homeabout uscontact us


Tutorial 3B: Step 1 Estimate Missing Values


By clustering the NCI60 t_matrix dataset , you can get an idea of the speed of Jarvis-Patrick clustering. First, missing values in the dataset must be estimated.

If you have completed Tutorial 2 (you have a 3-nearest-neighbors dataset under the t-matrix dataset in the Experiments navigator already) skip to Step 2 Perform Partitional Clustering.


Estimate Missing Values

1. If the t_matrix dataset in the Experiments navigator is not already highlighted, click it.

2. Click the Estimate Missing Values toolbar icon , or select Estimate Missing Values from the Data menu, or right-click the item and select Estimate Missing Values from the shortcut menu. The Estimate Missing Values dialog is displayed.

3. Set dialog parameters.



Remove Genes That Have Missing Values


Replacement Technique

Nearest Neighbors Estimation

Distance Metric


Choice of Median or Mean



4. Click OK. The Estimate Missing Value operation is performed and upon successful completion, a new complete Estimated: #mv <30 | medians dataset is added to the Experiments navigator under the original dataset.