How to determine what is an outlier

Identifying outliers Use the outlier feature in Analytics to identify records that are out of the ordinary and could require closer scrutiny. What are outliers? Example of an outlier in a group.

Note A record can be an outlier for a legitimate reason. Example of outliers in an entire set of records. Identifying outliers for a set of numbers. You want to identify any outliers in the following set of numbers: -3, -3, -1, 2, 3, 5, 6, 6, 8, 11 The mean average of the numbers is 3.

Note Key fields and the outlier field are automatically included in the output table, and do not need to be selected. Note The If condition is evaluated against only the records remaining in a table after any scope options have been applied First , Next , While.

Note If you select Median , the outlier field must be sorted. Tip If the data you are examining for outliers is significantly skewed, Median might produce results that are more representative of the bulk of the data. Note For the same set of data, as you increase the number of standard deviations, you potentially decrease the number of outliers in the output results.

Note The key field or fields must be sorted. Note Sorting a computed outlier field is an internal, technical requirement of Analytics.

Tip If the appropriate field or fields in the input table are already sorted, you can save processing time by not selecting Presort. Note The number of records specified in the First or Next options references either the physical or the indexed order of records in a table, and disregards any filtering or quick sorting applied to the view. Page options. Is this page helpful?

Feedback received. Would you take a moment to tell us what's wrong? Content needs more detail Content has errors Content is confusing Not what I'm looking for Different issue You can also contact support. Analytics Use a smaller standard deviation multiple. Try starting with 1. Use decimal multiples such as 1. The data is skewed, with a small percentage of the values being large, or small, when compared to the rest of the data.

Use Median , instead of Average , as the method for calculating the center point of the values that you are examining. The method used for calculating the center point of the values in the outlier field. Average use the average mean of the values in the field Median use the median of the values in the field The center point is used in calculating the standard deviation of the values in the outlier field.

In the outlier field, the number of standard deviations from the mean or the median to the upper and lower outlier boundaries. You can specify any positive integer or decimal numeral 0.

For example, specifying 2 establishes, for each key field group, or for the field as a whole: an upper outlier boundary 2 standard deviations greater than the mean or the median a lower outlier boundary 2 standard deviations less than the mean or the median Any value in the outlier field greater than an upper boundary, or less than a lower boundary, is included as an outlier in the output results.

The field or fields to use for grouping the data in the table. Do not group the data in the table. The numeric field to examine for outliers. You can examine only one field at a time. One or more additional fields to include in the output. Allows you to create a condition to exclude records from processing. Specifies the name and location of the output table. To save the output table to the Analytics project folder enter only the table name.

No account yet? Create an account. Edit this Article. We use cookies to make wikiHow great. By using our site, you agree to our cookie policy. Cookie Settings. Learn why people trust wikiHow. Download Article Explore this Article Steps. Tips and Warnings. Things You'll Need. Related Articles. Article Summary. Learn how to recognize potential outliers. Before deciding whether or not to omit outlying values from a given data set, first, obviously, we must identify the data set's potential outliers.

Generally speaking, outliers are data points that differ greatly from the trend expressed by the other values in the data set - in other words, they lie outside the other values. It's usually easy to detect this on data tables or especially on graphs. If, for instance, the majority of the points in a data set form a straight line, outlying values will not be able to be reasonably construed to conform to the line.

Let's consider a data set that represents the temperatures of 12 different objects in a room. If 11 of the objects have temperatures within a few degrees of 70 degrees Fahrenheit 21 degrees Celsius , but the twelfth object, an oven, has a temperature of degrees Fahrenheit degrees Celsius , a cursory examination can tell you that the oven is a likely outlier.. Arrange all data points from lowest to highest.

The first step when calculating outliers in a data set is to find the median middle value of the data set. This task is greatly simplified if the values in the data set are arranged in order of least to greatest. So, before continuing, sort the values in your data set in this fashion.

