Skip to main content
Fig. 1 | BMC Medical Research Methodology

Fig. 1

From: New approaches and technical considerations in detecting outlier measurements and trajectories in longitudinal children growth data

Fig. 1

Study experimental design. The study involves 3 steps: a) the injection of synthetic outliers of different types and different intensities, b) the application of the outlier detection methods for outlier measurements and outlier trajectories, and c) the evaluation of the impact of outliers on growth pattern detection. Abbreviations: TARGet Kids!, the applied research group for kids; zWFL ; weight-for-length z-scores ; zWA, weight-for-age z-scores; CTX, the co-trimoxazole prophylaxis trial; zMUAC, mid-upper arm circumference-for-age z-scores; SD, standard deviation; mBIV, modified method for biologically implausible values detection; sBIV, static detection method for biologically implausible values based on fixed WHO cut-off values ; MMOM, multi-model outlier measurement detection method; SMOM, single-model outlier measurement detection method; COT, clustering-based outlier trajectory detection method; MMOT, multi-model outlier trajectory detection method

Back to article page

BMC Medical Research Methodology

ISSN: 1471-2288

Contact us