Right Skew
Definition
A distribution is right-skewed when its tail extends further to the right than to the left. Many forensic measurement quantities (trace concentrations, waiting times, particle counts) are right-skewed and cannot be modelled accurately by the symmetric normal distribution.
- Tail direction
- Extends further to the right
- Common examples
- Trace concentrations, waiting times, particle counts
- Modelling caution
- Symmetric normal distribution is a poor fit
Common questions
Why does right skew matter when choosing a statistical test in forensic casework?+
Applying tests that assume a symmetric normal distribution, such as an unadjusted t-test, to right-skewed data can produce misleading confidence intervals or significance results, so analysts often use a log transform or a non-parametric test instead.
How can an analyst check whether forensic data is right-skewed before analysis?+
A histogram or a comparison of the mean against the median is a quick check, since a mean noticeably larger than the median is a common sign of right skew in a dataset.
Related terms
- Likelihood Ratio (LR)
- The ratio of two conditional probabilities: the probability of the observed evidence given the prosecution's hypothesis (same source), divided by the probability...
- Parameters
- The numerical constants that define the specific shape of a distribution within its family. The normal distribution has two parameters (mean and...
- Probability Distribution
- A function that assigns probabilities to each possible value (or range of values) of a random variable. It fully characterises the uncertainty...
- Rate Parameter (Lambda)
- The single parameter of the Poisson distribution, equal to both the mean and the variance of the distribution. In forensic contexts lambda...
- Shape and Rate Parameters
- The two parameters of the gamma distribution. The shape parameter controls how peaked or spread the distribution is; the rate parameter (sometimes...