Log-normal distribution
In probability theory, a log-normal distribution is a continuous probability distribution of a random variable whose logarithm is normally distributed. Thus, if the random variable is log-normally distributed, then has a normal distribution. Equivalently, if has a normal distribution, then the exponential function of,, has a log-normal distribution. A random variable which is log-normally distributed takes only positive real values. It is a convenient and useful model for measurements in exact and engineering sciences as well as medicine, economics and other fields, e.g. for energies, concentrations, lengths, financial returns and other amounts.
The distribution is occasionally referred to as the Galton distribution or Galton's distribution, after Francis Galton. The log-normal distribution has also been associated with other names, such as McAlister, Gibrat and Cobb–Douglas.
A log-normal process is the statistical realization of the multiplicative product of many independent random variables, each of which is positive. This is justified by considering the central limit theorem in the log domain. The log-normal distribution is the maximum entropy probability distribution for a random variate for which the mean and variance of are specified.
Definitions
Generation and parameters
Let be a standard normal variable, and let and be two real numbers. Then, the distribution of the random variableis called the log-normal distribution with parameters and. These are the expected value and standard deviation of the variable's natural logarithm, not the expectation and standard deviation of itself.
This relationship is true regardless of the base of the logarithmic or exponential function. If is normally distributed, then so is, for any two positive numbers. Likewise, if is log-normally distributed, then so is, where.
In order to produce a distribution with desired mean and variance, one uses
and
Alternatively, the "multiplicative" or "geometric" parameters and can be used. They have a more direct interpretation: is the median of the distribution, and is useful for determining "scatter" intervals, see below.
Probability density function
A positive random variable X is log-normally distributed if the logarithm of X is normally distributed,Let and be respectively the cumulative probability distribution function and the probability density function of the N distribution.
Then we have
Cumulative distribution function
The cumulative distribution function iswhere is the cumulative distribution function of the standard normal distribution.
This may also be expressed as follows:
where erfc is the complementary error function.
Multivariate log-normal
If is a multivariate normal distribution then has a multivariate log-normal distribution with meanand covariance matrix
Since the multivariate log-normal distribution is not widely used, the rest of this entry only deals with the univariate distribution.
Characteristic function and moment generating function
All moments of the log-normal distribution exist andThis can be derived by letting within the integral. However, the expected value is not defined for any positive value of the argument as the defining integral diverges. In consequence the moment generating function is not defined. The last is related to the fact that the lognormal distribution is not uniquely determined by its moments.
The characteristic function is defined for real values of but is not defined for any complex value of that has a negative imaginary part, and therefore the characteristic function is not analytic at the origin. In consequence, the characteristic function of the log-normal distribution cannot be represented as an infinite convergent series. In particular, its Taylor formal series diverges:
However, a number of alternative divergent series representations have been obtained.
A closed-form formula for the characteristic function with in the domain of convergence is not known. A relatively simple approximating formula is available in closed form and given by
where is the Lambert W function. This approximation is derived via an asymptotic method but it stays sharp all over the domain of convergence of.
Properties
Geometric or multiplicative moments
The geometric or multiplicative mean of the log-normal distribution is. It equals the median. The geometric or multiplicative standard deviation is. By analogy with the arithmetic statistics, one can define a geometric variance,, and a geometric coefficient of variation, has been proposed. This term was intended to be analogous to the coefficient of variation, for describing multiplicative variation in log-normal data, but this definition of GCV has no theoretical basis as an estimate of itself.Note that the geometric mean is smaller than the arithmetic mean. This is due to the AM–GM inequality, and corresponds to the logarithm being convex down. In fact,
In finance the term is sometimes interpreted as a convexity correction. From the point of view of stochastic calculus, this is the same correction term as in Itō's lemma for geometric Brownian motion.
Arithmetic moments
For any real or complex number, the -th moment of a log-normally distributed variable is given bySpecifically, the arithmetic mean, expected square, arithmetic variance, and arithmetic standard deviation of a log-normally distributed variable are given by
respectively.
The arithmetic coefficient of variation is the ratio. For a log-normal distribution it is equal to
This estimate is sometimes referred to as the "geometric CV" because of its use of the geometric variance. Contrary to the arithmetic standard deviation, the arithmetic coefficient of variation is independent of the arithmetic mean.
The parameters and can be obtained if the arithmetic mean and the arithmetic variance are known:
A probability distribution is not uniquely determined by the moments for. That is, there exist other distributions with the same set of moments. In fact, there is a whole family of distributions with the same moments as the log-normal distribution.
