What is 'Platykurtic'
Platykurtic describes a statistical distribution with extremely dispersed points along the X-axis that results in thinner tails than a normal distribution. Because this distribution has thin tails, it is less clustered around the mean than are mesokurtic and leptokurtic distributions. The prefix of the term, ‘platy’, means broad, and distributions are deemed platykurtic when the excess kurtosis value is negative owing to the fact that the distribution has more data in its tails and less data in its peak.
BREAKING DOWN 'Platykurtic'
Platykurtic distributions produce less extreme outliers compared to outliers found in a normal distribution. Investors often consider asset returns’ kurtosis because the distribution of values can offer an estimation of asset risk on potential investments.
Platykurtic distributions generally have a fairly basic and structured data layout; returns that follow this kind of distribution tend to have less major fluctuations than do asset with leptokurtic or normal distributions. For this reason, the investment comes with less risk.
Market, or equity, returns are regarded as being closer to leptokurtic distributions, as opposed to platykurtic and normal. Random and unpredictable events – otherwise known as black swans – are less likely to occur when market conditions are more platykurtic; black swan deviations don’t typically fall inside the short tails of platykurtic distributions. Cautious and traditional investors find investments with platykurtic return distributions best suited to their wants and needs.
Leptokurtic, Mesokurtic and Platykurtic
There are three basic data set distributions: leptokurtic, mesokurtic and platykurtic.
Leptokurtic distributions have data points on the X-axis that sit clustered and, thus, have higher kurtosis – or a higher peak – as a result. The curvature of leptokurtic distributions are higher than normal distributions and are significantly higher than platykurtic distributions. Leptokurtic distributions have fat tails that correspond with their high peaks, meaning that their distribution is more heavily clustered around the mean value; leptokurtic distributions are directly opposite of platykurtic distributions.
The kurtosis is a measurement of the ends of a distribution and is used to dictate the size of the tails of a data distribution. In dictating the size of the data distribution’s tails, kurtosis also works to measure the distribution’s peak. The coefficient for a normal distribution is three, indicative of data following a Gaussian distribution, with neither thin or fat tails. Thus, data distributions with a kurtosis higher than three – leptokurtic distributions – have fat tails and data distributions with a kurtosis of less than three – platykurtic distributions – have thin tails.