Regressions model the relationship between two variables as defined by a Conversion Table. In this relationship, one of the variables is independent (x) and the other is dependent (y).

Regressions can be used in hydrographic analysis to review a conversion table against manual gaugings in order to refine the stage (water level) to discharge relationship or rating (see Test and Modify Rating Tables). In this case the stage or depth of water is the primary "independent" data shown on the x axis and discharge, "dependent" upon the stage measurement, is shown on the y axis.

Using DataSight's Regressions Shift, you reverse this process and use the discharge as the primary "independent" data set and shift the "dependent" measured stage data, to take into account site specific conditions such as ice or sedimentation. This allows you to "shift" stage data as required by the United States Geological Survey (USGS) Standard for the Analysis and Processing of Surface-Water Data and Information. DataSight draws the shifted conversion table with a new reference where the curve axes are also transposed.

Apply Shift Analysis

1. In the Regressions window, load a Conversion Table.
2. Click Shift in the Regression group. A successful shift is indicated by yellow highlighted fields in your conversion table in the left panel.
3. Click OK to load your Gaugings with your shifted conversion table, or select gaugings of your choice by checking the selection box(es) against the Gauging(s) on the right.To view the coordinates of a gauging point on the chart, hover your mouse over it until its label is displayed. The gauging may be a single point measurement, and applicable over a certain period of time (see also Gage Height and Discharge).
4. Model your shifted conversion table using the following iterative process (See also Regression Analysis):
5. Select the range of the curve that you wish to analyse using Criteria. To achieve the best results, the conversion table should be analysed in sections where there is no major break or inflection in the table.
6. Customise the chart using Regressions as you see fit for your curve.

• (Optional) You can choose to copy values from the original table in the left panel into your output. This is helpful when only a subset of the Conversion Table rows needs to be manipulated.

To do this, right-click on a row you wish to copy to the output and select Copy Values to Output. To select multiple rows or a range of rows, hold down CTRL or SHIFT respectively when clicking on the rows. Then copy the values with the right-click menu.

It is possible to ignore the copied rows from affecting your curve (as they are already added to the output), by right-clicking on the row(s) and clicking Unselect. To include an unselected row into your curve, right-click on the row and click Select.

1. Analyse your table/rating with Regression Models.
2. Review the results then select or deselect points on the original table and/or gaugings to achieve a better "fit".
3. When you are happy with the "fit", highlight a value you wish to move across to the Output Table, right-click and select Copy Values to Output. To copy all the values, press CTRL + A, and then copy values to output with the right-click menu.
4. Once the new shifted conversion table is finalised, click Save to save the values in a Conversion Table.
5. Name the new shifted conversion table.
6. Set the Period of Applicability if required.
7. Apply to existing data to apply conversion to data set immediately (See Data Conversion for more details), or alternatively use the saved conversion table at a later date in a Calculation (See Use a Conversion Table for more details).

See also:

• Conversion Tables
• Calculations