Journal: Vaccines
Article Title: From Bivariate to Multivariate Analysis of Cytometric Data: Overview of Computational Methods and Their Application in Vaccination Studies
doi: 10.3390/vaccines8010138
Figure Lengend Snippet: Data transformations. ( a ) A random data set was generated using two gaussian distributions, centered at 10 2 (10000 cells) and 2*10 3 (1000 cells), and with standard deviation equal to 10 2 and 10 3 , respectively. The probability histogram is shown on a linear scale. ( b ) Arcsinh transformation. The parameter λ defines both the width of the linear region, and its slope. The transforming function is approximately linear for λ close to zero, while it approaches logarithmic transformations when x >> λ or when x << −λ. ( c ) Logicle transformation. The shape of the transforming function is defined by the parameters M, A, and W, which can be intuitively interpreted respectively as the number of decades, the number of negative decades, and the width of the linear region. ( d ) Probability histogram of the data in a transformed with the arcsinh function. ( e ) Probability histogram of the data in a transformed with the logicle function.
Article Snippet: , SWIFT , Matlab , Clustering method based on splitting and merging of Gaussian mixture models , [ ] .
Techniques: Generated, Standard Deviation, Transformation Assay