Difference between revisions of "Understanding Skewness"
(Created page with "File:Example.jpg '''A perfectly symmetrical data set''' will have a skewness of 0. Therefore, the normal distribution has a skewness of 0. -0.5 < skewness < 0.5, the dat...") |
|||
| Line 1: | Line 1: | ||
| − | [[File: | + | [[File:skewnessexample.png]] |
'''A perfectly symmetrical data set''' will have a skewness of 0. Therefore, the normal distribution has a skewness of 0. | '''A perfectly symmetrical data set''' will have a skewness of 0. Therefore, the normal distribution has a skewness of 0. | ||
Latest revision as of 12:39, 11 May 2022
A perfectly symmetrical data set will have a skewness of 0. Therefore, the normal distribution has a skewness of 0.
-0.5 < skewness < 0.5, the data are fairly symmetrical.
-1 < skewness < — 0.5 or 0.5 < skewness < 1, the data are moderately skewed
- 1 < skewness or skewness < -1, the data are highly skewed
Kurtosis describes how peaked the curve is. First, it sees whether the data are heavy-tailed (fat) or light-tailed relative to a normal distribution(the tallness of the central peak). It also measures the amount of probability in the tails (the sharpness of the central peak) (Sapountzi, 2018).
Reference: Sapountzi, A. (2018). Descriptive Statistics/Tell me the Summary of What Happened.
contributed by Marigrace Walker
