Poisson regression

Regression analysis
Part of a series on Statistics

Models
Linear regression Simple regression Ordinary least squares Polynomial regression General linear model
Generalized linear model Discrete choice Logistic regression Multinomial logit Mixed logit Probit Multinomial probit Ordered logit Ordered probit Poisson
Multilevel model Fixed effects Random effects Mixed model
Nonlinear regression Nonparametric Semiparametric Robust Quantile Isotonic Principal components Least angle Local Segmented
Errors-in-variables
Estimation
Least squares Ordinary least squares Linear (math) Partial Total Generalized Weighted Non-linear Non-negative Iteratively reweighted Ridge regression
Least absolute deviations Bayesian Bayesian multivariate
Background
Regression model validation Mean and predicted response Errors and residuals Goodness of fit Studentized residual Gauss–Markov theorem
Statistics portal

In statistics, Poisson regression is a generalized linear model form of regression analysis used to model count data and contingency tables. Poisson regression assumes the response variable Y has a Poisson distribution, and assumes the logarithm of its expected value can be modeled by a linear combination of unknown parameters. A Poisson regression model is sometimes known as a log-linear model, especially when used to model contingency tables.

Negative binomial regression is a popular generalization of Poisson regression because it loosens the highly restrictive assumption that the variance is equal to the mean made by the Poisson model. The traditional negative binomial regression model, commonly known as NB2, is based on the Poisson-gamma mixture distribution. This model is popular because it models the Poisson heterogeneity with a gamma distribution.

Poisson regression models are generalized linear models with the logarithm as the (canonical) link function, and the Poisson distribution function as the assumed probability distribution of the response.

Regression models

If $\mathbf {x} \in \mathbb {R} ^{n}$ is a vector of independent variables, then the model takes the form

\log(\operatorname {E} (Y\mid \mathbf {x} ))=\alpha +\mathbf {\beta } '\mathbf {x} ,

where $\alpha \in \mathbb {R}$ and $\mathbf {\beta } \in \mathbb {R} ^{n}$ . Sometimes this is written more compactly as

\log(\operatorname {E} (Y\mid \mathbf {x} ))={\boldsymbol {\theta }}'\mathbf {x} ,\,

where x is now an (n + 1)-dimensional vector consisting of n independent variables concatenated to a vector of ones. Here θ is simply α concatenated to β.

Thus, when given a Poisson regression model θ and an input vector x, the predicted mean of the associated Poisson distribution is given by

\operatorname {E} (Y\mid \mathbf {x} )=e^{{\boldsymbol {\theta }}'\mathbf {x} }.\,

If Y_i are independent observations with corresponding values x_i of the predictor variables, then θ can be estimated by maximum likelihood. The maximum-likelihood estimates lack a closed-form expression and must be found by numerical methods. The probability surface for maximum-likelihood Poisson regression is always concave, making Newton–Raphson or other gradient-based methods appropriate estimation techniques.

Maximum likelihood-based parameter estimation

Given a set of parameters θ and an input vector x, the mean of the predicted Poisson distribution, as stated above, is given by

\lambda :=\operatorname {E} (Y\mid x)=e^{\theta 'x},\,

and thus, the Poisson distribution's probability mass function is given by

p(y\mid x;\theta )={\frac {\lambda ^{y}}{y!}}e^{-\lambda }={\frac {e^{y\theta 'x}e^{-e^{\theta 'x}}}{y!}}

Now suppose we are given a data set consisting of m vectors $x_{i}\in \mathbb {R} ^{n+1},\,i=1,\ldots ,m$ , along with a set of m values $y_{1},\ldots ,y_{m}\in \mathbb {R}$ . Then, for a given set of parameters θ, the probability of attaining this particular set of data is given by

p(y_{1},\ldots ,y_{m}\mid x_{1},\ldots ,x_{m};\theta )=\prod _{i=1}^{m}{\frac {e^{y_{i}\theta 'x_{i}}e^{-e^{\theta 'x_{i}}}}{y_{i}!}}.

