 StatLect

# Exponential distribution - Maximum Likelihood Estimation

In this lecture, we derive the maximum likelihood estimator of the parameter of an exponential distribution.

The theory needed to understand the proofs is explained in the introduction to maximum likelihood estimation (MLE). ## Assumptions

We observe the first terms of an IID sequence of random variables having an exponential distribution.

A generic term of the sequence has probability density function where:

• is the support of the distribution;

• the rate parameter is the parameter that needs to be estimated. ## The likelihood function

The likelihood function is Proof

Since the terms of the sequence are independent, the likelihood function is equal to the product of their densities: Because the observed values can only belong to the support of the distribution, we can write ## The log-likelihood function

The log-likelihood function is Proof

This is obtained by taking the natural logarithm of the likelihood function: ## The maximum likelihood estimator

The maximum likelihood estimator of is Proof

The estimator is obtained as a solution of the maximization problem The first order condition for a maximum is The derivative of the log-likelihood is By setting it equal to zero, we obtain Note that the division by is legitimate because exponentially distributed random variables can take on only positive values (and strictly so with probability 1).

Therefore, the estimator is just the reciprocal of the sample mean ## Asymptotic variance

The estimator is asymptotically normal with asymptotic mean equal to and asymptotic variance equal to Proof

The score is The Hessian is By the information equality, we have that Finally, the asymptotic variance is This means that the distribution of the maximum likelihood estimator can be approximated by a normal distribution with mean and variance .

## Other examples

StatLect has several pages like this one. Learn how to derive the MLEs of the parameters of the following distributions and models.

TypeSolution
Normal distributionUnivariate distributionAnalytical
Poisson distributionUnivariate distributionAnalytical
T distributionUnivariate distributionNumerical
Multivariate normal distributionMultivariate distributionAnalytical
Normal linear regression modelRegression modelAnalytical
Logistic classification modelClassification modelNumerical
Probit classification modelClassification modelNumerical