Mode, median, quantiles
The mode is the point of global maximum of the probability density function. In particular, it solves the equation :Since the log-transformed variable has a normal distribution and quantiles are preserved under monotonic transformations, the quantiles of are
where is the quantile of the standard normal distribution.
Specifically, the median of a log-normal distribution is equal to its multiplicative mean,
Partial expectation
The partial expectation of a random variable with respect to a threshold is defined asAlternatively, and using the definition of conditional expectation, it can be written as. For a log-normal random variable the partial expectation is given by:
where is the normal cumulative distribution function. The derivation of the formula is provided in the discussion of this Wikipedia entry. The partial expectation formula has applications in insurance and economics, it is used in solving the partial differential equation leading to the Black–Scholes formula.
Conditional expectation
The conditional expectation of a lognormal random variable with respect to a threshold is its partial expectation divided by the cumulative probability of being in that range:Alternative parameterizations
In addition to the characterization by or, here are multiple ways how the lognormal distribution can be parameterized. ProbOnto, the knowledge base and ontology of probability distributions lists seven such forms:- Normal1 with mean, μ, and standard deviation, σ
- :
- LogNormal2 with mean, μ, and variance, υ, both on the log-scale
- :
- LogNormal3 with median, m, on the natural scale and standard deviation, σ, on the log-scale
- :
- LogNormal4 with median, m, and coefficient of variation, cv, both on the natural scale
- :
- LogNormal5 with mean, μ, and precision, τ, both on the log-scale
- :
- LogNormal6 with median, m, and geometric standard deviation, σg, both on the natural scale
- :
- LogNormal7 with mean, μN, and standard deviation, σN, both on the natural scale
- :
Examples for re-parameterization
For the transition following formulas hold
For the transition following formulas hold
All remaining re-parameterisation formulas can be found in the specification document on the project website.
Multiple, Reciprocal, Power
- Multiplication by a constant: If then
- Reciprocal: If then
- Power: If then for
Multiplication and division of independent, log-normal random variables
More generally, if are independent, log-normally distributed variables, then
Multiplicative Central Limit Theorem
The geometric or multiplicative mean of independent, identically distributed, positive random variables shows, for approximately a log-normal distribution with parameters and, as the usual Central Limit Theorem, applied to the log-transformed variables, proves. That distribution approaches a Gaussian distribution, since decreases to 0.Other
A set of data that arises from the log-normal distribution has a symmetric Lorenz curve.The harmonic, geometric and arithmetic means of this distribution are related; such relation is given by
Log-normal distributions are infinitely divisible, but they are not stable distributions, which can be easily drawn from.
Related distributions
- If is a normal distribution, then
- If is distributed log-normally, then is a normal random variable.
- Let be independent log-normally distributed variables with possibly varying and parameters, and. The distribution of has no closed-form expression, but can be reasonably approximated by another log-normal distribution at the right tail. Its probability density function at the neighborhood of 0 has been characterized and it does not resemble any log-normal distribution. A commonly used approximation due to L.F. Fenton is obtained by matching the mean and variance of another lognormal distribution:
- If then is said to have a Three-parameter log-normal distribution with support.,.
- The lognormal distribution is a special case of the semi-bounded Johnson distribution.
- If with, then .
- A substitute for the log-normal whose integral can be expressed in terms of more elementary functions can be obtained based on the logistic distribution to get an approximation for the CDF
Statistical Inference
Estimation of parameters
For determining the maximum likelihood estimators of the log-normal distribution parameters μ and σ, we can use the same procedure as for the normal distribution. Note thatwhere is the density function of the normal distribution. Therefore, the log-likelihood function is
Since the first term is constant with regard to μ and σ, both logarithmic likelihood functions, and, reach their maximum with the same and. Hence, the maximum likelihood estimators are identical to those for a normal distribution for the observations,
For finite n, these estimators are biased. Whereas the bias for is negligible, a less biased estimator for is obtained as for the normal distribution by replacing the denominator n by n-1 in the equation for.
When the individual values are not available, but the sample's mean and standard deviation s is, then the corresponding parameters are determined by the following formulas, obtained from solving the equations for the expectation and variance for and :
Statistics
The most efficient way to analyze log-normally distributed data consists of applying the well-known methods based on the normal distribution to logarithmically transformed data and then to back-transform results if appropriate.Scatter intervals
A basic example is given by scatter intervals: For the normal distribution, the interval contains approximately two thirds of the probability, and contain 95 %. Therefore, for a log-normal distribution,of the probability. Using estimated parameters, the approximately the same percentages of the data should be contained in these intervals.
