Overdispersion in health care performance data: Laney's approach

Mohammed, M A; Laney, David B

doi:10.1136/qshc.2006.017830

Cited by 39 publications

(33 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is termed “over-dispersion” and often indicates that assumption (b) and/or (c) have been violated. While there are statistical techniques for allowing for “over-dispersion”, this technical fix25 – 27 does not itself address the fundamental question of why “over-dispersion” exists. This requires detective work to understand the underlying process and learn why it is behaving in this way.…”

Section: Selecting the Right Control Chartmentioning

confidence: 99%

Plotting basic control charts: tutorial notes for healthcare practitioners

Mohammed

Worthington²,

Woodall

2008

Quality and Safety in Health Care

Self Cite

203

155

View full text Add to dashboard Cite

There is considerable interest in the use of statistical process control (SPC) in healthcare. Although SPC is part of an overall philosophy of continual improvement, the implementation of SPC usually requires the production of control charts. However, as SPC is relatively new to healthcare practitioners and is not routinely featured in medical statistics texts/courses, there is a need to explain the issues involved in the selection and construction of control charts in practice. Following a brief overview of SPC in healthcare and preliminary issues, we use a tutorial-based approach to illustrate the selection and construction of four commonly used control charts (xmr-chart, p-chart, u-chart, c-chart) using examples from healthcare. For each control chart, the raw data, the relevant formulae and their use and interpretation of the final SPC chart are provided together with a notes section highlighting important issues for the SPC practitioner. Some more advanced topics are also mentioned with suggestions for further reading.

show abstract

Section: Selecting the Right Control Chartmentioning

confidence: 99%

Plotting basic control charts: tutorial notes for healthcare practitioners

Mohammed

Worthington²,

Woodall

2008

Quality and Safety in Health Care

Self Cite

203

155

View full text Add to dashboard Cite

show abstract

“…Taking this precaution ensures that the control limits are not inaccurate if the data happen to be overdispersed; if the data are not overdispersed, the between-group SD will be approximately equal to one, and therefore have little effect on the calculated thresholds. First proposed by David Laney, the chart that results from this adjustment is known as a Laney u’-chart 22 23. The upper control limit (UCL) and lower control limit (LCL) for a Laney u’-chart can be represented in their simplest form as: and more specifically as: where µ is the historical average baseline rate, µ i is the rate during time period i, n i is the population during time period i, and k is the total number of baseline time periods.…”

Section: Methodsmentioning

confidence: 99%

Statistical process control charts for monitoring military injuries

2017

View full text Add to dashboard Cite

show abstract

“…The first key step in the analyses of hospital performance data was the recognition of inadequacy of league tables and their replacement either with Shewhart‐type double‐square‐root charts or with funnel plots . However, it soon became apparent that over‐dispersion is a major issue in national‐level healthcare monitoring, so two approaches were suggested: setting funnel plot limits via random‐effects regression modelling (which comprises two models – the multiplicative and the additive models) by Spiegelhalter and adaptation of the p ‐control chart to cross‐sectional data by Mohammed and Laney in the form of a funnel plot (henceforth called Laney's approach). Later, we proposed a modification of the double‐square‐root chart, which we now develop further and compare it with the two funnel plot approaches.…”

Section: The Compared Methodsmentioning

confidence: 99%

“…The extension to cross‐sectional data, although straightforward, has not met such rapid and wide acceptance. In addition to being more recent, the reason for this probably lies in the dominance of the comprehensive and mathematically rigorous approach of Spiegelhalter and associates, but possibly also in the mundane fact that the letter by Muhammed and Laney, even though relatively short, contains several typos that render the implementation a challenging task. To verify our corrections, we precisely reproduced the right panel of their Figure .…”

Section: The Compared Methodsmentioning

confidence: 99%

Outlier Detection for Healthcare Quality Monitoring – A Comparison of Four Approaches to Over‐Dispersed Proportions

Vidmar

Blagus

2013

Quality & Reliability Eng

View full text Add to dashboard Cite

bOutlier detection among over-dispersed proportions is important in healthcare quality monitoring. We had previously introduced control limits for double-square-root chart on the basis of prediction intervals from regression-through-origin and compared our approach to common outlier detection tests. In this study, we develop our approach further by adjusting the confidence level (in the spirit of Chauvenet's criterion and Bayesian thinking) and transforming the chart into an asymmetric funnel plot. We compare it to Laney's approach (p'-chart adapted for cross-sectional data), Spiegelhalter's approach (funnel plots based on multiplicative or additive regression models) and Carling's median rule. Comparisons are performed on simulated and real data. The simulations comprise 'small' (<0.2; highly right-skewed) and 'large' (>0.5; symmetrically distributed) proportions, drawn in samples of size 10-100 from lognormal distribution either without outliers or with one outlier added. The real data comprise hospital readmissions from the UK (used by Laney and Spiegelhalter) and business indicators of healthcare quality for Slovenian hospitals. In the simulations, Spiegelhalter's approach tended to yield very high false alarm rates, except the multiplicative version in very small samples. Laney's approach produced fewest false alarms but could not detect the outlier in very small samples among small proportions, and regardless of sample size among large proportions. Median rule performed similarly. Our approach performed the best overall, although it is slightly less liberal than median rule for small proportions, it appears to be the only generally useful approach for large proportions.

show abstract

Overdispersion in health care performance data: Laney's approach

Cited by 39 publications

References 5 publications

Plotting basic control charts: tutorial notes for healthcare practitioners

Plotting basic control charts: tutorial notes for healthcare practitioners

Statistical process control charts for monitoring military injuries

Outlier Detection for Healthcare Quality Monitoring – A Comparison of Four Approaches to Over‐Dispersed Proportions

Contact Info

Product

Resources

About