How to Display Data- P13:The best method to convey a message from a piece of research in health is via a fi gure. The best advice that a statistician can give a researcher is to fi rst plot the data. Despite this, conventional statistics textbooks give only brief details on how to draw fi gures and display data. | 52 How to Display Data 03 o . È 8 CT o f 6 2 rö D 6 4 No observations 6 5 1 1 a 2 Z 2 4 6 8 10 Reviewer 2 Overall rating of quality of care Figure Scatter diagram of two observers Reviewer 1 vs. Reviewer 2 ratings of the overall quality of care score from the medical notes score of 48 patients with COPD with line of equality These overlapprngdatapairswould be shown as only one point or combination on the scatter graph. This is slightly misleading as there are actually six data pairs with this combination of reviewer scores. This problem can be solved by havingdiffersnreizedmarkers forthevarious p airsofs cores with the size of theroarOeenelrtive tothenumber rf datavalues with this combination of revieworanoees . Bland-Ahtmanplots An alternative more informative plot has been proposed by Bland and Al as shown tn l e 5. . H e the dtfference tn scores between the two reviewers Reviewer 1-Reviewer 2 is plotted against their average. Three things ors rerpily ob-urcrble with this typf of nirf 1 The size oftUeOlSfernncfibotwean eeviewars. 2 The distr butlc rs of thrse diffeesnres abeut seer. 3 Whether abe drbeoances restelairdto She oe-tSir mecsurement for this purposa-ee abaragiotsWe boorehieweei reoias acts as the best estimate of the anua llnesl nwnvclueii Relationship between two continuous variables 53 How well do the two methods or observers in our example agree We could simply quote the mean difference and standarddeviationofthe differences SDdiff . However it is more useful to use these to construct a range of values which would be expected to cover the agreement between the methods for mo 0 smb tbaadohn 95 meesofagrecmeí7taredcfinedas the mean differsnce 2SDdiff. ihe rare cuoreni examelr ihb rneandiCfercnce is SD onh tha Ihcibs of agaebmeat arc riven bo - .g to 8. These are sdownin aottedlmco along withthe meatidiffee-ence of F-e- the size of ihedohben She pletaer o-onoes tional to the number 2 observations 4tat
