In
statistics, a distribution is said to be skewed if it is not symmetric.
Skewness refers to the degree of asymmetry in a distribution. Skewed
distributions can be either skewed left or skewed right, depending on the
direction of the skewness.
- Skewed
right: A distribution is said to be skewed right if the tail on the
right-hand side of the distribution is longer or more spread out than the
left-hand side. This means that the distribution has a higher frequency of
values on the left side and a few extreme values on the right side. A skewed-right
distribution is also called a positive-skew distribution. Examples of
skewed-right distributions include income, wealth, and age distributions.
- Skewed
left: A distribution is said to be skewed left if the tail on the
left-hand side of the distribution is longer or more spread out than the
right-hand side. This means that the distribution has a higher frequency
of values on the right side and a few extreme values on the left side. A
skewed-left distribution is also called a negative-skew distribution.
Examples of skewed-left distributions include reaction times and time to
complete a task.
The
significance of both variances depends on the context and purpose of the
analysis. In general, a skewed distribution can have a significant impact on
the statistical analysis and interpretation of the results. For example, if the
distribution is skewed, the mean may not be a good measure of central tendency,
and it may be better to use the median. Additionally, the skewedness of a
distribution can affect the choice of statistical tests used to analyze the
data. For example, if the distribution is significantly skewed, it may be
necessary to use non-parametric tests instead of parametric tests.