Confidence interval for
Using the principle, note that a confidence interval for is, where is the standard error and q is the 97.5 % quantile of a t distribution with n-1 degrees of freedom. Back-transformation leads to a confidence interval for,Extremal principle of entropy to fix the free parameter
- In applications, is a parameter to be determined. For growing processes balanced by production and dissipation, the use of a extremal principle of Shannon entropy shows that
- This value can then be used to give some scaling relation between the inflexion point and maximum point of the lognormal distribution. It is shown that this relationship is determined by the base of natural logarithm,, and exhibits some geometrical similarity to the minimal surface energy principle.
- These scaling relations are shown to be useful for predicting a number of growth processes .
- For instance, the lognormal function with such fits well with the size of secondary produced droplet during droplet impact and the spreading of one epidemic disease.
- The value is used to provide a probabilistic solution for the Drake equation.
Occurrence and applications
This multiplicative version of the central limit theorem is also known as Gibrat's law, after Robert Gibrat who formulated it for companies. If the rate of accumulation of these small changes does not vary over time, growth becomes independent of size. Even if that's not true, the size distributions at any age of things that grow over time tends to be log-normal.
A second justification is based on the observation that fundamental natural laws imply multiplications and divisions of positive variables. Examples are the simple gravitation law connecting masses and distance with the resulting force, or the formula for equilibrium concentrations of chemicals in a solution that connects concentrations of educts and products. Assuming log-normal distributions of the variables involved leads to consistent models in these cases.
Even if none of these justifications apply, the log-normal distribution is often a plausible and empirically adequate model. Examples include the following:
- Human behaviors
- * The length of comments posted in Internet discussion forums follows a log-normal distribution.
- * Users' dwell time on online articles follows a log-normal distribution.
- * The length of chess games tends to follow a log normal distribution.
- * Onset durations of acoustic comparison stimuli that are matched to a standard stimulus follow a log-normal distribution.
- * Rubik's Cube solves, both general or by person, appear to be following a log-normal distribution.
- In biology and medicine
- * Measures of size of living tissue.
- * For highly communicable epidemics, such as SARS in 2003, if public intervention control policies are involved, the number of hospitalized cases is shown to satisfy the lognormal distribution with no free parameters if an entropy is assumed and the standard deviation is determined by the principle of maximum rate of entropy production.
- * The length of inert appendages of biological specimens, in the direction of growth.
- * The normalised RNA-Seq readcount for any genomic region can be well approximated by log-normal distribution.
- * The PacBio sequencing read length follows a log-normal distribution.
- * Certain physiological measurements, such as blood pressure of adult humans.
- * In neuroscience, the distribution of firing rates across a population of neurons is often approximately lognormal. This has been first observed in the cortex and striatum and later in hippocampus and entorhinal cortex, and elsewhere in the brain. Also, intrinsic gain distributions and synaptic weight distributions appear to be lognormal as well.
- In colloidal chemistry and polymer chemistry
- *Particle size distributions.
- * Molar mass distributions.
- In hydrology, the log-normal distribution is used to analyze extreme values of such variables as monthly and annual maximum values of daily rainfall and river discharge volumes.
- In social sciences and demographics
- * In economics, there is evidence that the income of 97%–99% of the population is distributed log-normally. .
- * In finance, in particular the Black–Scholes model, changes in the logarithm of exchange rates, price indices, and stock market indices are assumed normal. However, some mathematicians such as Benoit Mandelbrot have argued that log-Lévy distributions, which possesses heavy tails would be a more appropriate model, in particular for the analysis for stock market crashes. Indeed, stock price distributions typically exhibit a fat tail. The fat tailed distribution of changes during stock market crashes invalidate the assumptions of the central limit theorem.
- * In scientometrics, the number of citations to journal articles and patents follows a discrete log-normal distribution.
- * City sizes.
- Technology
- * In reliability analysis, the lognormal distribution is often used to model times to repair a maintainable system.
- * In wireless communication, "the local-mean power expressed in logarithmic values, such as dB or neper, has a normal distribution." Also, the random obstruction of radio signals due to large buildings and hills, called shadowing, is often modeled as a lognormal distribution.
- * Particle size distributions produced by comminution with random impacts, such as in ball milling.
- * The file size distribution of publicly available audio and video data files follows a log-normal distribution over five orders of magnitude.
- * In computer networks and Internet traffic analysis, lognormal is shown as a good statistical model to represent the amount of traffic per unit time. This has been shown by applying a robust statistical approach on a large groups of real Interent traces. In this context, the log-normal distribution has shown a good performance in two main use cases: predicting the proportion of time traffic will exceed a given level i.e. link dimensioning based on bandwidth provisioning and predicting 95th percentile pricing.