Reports | Findings ANOVA

Findings ANOVA
This report screens all findings measurements for a specified domain one at a time by performing a repeated-measures analysis of variance . The baseline measurements can be considered as a covariate or as a response. A measurement is determined to be a baseline measurement by the xxBLFL variable where xx is substituted with the 2-letter code for the chosen domain for analysis. If this variable does not exist, baseline is calculated from measurements taken on or before day 1 of the study. A time can be specified to determine baseline measurements. A compound symmetry covariance structure is assumed within each subject. A separate model is fit for each lab measurement. You can also separate the data into time s. A volcano plot of the interaction effect and other output enable efficient screening of lab scores that differ between treatment groups.
For the LB domain, lab measurements are standardized by a reference range derived from the lower limit of normal (LLN) and upper limit of normal (ULN) to facilitate comparisons.
Note : JMP Clinical uses a special protocol for data including non-unique Findings test names. Refer to How does JMP Clinical handle non-unique Findings test names? for more information.
Report Results Description
Running this report for Nicardipine using default settings generates the tabbed Report shown below. Results organized in sections. Each sections contains one or more plots, data panels, data filters, or other elements that facilitate your analysis.
Results Section
This pane enables you to access and view the output plots and associated data sets on each tab. Use the drop-down menu to view the section in the Results pane or remove the section and its contents from the Results pane.
LB Results
Shows the primary results from the analysis, including Volcano Plot s and various analyses on least squares means.
Note : The name of this section and the findings results ( LB , VS , or EG ) displayed depend on the domain selected using the Findings Domain to Analyze option.
This section provides a comprehensive summary of ANOVA model fitting results. It is important to keep in mind which model was fit and to carefully consider hypotheses of interest. Depending on the variability in your data and your objectives, you might wish to alter the significance criterion to obtain fewer or more significant Findings tests. The numerous -down options are valuable for exploring interesting subsets.
This section contains the following elements:
A series of volcano plots .
Volcano plots are a convenient way to summarize a specific hypothesis test across all Findings tests. Each plot is based on a single hypothesis of interest and each point in the plot is a Findings test. The X axis represents a difference or estimate and the Y axis its corresponding -log 10 ( p-value ). Volcano plots have a characteristic "V" shape because estimates near zero (0) tend not to be significant and those away from zero tend to have smaller p -values and larger -log 10 ( p -values). Significant Findings tests are those in the upper left and right quadrants of the plot, akin to exploding pieces of molten lava. The red dashed horizontal line usually represents a significant criterion computed by some multiple testing method like FDR . You can change this value with an action button in the left panel. You can also resize all of the plots with a slider above them.
When interpreting volcano plots, it is important keep in mind the direction of the difference on the X axis. For example, the plot from the Nicardipine example shown above has Diff of TRT01P = (NIC .15)-(Placebo) on the X axis. Positive differences are located on the right side, whereas negative differences are located on the left.
You can mouse over points of interest to see their labels or select points by dragging a mouse rectangle over them. Use the lasso tool to select irregular regions. To find specific Findings tests whose identifier you know, click Results in the Tabs section, and then click View Data . In the subsequently opened data table, click Edit > Search , and type in the desired search string. Any Findings tests that you select in the table is highlighted in the graphs and vice versa. Selected Findings tests are highlighted in other plots and you can also then click on various Down Buttons on the left-hand side for further analyses on those specific Findings tests.
Volcano plots are generated for the set of LS means you specify in the input dialog (for example, all possible pairs or differences with a control) as well as for all custom ESTIMATE statements that you specify.
See Volcano Plot for more information.
A dendrogram showing the Hierarchical Clustering of Standardized LSMeans .
This plot enables you to compare expression patterns for all significant Findings tests simultaneously. The standardized least squares means for every Findings test that is significant in at least one volcano plot are clustered both horizontally and vertically and depicted with a heat map. The standardization is to mean zero (0) and variance one (1). Each row of the heat map is a Findings test and each column is a distinct LS mean. You can see which Findings tests and LS means have similar profiles. You can click on branches of the horizontal dendrogram to select all Findings tests in that cluster. These Findings tests are then highlighted in other plots, and you can click on the Down Buttons on the left-hand side for further analyses.
