Healthcare quality professionals need to understand and use inferential statistics to interpret sample data from their organizations. Since in quality improvement and healthcare research studies, all the data from a population often are not available, investigators take samples and make inferences about that population using inferential statistics. This series of six articles will give readers an understanding of the concepts of inferential statistics, as well as the specific tools for calculating confidence intervals and tests of statistical significance for samples of data. ⋯ This article, Part 4, starts with a review of the information contained in Parts 1, 2, and 3, which appeared in the July/August 2003 issue of the Journal for Healthcare Quality. This article describes t distributions and how these are used to calculate confidence intervals for estimating a population mean based on a sample mean of a continuous variable. Part 4 concludes with a discussion of standard error, margin of error, and confidence intervals for estimating a population proportion based on a sample proportion from a binomial variable.
Group Health Cooperative of South Central Wisconsin, Madison, USA. john_hansen@ghc-hmo.com
J Healthc Qual. 2004 Jul 1;26(4):26-32.
AbstractHealthcare quality professionals need to understand and use inferential statistics to interpret sample data from their organizations. Since in quality improvement and healthcare research studies, all the data from a population often are not available, investigators take samples and make inferences about that population using inferential statistics. This series of six articles will give readers an understanding of the concepts of inferential statistics, as well as the specific tools for calculating confidence intervals and tests of statistical significance for samples of data. The statistical principles are equally applicable to quality improvement and healthcare research studies. This article, Part 4, starts with a review of the information contained in Parts 1, 2, and 3, which appeared in the July/August 2003 issue of the Journal for Healthcare Quality. This article describes t distributions and how these are used to calculate confidence intervals for estimating a population mean based on a sample mean of a continuous variable. Part 4 concludes with a discussion of standard error, margin of error, and confidence intervals for estimating a population proportion based on a sample proportion from a binomial variable.