### How are baselines calculated in a Live Exceptions profile (Legacy KB ID CNC TS7933 )

book

calendar_today

CA eHealth

#### Issue/Introduction

Live Exceptions stores a normal value for each hour of the day, computed as the average value for that hour over the preceding six weeks (the default baseline).

A defined condition which compares the current data value to the normal value is an unusual value condition. Live Exceptions raises an alarm when the variable deviates from the normal value for the condition window. To determine the deviation from a normal value, Live Exceptions uses the statistical standard deviation, which measures the spread of a set of values from its average (normal) value. Live Exceptions expresses this value as a percentile. The percentile of a set of values with respect to a given value is the percentage of the number of values in the set which are below the given value.

For example, you might say that 50 is the 90th percentile value, meaning that 90% of the values in a set are below 50. This is an accurate statement of real multiples of standard deviation as well.

Live Exceptions also allows you to specify deviations by ordinary percentage and by absolute value. Concerning Time Over Dynamic Threshold values, over a period of time a series of data values will possess a distribution among the values presented. A distribution is normally summarized by stating its mean and standard deviation, concepts derived from the normal or bell curve distribution commonly found in statistical measurements.

The mean is the average value over the data set.

The standard deviation measures the average width of the deviation of the values from the mean. It is a measure of the likelihood that a particular series of values will change dramatically from its current trajectory.

In some cases, it is important to know when a value plus its standard deviation are above a defined threshold, that is, when the value is getting too close to the edge. This is the underlying concept of the Time Over Dynamic Threshold condition.

You can view the ToDT rule in two ways. One is to reduce a user-defined threshold by the standard deviation, and use the result as the actual threshold with which to compare the data value. Since the standard deviation is computed dynamically from the data, this explains the dynamic threshold term in the rule?s name. The idea can be summarized by the following simple formula for determining when a value is over the threshold: DataValue > UserThreshold - StandardDeviation

Another way to view this rule is by the "too close to the edge" analogy. Rearranging the formula slightly provides this viewpoint: DataValue + StandardDeviation > UserThreshold Note that this rule differs from simply defining a reduced threshold in that Live Exceptions computes the reduced threshold automatically, keeping track of day-to-day swings in usage of the variable. You do not need to continually adjust the threshold to the desired level of sensitivity.

.

Related Issues/Questions:
How is the baseline calculated for "time over dynamic threshold" in a Live Exceptions profile
How are baselines calculated in a Live Exceptions profile
How is "time over dynamic threshold" determined
How does Live Exceptions determine the "time over dynamic threshold"

Problem Environment:
Live Exceptions
eHealth