# Simulation Evaluation Node Settings Tab

On the Settings tab of the Simulation Evaluation node, you can specify the role of each field in your data set, and customize the output that is generated by the simulation.

**Select an item.** Enables you to switch between the three
views of the Simulation Evaluation node: Fields, Density Functions,
and Outputs.

Fields view

**Target field.** This is a required field. Click the arrow
to select the target field of your data set from the drop-down list.
The selected field can have either continuous, ordinal or nominal
measurement level, but cannot have date or an unspecified measurement
level.

**Iteration field (optional).** If your data has an iteration
field that indicates to which iteration each record in your data belongs,
you must select it here. This means that each iteration will be evaluated
separately. Only fields with continuous, ordinal or nominal measurement
levels can be selected.

**Input data is already sorted by iteration.** Only enabled
if an iteration field is specified in the Iteration field
(optional) field. Only select this option if you are sure
that your input data is already sorted by the iteration field specified
in Iteration field (optional).

**Maximum number of iterations to plot.** Only enabled if an
iteration field is specified in the Iteration field (optional) field.
Click the arrows to specify the number of iterations to plot. Specifying
this number avoids trying to plot too many iterations on a single
chart, which would make the plot difficult to interpret. The lowest
level that the maximum number of iterations can be set to is 2; the
highest level is 50. The maximum number of iterations to plot is initially
set to 10.

**Input fields for correlation tornado.** The correlation tornado
chart is a bar chart that displays the correlation coefficients between
the specified target and each of the specified inputs. Click the field
picker icon to select the input fields to be included in the tornado
chart, from a list of available simulated inputs. Only input fields
with continuous and ordinal measurement levels can be selected. Nominal,
typeless, and date input fields are not available in the list and
cannot be selected.

Density Functions view

With the options in this view, you can customize the output for probability density functions and cumulative distribution functions for continuous targets, as well as bar charts of predicted values for categorical targets.

**Density functions.**Density functions are the primary means of probing the set of outcomes from your simulation.

**Probability density function (PDF).**Select this option to produce a probability density function for the target field. The probability density function displays the distribution of the target values. You can use the probability density function to determine the probability that the target is within a particular region. For categorical targets (targets with a measurement level of nominal or ordinal) a bar chart is generated that displays the percentage of cases that fall in each category of the target.**Cumulative distribution function (CDF).**Select this option to produce a cumulative distribution function for the target field. The cumulative distribution function displays the probability that the value of the target is less than or equal to a specified value. It is only available for continuous targets.

**Reference lines (continuous).**These options are enabled if Probability density function (PDF), Cumulative distribution function (CDF), or both, are selected. With these options, you can add various fixed vertical reference lines to probability density functions and cumulative distribution functions.

**Mean.**Select this option to add a reference line at the mean value of the target field.**Median.**Select this option to add a reference line at the median value of the target field.**Standard Deviations.**Select this option to add reference lines at plus and minus a specified number of standard deviations from the mean of the target field. Selecting this option enables the adjoining Number field. Click the arrows to specify the number of standard deviations. The minimum number of standard deviations is 1 and the maximum is 10. The number of standard deviations is initially set to 3.**Percentiles.**Select this option to add reference lines at two percentile values of the distribution of the target field. Selecting this option enables the adjoining Bottom and Top text fields. For example, entering a value of 90 in the Top text field would add a reference line at the 90th percentile of the target, which is the value below which 90% of the observations fall. Likewise, a value of 10 in the Bottom text field represents the tenth percentile of the target, which is the value below which 10% of the observations fall.**Custom reference lines.**Select this option to add reference lines at specified values along the horizontal axis. Selecting this option enables the adjoining Values table. Every time that you enter a valid number into the Values table, a new empty row is appended to the bottom of the table. A valid number is a number within the range of values of the target field

**Categorical target (PDF only).**These options are only enabled if Probability density function (PDF) is selected.

**Category values to report.**For models with categorical target fields, the result of the model is a set of predicted probabilities, one for each category, that the target value falls in each category. The category with the highest probability is taken to be the predicted category and used in generating the bar chart for the probability density function. Select Predicted category to generate the bar chart. Select Predicted probabilities to generate histograms of the distribution of predicted probabilities for each of the categories of the target field. You can also select Both to generate both types of chart.**Grouping for sensitivity analysis.**Simulations that include sensitivity analysis iterations generate an independent target field (or predicted target field from a model) for each iteration that is defined by the analysis. There is one iteration for each value of the distribution parameter that is being varied. When iterations are present, the bar chart of the predicted category for a categorical target field is displayed as a clustered bar chart that includes the results for all iterations. Select either Group categories together or Group iterations together.

Outputs view

**Percentile values of target distributions.** With these options,
you can choose to create a table of percentile values of the target
distributions, and specify the percentiles to display.

**Create a table of percentile values.**For continuous target fields, select this option to obtain a table of specified percentiles of the target distributions. Choose one of the following options to specify the percentiles:

**Quartiles.**Quartiles are the 25th, 50th, and 75th percentiles of the target field distribution. The observations are divided into four groups of equal size.**Intervals.**If you want an equal number of groups other than four, select Intervals. Selecting this option enables the adjoining Number field. Click the arrows to specify the number of intervals. The minimum number of intervals is 2 and the maximum is 100. The number of intervals is initially set to 10.**Custom percentiles.**Select Custom percentiles to specify individual percentiles, for example, the 99th percentile. Selecting this option enables the adjoining Values table. Every time that you enter a valid number, between 1 and 100, into the Values table, a new empty row is appended to the bottom of the table.