Description Usage Format Details
Very few responders
1 |
A data frame with five variables: result
, analyst
,
plate
, subjectID
, and treatment
.
40 biological samples (distinguished in variable subjectID) are analyzed at each of 3 days and on each of 3 plates per day variable treatment distinguishes negative controls ('negcontrol') from biological samples ('sample') there are 4 obs. of a negative control within each plate
normalize: log-transform and substract mean model structure: runs crossed with biological samples. when running a model with many parameters (random effects and residual variance different between subgroups), a simple model with 1 component is better than a 2-component mixture when running a mixture model with random effects and residual variance assumed equal in both subgroups, a 2-component mixture is better than a simple model with 1 component
irrespective of the model choice, the same 2 individuals are classified as responders in the 2-component mixture
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.