conditionalprob.JGR: Dialog box for computing and plotting conditional...

In CADStat: Provides a GUI to Several Statistical Methods

Description

Computes and plots conditional probabilities of an event (e.g., an undesirable biological condition) given values of a another variable (e.g., a stressor).

Details

A conditional probability plot provides a graphical representation of the impact one variable can have on the probability of another occuring. One way to assess whether the probability of an event of interest occuring changes for different values of an explanatory variable is to consider how susets of the response change as a function of the explanatory variable.

The first variable is the response. It is this column that subsets will be taken from based on a user-specified conditioanl value. The condfitional value must be between the maximum and minimum values of the response variable. The second variable is the explanatory variable.

It is often the case in biological applications, that thresholds exist. Conditional probability plots are useful for qualitatively identifying thresholds when they may exist.Conditional probability plots are often used in the development of tolerance values. Once the empirical curve for conditional probability is generated, possible threshold levels for eliciting impact can be identified for eventual use in the development of stressor criteria. This threshold of impact is determined by the identification of a changepoint that separates the empirical curve into two groups so that the probability of impact is different for samples above and below the changepoint. There are three potential methods for the identification of thresholds of impact for the conditional probability empirical curves. These include: 1) change in curvature of fitted curve, 2) nonparametric deviance reduction, and 3)non-overlapping confidence intervals (CIS). For a detailed explanation of these methods see Paul and McDonald (Journal of the American Water Resources Association 41(5) p. 1211-1223 2005).

Once thresholds have been identified, it may be of interest to utilize additional analyses that will quantify the relationship between the subsetted data. Specifically, one may choose to compute the correlation between the variables in the conditional dataset or if a threshold exists it may be of interest to generate a regression line for the sets of probabilities that are both above and below a threshold.

User Interface

Select Analysis Tools -> Conditional Probability from the menus. A dialog box will open. Select the data set of interest from the pull-down menu, or browse for a tab-delimited text file. The Data Subsetting tab can be used to select a subset of the data file by choosing a variable from the pull down menu and then selecting the levels of that variable to include. You can hold down the <CTRL> key to select several levels.

Select Stressor and Response variables from the pull-down menu. If each sample in your data set represents a different proportion of your population (e.g., data collected using a stratified random sampling design), you can Specify a weighting variable that provides the relative weight for each sample.

Assign a Response Cutoff Value. This value defines the threshold for defining your response of interest. For example, if your response is an IBI, the Response Cutoff Value would be the criterion value for your IBI below which the site is assess as biologically impaired. Selection of the Cutoff Value Direction depends on whether you expect the value of your response to increase or decrease with stress. For IBI, which decreases with stress, Cutoff Value Direction would be Less Than.

Probability Direction defines the direction in which you would like to assess the stressor level. For a stressor whose severity increases with increasing values (e.g., percent fines), you should select Greater Than or Equal. Other stressors (e.g., pH) increase in severity as their value decreases, in which case you would select Less Than or Equal.

Selecting Bootstrap confidence intervals directs the tool to repeatedly resample the data set to estimate confidence intervals on the estimate relationship.

You may change the axes labels and plot title by typing them in the Plot Labels dialog.

The output is a graph of the fitted probability (that the dependent variable is less than the conditional value) versus the independent variable.

CADStat documentation built on May 1, 2019, 6:51 p.m.