Skip to main content
Fig. 3 | BMC Medical Research Methodology

Fig. 3

From: Exploring flexible polynomial regression as a method to align routine clinical outcomes with daily data capture through remote technologies

Fig. 3

Visualisations of the flexible polynomial results across 3 example individuals with less than 8 measurements, or with 8–14 measurements but greater than 6 months between at least one observation. Points indicate observed values; black lines/points indicate daily predicted values; grey shading indicates the 95% confidence interval. (A) Flexible polynomial method with no criteria applied. Individuals with few values far apart in time had between-value predictions widely different than expected. (B) Flexible polynomial method with criteria applied. Profiles 1,2&3 have a linear model allocated because they have less than 8 measurements, and Profile 3 only has a model generated between the consecutive measurements within 6 months

Back to article page