...

• • User only reliable estimation results: There are situations when a model estimation procedure does not fail outright, but still encounters some difficulties. In this case,  it can even generate p-value and fold change on the comparisons, but they are not reliable, i.e. they can be misleading. Therefore, the default of Use only reliable estimation results is set Yes.

  • Report p-value for effects: If set to No, only the p-value of comparison will be displayed on the report, the p-value of the factors and interaction terms are not shown in the report table. When you choose Yes in addition to the comparison’s p-value, type III p-values are displayed for all the non-random terms in the model.

  • Shrinkage to error term variance: by default, None is select, which is lognormal model. Limma-trend and Limma-voom options are lognormal with shrinkage. (Limma-trend is the same as the GSA default option–lognormal with shrinkdage). Shrinkage options are recommended for small sample size design, no random effects can be included when perform shrinkage. If there is numeric factors in the model, the partial correlations cannot be reported on the numeric factors when shrinkage is performed. Limma-trend works well if the ratio of the largest library size to the smallest is not more than 3 fold, it is simple and robust for any type of data. Limma-voom is recommended for sequencing data when library sizes vary substantially, but it can only be invoked on data node normlized using TMM, Total count, or upper Upper quartile methods . while Limma-trend can be applied to normalized data using any method.

  • Report partial correlations: If the model has a numeric factor(s), when choosing Yes, partial correlation coefficient(s) of the numeric factor(s) will be displayed in the  result table. When choosing No,  partial correlation coefficients are not shown.

  • Data has been log transformed with base: showing the current scale of the input data on this task.

...