The Alberta Inpatient Hospital Experience Survey: Representativeness of Sample and Initial Findings

Kyle Kemp, Nancy Chan, Brandi McCormack


In health survey research, it is paramount that survey respondents are representative of the general target population, thereby ensuring that the policies and program decisions supported by the underlying data are well-informed. In order to assess the representativeness of our survey respondents, we sought to compare selected demographic and clinical attributes of our inpatient hospital experience survey respondents with those of eligible nonrespondents. This retrospective analysis of cross-sectional administrative hospital data included 26,295 survey respondents, and 466,034 non-respondents. These were based on all inpatient hospital discharges that were eligible to be surveyed in the province of Alberta, Canada from April 1, 2011 to March 31, 2014. When compared with eligible nonrespondents, survey respondents had similar patterns in terms of mean age (53.8±20.0 vs. 54.4±21.3 years), sex (35.0% vs. 38.8% male), admission type (60.7% urgent in both groups), and the mean number of comorbidities (0.8±1.2 vs. 1.0±1.3). Compared to nonrespondents, survey respondents tended to be healthier, as evidenced by a shorter mean length of stay (5.4±9.4 vs.7.0±15.4 days), less need for ICU care (2.1% vs. 3.0% of cases), and being more likely to be discharged directly home (95.2% vs. 91.9% of cases). The survey sampling strategy resulted in a sample that was, in most cases, representative of the general inpatient population in our jurisdiction of approximately 4 million residents. Our findings indicate that an adequate sampling strategy may still provide a representative sample, despite a low response rate.


Inpatient hospital experience; HCAHPS; telephone surveys; nonresponse bias

Full Text: PDF HTML

About Survey Practice Our Global Partners Disclaimer
The Survey Practice content may not be distributed, used, adapted, reproduced, translated or copied for any commercial purpose in any form without prior permission of the publisher. Any use of this e-journal in whole or in part, must include the customary bibliographic citation and its URL.