Data Binning Using Survival Analysis

Data binning is used in survival analyses if the variable you wish to use is continuous (for example, age), but needs to be viewed as categorical data. Alternatively, it can be used to regroup categorical data. For example, if histological grade with values such as Well Defined, Moderately Well Defined, and Poorly Defined are selected, you can group Moderately Well Defined with Poorly Defined and treat them as one group for the purposes of this analysis.

To use the data binning feature with a survival analysis:

1.  Run tranSMART, then click the Dataset Explorer tab.

2.  Define the cohorts you wish to analyze by dragging one or more concepts from a study into empty subset definition boxes. For more information, see Populating the Study Groups.

3.  Click the Advanced Workflow tab:

Description: C:\Users\ctucker\AppData\Local\Temp\SNAGHTML27dca9d6.PNG

4.  Select Survival Analysis from the Analysis dropdown menu:

The Variable Selection section appears.

5.  Define the variables:

Variable

Required?

Description

Example

Time

Yes

A time variable used in the study.

Survival Time

Category

No

A variable that you wish to use to sort the cohorts.

If the variable you wish to use is continuous (for example, age), the binning feature should be used.

Cancer Stage

Censoring Variable

No

A censoring variable (occurs when the value of a measurement/observation is partially known).

Survival (Censor)

 

6.  Under Binning, click Enable:

Description: C:\Users\ctucker\AppData\Local\Temp\SNAGHTML15680869.PNG

7.  Define the following:

Field

Description

Comments

Variable Type

Select whether the variable you have defined above is continuous or categorical.

A continuous variable can be treated as a categorical variable when you use the binning feature.

Number of Bins

Type the number of bins you would like data to be organized in.

This step may require trial and error based on how you wish to display data.

Bin Assignments

Select how you would like data to be binned.

Note:  This feature can only be used when the variable type selected above is continuous. 

■   Evenly Distribute Population: assigns bins based on the underlying data.

For example, if the majority of the subjects in the study were elderly, bins based on age could look like: [(1-40), (40-80), (81-85), (86-90), (90-92)].

■   Evenly Spaced Bins: creates bins based on the overall range of the variable.

For example, if the majority of the subjects in the study were elderly, bins based on age could look like: [(1-20), (21-40), (41-60), (61-80), (81-100)].

Manual Binning

Select the checkbox if you wish to bin manually.

Note:  This is the only binning method available if you are attempting to bin a categorical variable type.

Complete the binning form that populates as a result of checking the Manual Binning box.

■   For continuous data:

■   For categorical data:

 

8.  Click Run.