# Monotone likelihood ratio

Monotone likelihood ratio
A monotonic likelihood ratio in distributions f(x) and g(x)

The ratio of the density functions above is increasing in the parameter x, so f(x)/g(x) satisfies the monotone likelihood ratio property.

In statistics, the monotone likelihood ratio property is a property of the ratio of two probability density functions (PDFs). Formally, distributions ƒ(x) and g(x) bear the property if

for any x1 > x0,   $\frac{f(x_1)}{g(x_1)} \geq \frac{f(x_0)}{g(x_0)}$

that is, if the ratio is nondecreasing in the argument x.

If the functions are first-differentiable, the property may sometimes be stated

$\frac{\partial}{\partial x} \left( \frac{f(x)}{g(x)} \right) \geq 0$

For two distributions that satisfy the definition with respect to some argument x, we say they "have the MLRP in x." For a family of distributions that all satisfy the definition with respect to some statistic T(X), we say they "have the MLR in T(X)."

## Intuition

The MLRP is used to represent a data-generating process that enjoys a straightforward relationship between the magnitude of some observed variable and the distribution it draws from. If f(x) satisfies the MLRP with respect to g(x), the higher the observed value x, the more likely it was drawn from distribution f rather than g. As usual for monotonic relationships, the likelihood ratio's monotonicity comes in handy in statistics, particularly when using maximum-likelihood estimation. Also, distribution families with MLR have a number of well-behaved stochastic properties, such as first-order stochastic dominance and increasing hazard ratios. Unfortunately, as is also usual, the strength of this assumption comes at the price of realism. Many processes in the world do not exhibit a monotonic correspondence between input and output.

### Example: Working hard or slacking off

Suppose you are working on a project, and you can either work hard or slack off. Call your choice of effort e and the quality of the resulting project q. If the MLRP holds for the distribution of q conditional on your effort e, the higher the quality the more likely you worked hard. Conversely, the lower the quality the more likely you slacked off.

1. Choose effort $e \in \{H,L\}$ where H means high, L means low
2. Observe q drawn from f(q | e). By Bayes' law with a uniform prior,
$Pr[e=H|q]=\frac{f(q|H)}{f(q|H)+f(q|L)}$
3. Suppose f(q | e) satisfies the MLRP. Rearranging, the probability the worker worked hard is
$\frac{1}{1+f(q|L)/f(q|H)}$
which, thanks to the MLRP, is monotonically increasing in q. Hence if some employer is doing a "performance review" he can infer his employee's behavior from the merits of his work.

## Families of distributions satisfying MLR

Statistical models often assume that data are generated by a distribution from some family of distributions and seek to determine that distribution. This task is simplified if the family has the Monotone Likelihood Ratio Property (MLRP).

A family of density functions $\{ f_\theta (x)\}_{\theta\in \Theta}$ indexed by a parameter θ taking values in an ordered set Θ is said to have a monotone likelihood ratio (MLR) in the statistic T(X) if for any θ1 < θ2,

$\frac{f_{\theta_2}(X=x_1,x_2,x_3,\dots)}{f_{\theta_1}(X=x_1,x_2,x_3,\dots)}$  is a non-decreasing function of T(X).

Then we say the family of distributions "has MLR in T(X)".

### List of families

Family T(X)  in which fθ(X) has the MLR
Exponential[λ] $\sum x_i$ observations
Binomial[n,p] $\sum x_i$ observations
Poisson[λ] $\sum x_i$ observations
Normal[μ,σ] if σ known, $\sum x_i$ observations

### Hypothesis testing

If the family of random variables has the MLRP in T(X), a uniformly most powerful test can easily be determined for the hypotheses $H_0 : \theta \le \theta_0$ versus H1:θ > θ0.

### Example:Effort and output

Example: Let e be an input into a stochastic technology --- worker's effort, for instance --- and y its output, the likelihood of which is described by a probability density function f(y;e). Then the monotone likelihood ratio property (MLRP) of the family f is expressed as follows: for any e1,e2, the fact that e2 > e1 implies that the ratio f(y;e2) / f(y;e1) is increasing in y.

## Relation to other statistical properties

If a family of distributions fθ(x) has the monotone likelihood ratio property in T(X),

1. the family has monotone decreasing hazard rates in θ (but not necessarily in T(X))
2. the family exhibits the first-order (and hence second-order) stochastic dominance in x, and the best Bayesian update of θ is increasing in T(X).

But not conversely: neither monotone hazard rates nor stochastic dominance imply the MLRP.

