From Eigenvector Research Documentation Wiki
Jump to navigation Jump to search


Univariate trend- and image-analysis tool.


results = trendtool(data,markers) %apply markers to new data


TRENDTOOL allows the user to graphically perform univariate analysis of time or otherwise-ordered data. Inputs are axis which is the variable scale to plot against [can be omitted] and data the data to plot. Recall that the convention is that rows are samples and columns are variables. If data is omitted, the user is prompted to load a DataSet to analyze.

By placing markers, the response at individual variables can be viewed in a "Trend Plot" (often, this tool is used with data collected as a function of time, thus the term "trend".) In addition to examining individual responses at given variables, several other analysis methods are available including integrated area, peak position, and peak width.

Graphical Operations

Right-clicking on the trend data plot allows placement of "markers". Markers return the height at a point ('height' mode), integrated area between two points ('area' mode) , position of the maximum value between two points ('position' mode) , or full-width at half-height of the maximum between two points ('width' mode).

Reference markers can be added to each marker to subtract the height at a point or subtract a two-point baseline from the associated marker. Right-click a marker to add a reference marker and then right-click that reference marker to convert it into a pair of baseline markers. See also detailed instructions for baseline correction with trendtool.

Markers can be saved or loaded using toolbar buttons. A Waterfall plot (linked to axis range shown in data plot) can be created using the waterfall toolbar button.

Results of the analysis are plotted in the trend results plot showing color-coded results of the univariate analysis. It also allows saving analysis results and selection of points to show in the trend data figure.

See also TrendTool for images for information on how to use the interface with Image type data.

Applying trend markers to new data: Trend markers can be saved using the save toolbar button in the GUI. These markers can be applied to new data by calling trendtool with the new data and the markers as input. In this case, no GUI is created and the results are simply returned to the caller as a DataSet object.

See Also

pca, plotgui, TrendTool EVRIGUI Object , Baseline correction with trendtool