Printer Friendly


In this issue, Olrich, Kalman, and Nigolian (2012) used a u-chart to determine if the rate of call light usage was different in the pre-, initial, or post-implementation time periods of their study. U-charts are one type of control chart that is used to monitor attributes over time. This type of analysis, also known as statistical process control, can be a tool for research and quality improvement. Although there are different control charts for different kinds of data, I will focus on the u-chart in this column as one frequently used in health care (Lloyd, 2004).

Statistical process control is a strategy for examining data about health care processes over time. This strategy is based on the idea that in all processes there is inherent variation due to fluctuations in patient's biological process, differences in the process of care, and errors in measurement. Some of the variation is normal and due to chance. However, when improvements are made, we want to know if the variation we see in the event of change is greater than normal variation. Control charts are the primary tool used in statistical process control (Benneyan, Lloyd, & Plsek, 2003; Cary, 2003; Thor et al., 2007).

What Are Control Charts?

Control charts are a method of monitoring data on selected attributes or quality indicators (e.g., falls, call light usage, medication areas, infection rates) over time. The chart's vertical axis reflects the quality indicator and the horizontal axis represents time. Data on indicators are graphed on this chart, with a center line for the mean and upper and lower control limit lines. Upper and lower control limits are typically three standard deviations above and below the center line; if the process is in control, 99.73% of the points thus will fall between these control limits (Benneyan et al., 2003). In other words, data that fall within the upper and lower limits are considered to be normal variation, or the difference in the data (from the mean) is due to chance alone and generally indicates the data are stable. Another name for this is common cause variation. When data fall outside the upper or lower control limits, this is considered to be special cause variation, meaning the difference from the mean or average is considered statistically significant (Lloyd, 2004).

When data are monitored without an attempt to change anything, and data fall outside the control limits, the process is unstable and something is wrong with the process. An example of this in the study by Olrich and colleagues (2012) occurred when the authors described the significant increase in call light usage by a patient with delirium who did not usually need anything. This is special cause variation. In this case, the staff would not try to change the process, but would try to identify a plan of action for that particular patient (Lloyd, 2004).

When attempting to improve a process, nurses are trying deliberately to increase or decrease the attribute. They might want to decrease falls or increase patient satisfaction, so they institute various quality improvement initiatives. In this case, authors were trying to produce a special cause variation and were monitoring to see if the intervention (hourly rounding) makes a statistical difference. They were hoping results would fall outside the control limits in the right direction.


As mentioned earlier, there are different types of control charts, depending on what is being measured. Five types of control charts are used commonly in health care: X-bar and S chart, XmR chart, p-chart, c-chart, and u-charts (see Lloyd, 2004, Chapter 6, for an explanation of the various types of control charts). In a u-chart, a count of the attribute in question can be averaged over the number of opportunities for that attribute to occur over a particular time period. For falls, for example, the researcher might count the number of falls that occur per 100 patient clays or per 1,000 patient days; this would depend on the number of opportunities for the size of the hospital.

Several criteria exist for use of a u-chart. First, in an area of opportunity, any number of events can occur (e.g., patients can make any number of calls during each day, as in the study by Olrich et al. [2012]). In addition, the area of opportunity may vary or is not usually consistent; a month might have 90 or 100 patient days, for example. Third, the area of opportunity has been identified and the number of areas of opportunities can be fractional. If any of these criteria are not met, then another chart will have to be used (Cary, 2003).

Quality Improvement Studies

The u-chart and other control charts can be used to do continuous monitoring of data to ensure there are no unexpected special causes and to maintain control of the process. In other cases, as mentioned earlier, researchers may want to try deliberately to change the process to increase or decrease the attribute in question. In the Olrich et al. study (2012), the research team identified time periods, pre-implementation, initial implementation, and post-implementation of hourly rounding, and then determined if there was any difference in call usage during these periods. The investigators would analyze the data to determine if data occurred outside the control limits (in this case, less than) established during the pre-implementation period.

Control charts are important decision aids. The control limits within the charts demonstrate process behavior (Roos, 2006). As nurses are involved in quality improvement, they should become familiar with the methods such as control charts used to monitor clinical processes. They must have the knowledge of data collection to form the rates and to analyze the control charts (Lloyd, 2004). A great deal more is involved with understanding control charts, including their strengths and weakness, but is beyond the scope of this column and readers are encouraged to review the references.


Benneyan, J.C., Lloyd, R.C., & Plsek, P.E. (2003). Statistical process control as a tool for research and healthcare improvement. Quality and Safety in Health Care, 12(6), 458-464.

Cary, R.G. (2003). Improving health care with control charts. Milwaukee, WI: ASQ Quality Press.

Lloyd, R. (2004). Quality health care: A guide to developing and using indicators. Burlington, MA: Jones & Bartlett Publisher.

Olrich, T., Kalman, M., & Nigolian, C. (2012). Hourly rounding: A replication study. MEDSURG Nursing, 21(1), 23-26, 36.

Roos, T.K. (2006). A statistical process control case study. Quality Management in Health Care, 15(4), 221-236.

Thor, J., Lundberg, J., Ask, J., Olsson, J., Carli, C., Harenstam, K.P., & Brommels, M. (2007). Application of statistical process control in healthcare improvement: A systematic review. Quality and Safety in Health Care, 16(5), 387-399.

Lynne M. Connelly, PhD, RN, is an Associate Professor and Director of Nursing, Benedictine College, Atchison, KS. She is Research Editor for MEDSURG Nursing.
COPYRIGHT 2012 Jannetti Publications, Inc.
No portion of this article can be reproduced without the express written permission from the copyright holder.
Copyright 2012 Gale, Cengage Learning. All rights reserved.

Article Details
Printer friendly Cite/link Email Feedback
Title Annotation:Research Roundtable
Author:Connelly, Lynne M.
Publication:MedSurg Nursing
Geographic Code:1USA
Date:Jan 1, 2012
Previous Article:Hyperglycemic State.
Next Article:Oral gallstone dissolution therapies.

Terms of use | Privacy policy | Copyright © 2019 Farlex, Inc. | Feedback | For webmasters