Statistical process control charts for attribute data involving very large sample sizes: a review of problems and...

Area of Science:

• Healthcare Quality Improvement
• Statistical Process Control
• Data Analysis in Medicine

Background:

• Statistical process control (SPC) charts are increasingly used in healthcare to monitor processes.
• Traditional SPC charts struggle with large datasets, leading to inaccurate variation assessments.
• Misinterpretation of variation can result in incorrect process improvement strategies.

Purpose of the Study:

• To review the challenges of using traditional SPC charts with large healthcare datasets.
• To highlight the problem of inaccurate variation assessment due to within-subgroup analysis.
• To present solutions for accurately analyzing variation in large healthcare data.

Main Methods:

• Review of traditional attribute and count data SPC charts.
• Discussion of limitations with large sample sizes and tight control limits.
• Introduction of Laney's attribute charts and measurements charts considering between-subgroup variation.

Main Results:

• Traditional SPC charts can produce false signals of variation with large datasets.
• Within-subgroup variation analysis is insufficient for large healthcare data.
• Newer attribute charts and measurements charts offer improved accuracy.

Conclusions:

• Accurate variation assessment is crucial for effective healthcare process improvement.
• Traditional SPC charts require adaptation or replacement for large datasets.
• Implementing advanced SPC methods can lead to more reliable quality monitoring in healthcare.