### Proofs

Let distribution family fθ satisfy MLR in x, so that for θ1 > θ0 and x1 > x0:

$\frac{f_{\theta_1}(x_1)}{f_{\theta_0}(x_1)} \geq \frac{f_{\theta_1}(x_0)}{f_{\theta_0}(x_0)},$

or equivalently:

$f_{\theta_1}(x_1) f_{\theta_0}(x_0) \geq f_{\theta_1}(x_0) f_{\theta_0}(x_1). \,$

Integrating this epression twice, we obtain:

 1. To x1 with respect to x0 $\int_{\min_x \in X}^{x_1} f_{\theta_1}(x_1) f_{\theta_0}(x_0) \, dx_0$ $\geq \int_{\min_x \in X}^{x_1} f_{\theta_1}(x_0) f_{\theta_0}(x_1) \, dx_0$ integrate and rearrange to obtain $\frac{f_{\theta_1}}{f_{\theta_0}}(x) \geq \frac{F_{\theta_1}}{F_{\theta_0}}(x)$ 2. From x0 with respect to x1 $\int_{x_0}^{\max_x \in X} f_{\theta_1}(x_1) f_{\theta_0}(x_0) \, dx_1$ $\geq \int_{x_0}^{\max_x \in X} f_{\theta_1}(x_0) f_{\theta_0}(x_1) \, dx_1$ integrate and rearrange to obtain $\frac{1-F_{\theta_1}(x)}{1-F_{\theta_0}(x)} \geq \frac{f_{\theta_1}}{f_{\theta_0}}(x)$

#### First-order stochastic dominance

Combine the two inequalities above to get first-order dominance:

$F_{\theta_1}(x) \leq F_{\theta_0}(x) \ \forall x$

#### Monotone hazard rate

Use only the second inequality above to get a monotone hazard rate:

$\frac{f_{\theta_1}(x)}{1-F_{\theta_1}(x)} \leq \frac{f_{\theta_0}(x)}{1-F_{\theta_0}(x)} \ \forall x$

## Uses

### Economics

The MLR is an important condition on the type distribution of agents in mechanism design. Most solutions to mechanism design models assume a type distribution to satisfy the MLR to take advantage of a common solution method.

Wikimedia Foundation. 2010.

### Look at other dictionaries:

• Monotone likelihood ratio property — is a property of a family of probability distributions described by their probability density functions (PDFs). A family of density functions { f heta (x)} { hetain Theta} indexed by a parameter heta taking values in a set Theta is said to have… …   Wikipedia

• Maximum likelihood — In statistics, maximum likelihood estimation (MLE) is a method of estimating the parameters of a statistical model. When applied to a data set and given a statistical model, maximum likelihood estimation provides estimates for the model s… …   Wikipedia

• List of statistics topics — Please add any Wikipedia articles related to statistics that are not already on this list.The Related changes link in the margin of this page (below search) leads to a list of the most recent changes to the articles listed below. To see the most… …   Wikipedia

• List of mathematics articles (M) — NOTOC M M estimator M group M matrix M separation M set M. C. Escher s legacy M. Riesz extension theorem M/M/1 model Maass wave form Mac Lane s planarity criterion Macaulay brackets Macbeath surface MacCormack method Macdonald polynomial Machin… …   Wikipedia

• Theory of conjoint measurement — The theory of conjoint measurement (also known as conjoint measurement or additive conjoint measurement) is a general, formal theory of continuous quantity. It was independently discovered by the French economist Gerard Debreu (1960) and by the… …   Wikipedia

• MLR — abbr. Minimum Lending Rate monotone likelihood ratio …   Dictionary of English abbreviation

• Uniformly most powerful test — In statistical hypothesis testing, a uniformly most powerful (UMP) test is a hypothesis test which has the greatest power 1 eta among all possible tests of a given size α . For example, according to the Neyman Pearson lemma, the likelihood ratio …   Wikipedia

• Projet:Mathématiques/Liste des articles de mathématiques — Cette page n est plus mise à jour depuis l arrêt de DumZiBoT. Pour demander sa remise en service, faire une requête sur WP:RBOT Cette page recense les articles relatifs aux mathématiques, qui sont liés aux portails de mathématiques, géométrie ou… …   Wikipédia en Français

• Liste des articles de mathematiques — Projet:Mathématiques/Liste des articles de mathématiques Cette page recense les articles relatifs aux mathématiques, qui sont liés aux portails de mathématiques, géométrie ou probabilités et statistiques via l un des trois bandeaux suivants  …   Wikipédia en Français

• Exponential family — Not to be confused with the exponential distribution. Natural parameter links here. For the usage of this term in differential geometry, see differential geometry of curves. In probability and statistics, an exponential family is an important… …   Wikipedia