Row-by-Row Modeling

Click on a button corresponding to an expression row-by-row modeling process. Refer to the table below for guidance.

Process	Choose this process for...
One-Way ANOVA	Fitting a one-way repeated-measures ANOVA linear model to rows of the input data set, using all combinations of different effects as distinct groups Tip: To examine all possible effects and their interactions separately, choose the ANOVA process instead.
ANOVA	Fitting an analysis-of-variance linear model to sequential rows of the input data set, allowing for h hypothesis testing on all possible effects of each of the variables and interactions separately	Caution: These processes can be computationally intensive for large data sets.
Mixed Model Analysis	Fitting a mixed linear model on a row-by-row basis to pre-normalized data and creating numerous output displays, with maximum sophistication and flexibility Note: You must understand SAS PROC MIXED syntax to use this process.
Survival Analysis	• Testing association of each normalized input data set row with a censored response, fitting a Cox proportional hazards model on a row-by-row basis
Allele Specific Expression Filter	Screening for potential allele-specific expression, using both DNA and RNA intensity data
Estimate Builder	Constructing customized linear hypothesis tests in the form of SAS ESTIMATE statements Tip: These statements can be saved in a file and used in ANOVA and Mixed Model Analysis (and in Workflows using these processes) to test an arbitrary set of linear hypotheses regarding the relative importance of different combinations of fixed effects parameters.
Difference Chooser	Quickly and easily selecting LSMeans fixed effect level differences Tip: These differences can be saved in a file and used in ANOVA and Mixed Model Analysis (and in workflows using these processes)
Two-Way Plotter	Drawing HTML line plots and bar charts for selected rows of a tall data set and two selected experimental design variables, in order to visualize the effects of individual experimental factors, or to detect possible interactions between experimental factors for a given gene or set of genes

See Expression for other subcategories.