| Contribution
|
Use the options in this group box to generate histograms and spreadsheets of variable contributions.
|
| Contribution
|
Click this button to generate a histogram of variable contributions to the score of an observation in the direction of a principal component. You can uniquely specify an observation by selecting its time slot and batch number (see the descriptions of the Time and Batch options below). The principal components can be specified from the First list (see below). Different analysis variables make different contributions to the scores.
|
|
Click this button to generate the same information described above in spreadsheet format.
|
|
|
| Time
|
Use this option (together with the Batch option) to specify an observation for which you want to generate a contributions plot.
|
| Batch
|
Use this option (together with the Time option) to specify an observation for which you want to generate a contributions plot.
|
| Lineplot (t)
|
Click this button to create a line plot of the scores factors for the principal component selected in the First list. You can generate more than one graph by making multiple selections in the First list. The t-scores are the presentation of the original measurements in the new coordinate system. In BMPLS modeling, the scores are used to examine the normality of a batch. The larger the score of a batch, the less normal the batch is. Deviations from zero with magnitudes comparable or larger than the control limits may indicate abnormalities.
|
|
|
Click this button to generate the same information as above in spreadsheet format.
|
| Scatter (t)
|
Click this button to create a scores scatterplot for the principal components selected in the First and Second lists. For example, selecting component 1 in the First list and component 2 in the Second list will create a scatterplot of the t-scores of component 1 against the t-scores of component 2. This graph will also display an ellipse, defined as:
|
| Observations with score values falling outside this ellipse may be outliers
|
Note: Note that you can generate more than one graph by making multiple selections in the First and Second lists. For example, you can generate the scatterplots of components 1 and 2 vs. 3 if you select components 1 and 2 in the First list and 3 in the Second. See the description of the Lineplot (t) option above for more details.
|
|
|
Click this button to generate the same information as above in spreadsheet format.
|
|
|
| Control (t)
|
Click this button to generate a control chart for the t-scores for a specified principal component (see First list). A t control chart shows the time trajectory of the scores in the direction of a principal component for every batch in the data set.
|
|
|
Click this button to generate the same information as above in spreadsheet format.
|
|
|
| Lineplot (p)
|
Click this button to create a line plot of the loading factors for the specified principal component in the First list. For generating more than one graph, make multiple selections in the list.
Note: Different variables contribute differently to the loading factor of a principal component. The loading factors determine the orientation of the principal components with respect to the original coordinate system. The more influential a variable, the larger its loading factor. Thus, by examining the loading factors, we can tell how different variables contribute to the principal components.
|
| Scatterplot (p)
|
Click this button to create a loading factor scatterplot for the principal components selected in the First and Second lists. For example, selecting component 1 in the First list and component 2 in the Second will create a scatterplot of the p-factors for component 1 against the p-factors for component 2. Scatterplots of the loading factors can be used to examine the relationship between the process variables and the type of influence they exert on the PC model. Clustered variables are positively related to each other and negatively related to those located on the opposite quadrant. Clustered variables also influence the PC model in similar ways.
|
| Display text labels
|
Select this check box to include variable or case identifiers (whichever is appropriate) in the graphs of scores and loading factors (lines and scatterplots). Case identifiers are expressed by their batch and observation memberships. For example, "B1, 10" means observation 10 in batch 1. Note that this option can't be used with control t charts.
|
| First
|
In this list, specify the principal component(s) for which you want to generate scores and loading factor plots and spreadsheets.
|
| Second
|
In this list, specify the principal component(s) for which you want to generate scores and loading factor plots and spreadsheets.
|
|
|
| Limits (t)
|
Use the options in this group box to define limits for the score plots (line or scatter).
|
| Multiple of std. dev.
|
Select this option button to define the upper and lower bounds for the score limits as control standard deviation.
|
| Compute from p
|
If you select this option button, STATISTICA will assume that the scores are normally distributed and the 99% confidence levels are used to define the upper and lower limits.
|
| Control
|
In this box, specify the control limits. When the Multiply std. dev. option button is selected (see this option description above), this value is multiplied by the computed standard deviation for defining the upper and lower limits.
|
| Warning
|
Select this check box to include an upper and a lower warning limit in the scores graph. Specify the warning limit in the adjacent box. For the Multiply std. dev. option, this value will be multiplied by the standard deviation for the scores to define the lower and upper warning limits.
|