Click and slide the cross-hair point at the top or bottom of the horizontal dendrogram to change the number of colored cluster groups.
See Heat Map and Dendrogram for more information.
A parallel plot of LSMeans.
This plot shows the unstandardized LS means, enabling you to see degree of overall results for the same set of significant Findings tests.
See Parallel Plot for more information.
This plot provides an alternative way of comparing significant LS means. It computes a principal components analysis on them and plots the first two components. This projects high-dimensional patterns into two dimensions. Findings tests that cluster together in this plot tend to also cluster together in the hierarchical clustering and parallel plots. This plot can help identify outliers. Points near the outer virtual bounding ellipse are well-explained by the first two principal components.
See Principal Components Analysis Plot for more information.
Variability Estimates
Shows the analyses on variance component estimates from the ANOVA model fits.
The Variability Estimates section contains the results of a distribution and multivariate analysis for each sample.
These show the distributions of each of the variance component estimates from the fitted ANOVA models, including quantiles and summary statistics. You can see which variance components are explaining the most variability across Findings (or adverse event ) tests. RSquare is an approximation to the proportion of variability explained by the model . The quantiles can be useful when conducting a power and sample size exercise.
See Distribution for more information.
Multivariate Analysis.
These plots provide a multivariate analysis of the variance component estimates, including their correlations and a scatterplot matrix. These reveal interrelationships between the components and how they compete to explain variability.
See Scatterplot Matrix for more information.
Output Data
This pane provides links to the following output data sets:
Significant Differences Data Set : This output data set contains a complete list of the Findings tests significant by one or more criteria. This data set is indicated by the _sig suffix. Click Open to view the data set.
Stacked Data Set : Contains findings measurements at subject level in a stacked format. Click Open to view the data set.
Experimental Design Data Set : This is a SAS data set that provides information about the columns of a tall data set. It describes relevant experimental variables such as treatment conditions and covariates as well as a variable named ColumnName. Refer to The Example Data for more information. Click Open to view the data set.
Action Buttons
Action buttons, provide you with an easy way to drill down into your data. The following action buttons are generated by this report:
Fit Model and Plot LS Means : Select points or rows and click to select variable (s) that uniquely define wide column names. Selected Findings tests are analyzed in the JMP Fit Model platform to view detailed fitting results and plots. Attention : Read the warning found in the link.
Construct One-way Plots : Click to plot the original data in one-way format using treatment variables of your choice.
Trend Plots : Select Findings tests of interest and click to run the Findings Time Trends report to plot the time course of measurements along the trial for selected tests.
Shift Plot : Select Findings tests of interest and click to run the Findings Shift Plots report to show differences between baseline and on-treatment findings measurements for selected tests.
Box Plot : Select Findings tests of interest and click to run the Findings Box Plots report to show the distributions of measurement values for the selected tests.
Waterfall Plot : Click to launch a dialog from which you can generate a waterfall plot to show the distribution of changes in test measurements for the selected Findings domain across subjects
Click to generate a standardized pdf - or rtf -formatted report containing the plots and charts of selected sections.
Click the Options arrow to reopen the completed report dialog used to generate this output.
Click the gray border to the left of the Options tab to open a dynamic report navigator that lists all of the reports in the review. Refer to Report Navigator for more information.
Report Options
Report Option Descriptions
Specific documentation for each of the options can be viewed by clicking on the following links:
General Options
Findings Domain to Analyze , Findings Domain Tests for Analysis
Treatment or Comparison Variable to Use , Treatment or Comparison Variable
Normalization of Lab Measurements
Subject Filter 1
Additional Filters
Additional Filter to Include Subjects 2 , Merge supplemental domain , Include the following findings records: , Additional Filter to Include Findings Tests , Select the population to include in the analysis , By Variables
Model baseline as: , Time Scale , Baseline Time Window , Calculate baseline as: , Trial Time Windows
Additional Class Variables , Additional Fixed Effects , Random Effects
LSMeans Difference Set for Volcano Plots , LSMeans Treatment Control Level
Multiple Testing Method , Alpha , -l og 10 (p-Value) Cutoff
Additional Filter for Significant Tests
Include T-statistics , Include p-values in addition to -log 10 (p-values) , Plot standardized residuals

Subject-specific filters must be created using the Create Subject Filter report prior to your analysis.

For more information about how to specify a filter using this option, see The SAS WHERE Expression .