This website presents a range of quality indicators as a series of control charts (graphs), covering regional and national benchmarking, and data tables. This section explains the features of these graphs and tables.
Types of graphs Tables Legend
What are control limits? What are confidence intervals?
Types of graphs
Three types of graph are used in this website, they are called a modified box and whisker plot, a funnel plot and a time series chart. The regional view (East Midlands) normally uses a modified box and whisker plot and the National view usually appears as a funnel plot.
The modified box and whisker plot graphically depicts groups of numerical data through their five-number summaries: the upper end of the box or bar represents the upper 99.8% confidence interval, the bottom end of the box or bar represents the lower 99.8% confidence interval. A black diamond is used to indicate the actual reported value. The lower and upper end of the whisker plot indicate, respectively, the minimum and maximum peer values. The green and red arrows also show the percentage change against the previous quarter.
Funnel plots allow many points to be plotted simultaneously, with information about whether each point is significantly above or below the expected, or average, value. Funnel plots were developed as a method of displaying data for Statistical Process Control (SPC).
Time series charts show each individual trusts position over a period of consecutive quarters. This is particularly useful when considering the overall trend of an organisation against other organisation within the region to see where quarter on quarter variation exists.
Tables show the numerical summaries of the graphs. All tables have each organisations values shown as a separate row. They also show the organisations peer min/max range and the overall East Midlands and National mean values
What are control limits?
Control charts are useful tools to monitor quality. A control chart contains a centre line that represents the average value for the data (coloured yellow). Two other horizontal lines, called the upper control limit (UCL) and the lower control limit (LCL), are also shown on the chart. In general, all of the data points (~99%) will to fall within these limits. When an organisation falls outside the control limits, it is worthwhile to understand the circumstances.
The control limits are coloured red and green. The red control limit indicates that data points on this side of the mean represents worse behaviour. The green control limit indicates that data points on this side of the mean represent better behaviour.
When there is a high degree of variability among data, a control limit may be out of the bounds of 0.1% – 99.9%. In this case, the control limit is set to either 0.1% (LCL) or 99.9% (UCL).
What are confidence intervals?
A confidence interval provides an estimate of a range of values within which the measure in question is likely to lie. How likely the interval is to contain the parameter is determined by the confidence level or confidence coefficient (generally set to 99.8% in this instance). Increasing the desired confidence level will widen the confidence interval.
Information within in the legend describes the symbols used in the charts. The symbols used are: