From Array Suite Wiki

Cox Model

To run this module, type MicroArray | Inference | Cox Model. The Cox Model command will analyze a study containing a survival trait, and will generate a report table containing p-values and other analysis information (such as hazard ratio, goodness of fit, etc). Users can specify the Time, Status, and Event for a survival analysis, as well as any accompanying covariates for the model. In addition, Strata can be optionally specified, if the design table contains stratification information (usually used for population stratification).

Cox model menu.png

Input Data Requirements

This module works on -Omic data types. The data do not need to be log2-transformed to approximate a normal distribution, but should be normalized to allow between-sample comparisons (e.g. Upper-quartile normalization of RNAseq FPKM values).

General Options



  • Project & Data: The window includes a dropdown box to select the Project and Data object to be filtered.
  • Variables: Selections can be made on which variables should be included in the filtering (options include All variables, Selected variables, Visible variables, and Customized variables (select any pre-generated Lists)).
  • Observations: Selections can be made on which observations should be included in the filtering (options include All observations, Selected observations, Visible observations, and Customized observations (select any pre-generated Lists).
  • Output name: The user can choose to name the output data object.


  • Specify Model: Specify the survival trait information and any other covariates to be used in the analysis.
  • Time: Specify the Time column for the survival analysis (selected from available columns in the design table).
  • Strata: The user can specify a Strata column from the design table. For example, if the user specifies 'group' as Strata and there are 3 levels in groups, 3 different survival functions will be estimated.
  • Status: Specify the Status column, i.e, the observation result for the sample in the survival analysis (containing survival status information).
  • Event: Once the Status is specified, Array Studio will automatically populate the Event drop-down box, so that the user can choose the Event, such as death in biological organisms and failure in mechanical systems, to be used for the survival analysis.
  • Columns: The user can select any design columns to be used as covariates in the model.
    • Class: Check this box would indicate the corresponding term is categorical. Otherwise the term is numeric.
    • Term: The available factors in the design table that can be used as covariates in the model.
  • Construct Model: Build the survival model.
    • Add: Clicking this button will add the selected terms to the model.
    • Cross: Cross the terms selected on the left (this is discussed in more detail later).
    • Nest: Nest the selected term on the left panel to the selected term on the right panel.
    • Remove: Clicking this button will remove selected terms in right panel.
  • Report p-values for covariate terms: output the p-values for covariate terms included in the model.
  • Report goodness of fit test p-value: Report goodness of fit test p-value.
  • Report hazard ratio data: Report hazard ratio data.
  • Multiplicity: The available methods for p value adjustment can be specified ("FDR_BH", "FDR_BY", "Bonferroni", "Sidak", "StepDownBonferroni", "StepDownSidak", and "StepUp"), with "FDR_BH" being the default value.

Note: The Multiplicity adjustment takes into account the total number of tests performed within a given analysis. There is the ability to set the default option to adjust p-values on a per-test basis. Please refer to the "[ Statistics]" section in the User Guide.

  • Anova type: Specify the ANOVA type for the analysis(Perform ANOVA and compute Type 1 , type 2, type 3 or type 4 sum of squares of the given generalized linear model).
  • Test Type: Specify the way to perform the hypothesis test(options include "WaldTest", and "LikelihoodRatioTest").
  • Alpha level: The p-value cutoff for generation of a list. Only the variable with a adjusted p value less than Alpha level will be saved in the output list.

Output Results

An example Survival Trait Association report is shown below:

The first two columns are the statistical test results (raw p value and adjusted p value) for each variables (probesets/genes) to see whether they are significantly related to the survival status. The rest of the tables are annotations for the variables.



Survival Trait Association

Related Articles