Let's continue with the example above. Calculate the median of the data set. The median of a data set is the data point above which half of the data sits and below which half of the data sits - essentially, it's the "middle" point in a data set. However, if there are an even number of points, then, since there is no single middle point, the 2 middle points should be averaged to find the median.

Note that, when calculating outliers, the median is usually assigned the variable Q2 - - this is because it lies between Q1 and Q3, the lower and upper quartiles, which we will define later. Don't be confused by data sets with even numbers of points - the average of the two middle points will often be a number that doesn't appear in the data set itself - this is OK. However, if the two middle points are the same number, the average, obviously, will be this number as well, which is also OK.

In our example, we have 12 points. The middle 2 terms are points 6 and 7 - 70 and 71, respectively. Calculate the lower quartile. This point, to which we will assign the variable Q1, is the data point below which 25 percent or one quarter of the observations set. In other words, this is the halfway point of the points in your data set below the median. If there are an even number of values below the median, you once again must average the two middle values to find Q1, much like you may have had to do to find the median itself.

In our example, 6 points lie above the median and 6 points lie below it. This means that, to find the lower quartile, we will need to average the two middle points of the bottom six points. Points 3 and 4 of the bottom 6 are both equal to Calculate the upper quartile. This point, which is assigned the variable Q3, is the data point above which 25 percent of the data sits. Finding Q3 is almost identical to finding Q1, except that, in this case, the points above the median, rather than below it, are taken into account.

Continuing with the example above, the two middle points of the 6 points above the median are 71 and Find the interquartile range. Now that we've defined Q1 and Q3, we need to calculate the distance between these two variables. The distance from Q1 to Q3 is found by subtracting Q1 from Q3.

The value you obtain for the interquartile range is vital for determining the boundaries for non-outlier points in your data set. In our example, our values for Q1 and Q3 are 70 and To find the interquartile range, we subtract Q3 - Q1: Note that this works even if Q1, Q3, or both are negative numbers.

For example, if our Q1 value was , our interquartile range would be Find the "inner fences" for the data set. Using the and formulas, we can determine that both the minimum and maximum values of the data set are outliers.

This allows us to determine that there is at least one outlier in the upper side of the data set and at least one outlier in the lower side of the data set. Without any more information, we are not able to determine the exact number of outliers in the entire data set. Step 1: Recall the definition of an outlier as any value in a data set that is greater than or less than.

Step 2: Calculate the IQR, which is the third quartile minus the first quartile, or. To find and , first write the data in ascending order. Then, find the median, which is. Next, Find the median of data below , which is. Do the same for the data above to get. Step No values less than A certain distribution has a 1st quartile of 8 and a 3rd quartile of Which of the following data points would be considered an outlier?

An outlier is any data point that falls above the 3rd quartile and below the first quartile. The inter-quartile range is and. The lower bound would be and the upper bound would be. The only possible answer outside of this range is. If you've found an issue with this question, please let us know.

With the help of the community we can continue to improve our educational resources. If Varsity Tutors takes action in response to an Infringement Notice, it will make a good faith attempt to contact the party that made such content available by means of the most recent email address, if any, provided by such party to Varsity Tutors.

Your Infringement Notice may be forwarded to the party that made the content available or to third parties such as ChillingEffects. Thus, if you are not sure content located on or linked-to by the Website infringes your copyright, you should consider first contacting an attorney.

Hanley Rd, Suite St. Louis, MO Subject optional. Email address: Your name:. Example Question 11 : Bivariate Data. Use the following five number summary to determine if there are any outliers in the data set: Minimum: Q1: Median: Q3: Maximum:. Possible Answers: There is at least one outlier on the high end of the distribution and no outliers on the low end of the distribution.

It is not possible to determine if there are outliers based on the information given. Correct answer: There are no outliers. Explanation : An observation is an outlier if it falls more than above the upper quartile or more than below the lower quartile.