average absolute deviation
- noun
- Specialized
:
desviación absoluta media
- To estimate the variability of the scores, we calculated the average absolute deviation.
Examples
-
The average absolute deviation is less sensitive to extreme values than the standard deviation.
-
Using the average absolute deviation provides a straightforward way to describe the spread of the data.
-
The average absolute deviation is a useful measure of variability.
-
To calculate the average absolute deviation, subtract each value from the mean.
-
To measure the consistency of the data, we computed the average absolute deviation from the mean.
-
The average absolute deviation gives a clear indication of how much the individual data points differ from the central value.
-
In analyzing the test results, the average absolute deviation was used to summarize the variability of students' scores.
Synonyms
A number that shows how far numbers usually are from the middle value
The average distance of each number from the group's average
A measure showing how much numbers differ from their average
How Variable
- Specialized
49
7.1
- Specialized
8
4.7
- Specialized
363
3.1
Surface Forms
Morphology
average + absolute + deviation
The phrase is compositionally built — 'average' (a mean) of 'absolute deviation' (deviations without regard to sign) — so its basic idea (a summary measure of how far values differ from a central value) can be inferred from the parts. However, the specific statistical sense of 'absolute' (absolute value) and the procedural meaning (take absolute differences then average them) is technical and not fully predictable to a B1 learner without some mathematical background, so full understanding requires domain knowledge.
Etymology
The noun average absolute deviation comes from a simple picture: deviation is how far each number is from the center, absolute means we only use the size of that distance, not the direction, and average means we take the usual size of those distances. So the phrase describes a single number that tells us the 'spread' of the data.