ED) population.
We analyzed the electronic records of 21,662 consecutive patient visits at an urban, academic ED. From this population, we simulated different models of study recruitment in the ED by using 2 sample sizes (n=200 and n=400) and 4 sampling methods: true random, random 4-hour time blocks by exact sample size, random 4-hour time blocks by a predetermined number of blocks, and convenience or "business hours." For each method and sample size, we obtained 1,000 samples from the population. Using χ(2) tests, we measured the number of statistically significant differences between the sample and the population for 8 variables (age, sex, race/ethnicity, language, triage acuity, arrival mode, disposition, and payer source). Then, for each variable, method, and sample size, we compared the proportion of the 1,000 samples that differed from the overall ED population to the expected proportion (5%).
Only the true random samples represented the population with respect to sex, race/ethnicity, triage acuity, mode of arrival, language, and payer source in at least 95% of the samples. Patient samples obtained using random 4-hour time blocks and business hours sampling systematically differed from the overall ED patient population for several important demographic and clinical variables. However, the magnitude of these differences was not large.
Common sampling strategies selected for ED-based studies may affect parameter estimates for several representative population variables. However, the potential for bias for these variables appears small.
我们评估了 4 种采样方法生成急诊科（ED）人群代表性样本的能力。
我们分析了一家城市学术 ED 连续 21662 例患者的电子记录。从该人群中，我们通过使用 2 种样本量（n=200 和 n=400）和 4 种采样方法（真随机、按精确样本大小随机 4 小时时间块、按预定块数随机 4 小时时间块和方便或“营业时间”）模拟 ED 中的不同研究招募模型。对于每种方法和样本量，我们从人群中获得了 1000 个样本。使用 χ(2)检验，我们测量了 8 个变量（年龄、性别、种族/民族、语言、分诊 acuity、到达模式、处置和支付来源）中样本与人群之间的统计学显著差异的数量。然后，对于每个变量、方法和样本量，我们将 1000 个样本中有别于整个 ED 人群的比例与预期比例（5%）进行比较。
只有真随机样本在至少 95%的样本中代表了人口的性别、种族/民族、分诊 acuity、到达模式、语言和支付来源。使用随机 4 小时时间块和营业时间采样获得的患者样本在几个重要的人口统计学和临床变量上与整个 ED 患者人群系统不同。然而，这些差异的幅度并不大。
为 ED 研究选择的常见采样策略可能会影响几个代表性人群变量的参数估计。然而，这些变量的潜在偏差似乎很小。