By the method of maximum likelihood, we wish to find the set of parameters θ that makes this probability as large as possible. To do this, the equation is first rewritten as a likelihood function in terms of θ:

L(\theta \mid X,Y)=\prod _{i=1}^{m}{\frac {e^{y_{i}\theta 'x_{i}}e^{-e^{\theta 'x_{i}}}}{y_{i}!}}.

Note that the expression on the right hand side has not actually changed. A formula in this form is typically difficult to work with; instead, one uses the log-likelihood:

\ell (\theta \mid X,Y)=\log L(\theta \mid X,Y)=\sum _{i=1}^{m}\left(y_{i}\theta 'x_{i}-e^{\theta 'x_{i}}-\log(y_{i}!)\right).

Notice that the parameters θ only appear in the first two terms of each term in the summation. Therefore, given that we are only interested in finding the best value for θ we may drop the y_i! and simply write

\ell (\theta \mid X,Y)=\sum _{i=1}^{m}\left(y_{i}\theta 'x_{i}-e^{\theta 'x_{i}}\right).

To find a maximum, we need to solve an equation ${\frac {\partial \ell (\theta \mid X,Y)}{\partial \theta }}=0$ which has no closed-form solution. However, the negative log-likelihood, $-\ell (\theta \mid X,Y)$ , is a convex function, and so standard convex optimization techniques such as gradient descent can be applied to find the optimal value of θ.

Poisson regression in practice

Poisson regression may be appropriate when the dependent variable is a count, for instance of events such as the arrival of a telephone call at a call centre.^[1] The events must be independent in the sense that the arrival of one call will not make another more or less likely, but the probability per unit time of events is understood to be related to covariates such as time of day.

"Exposure" and offset

Poisson regression may also be appropriate for rate data, where the rate is a count of events divided by some measure of that unit's exposure (a particular unit of observation). For example, biologists may count the number of tree species in a forest: events would be tree observations, exposure would be unit area, and rate would be the number of species per unit area. Demographers may model death rates in geographic areas as the count of deaths divided by person−years. More generally, event rates can be calculated as events per unit time, which allows the observation window to vary for each unit. In these examples, exposure is respectively unit area, person−years and unit time. In Poisson regression this is handled as an offset, where the exposure variable enters on the right-hand side of the equation, but with a parameter estimate (for log(exposure)) constrained to 1.

\log {(\operatorname {E} (Y\mid x))}=\log {({\text{exposure}})}+\theta 'x

which implies

\log {(\operatorname {E} (Y\mid x))}-\log {({\text{exposure}})}=\log {\left({\frac {\operatorname {E} (Y\mid x)}{\text{exposure}}}\right)}=\theta 'x

Offset in the case of a GLM in R can be achieved using the offset() function:

glm(y ~ offset(log(exposure)) + x, family=poisson(link=log) )

Overdispersion and zero inflation

A characteristic of the Poisson distribution is that its mean is equal to its variance. In certain circumstances, it will be found that the observed variance is greater than the mean; this is known as overdispersion and indicates that the model is not appropriate. A common reason is the omission of relevant explanatory variables, or dependent observations. Under some circumstances, the problem of overdispersion can be solved by using quasi-likelihood estimation or a negative binomial distribution instead.^[2]^[3]

Ver Hoef and Boveng described the difference between quasi-Poisson (also called overdispersion with quasi-likelihood) and negative binomial (equivalent to gamma-Poisson) as follows: If E(Y) = μ, the quasi-Poisson model assumes var(Y) = θμ while the gamma-Poisson assumes var(Y) = μ(1 + κμ), where θ is the quasi-Poisson overdispersion parameter, and κ is the shape parameter of the negative binomial distribution. For both models, parameters are estimated using Iteratively reweighted least squares. For quasi-Poisson, the weights are μ/θ. For negative binomial, the weights are μ/(1 + κμ). With large μ and substantial extra-Poisson variation, the negative binomial weights are capped at 1/κ. Ver Hoef and Boveng discussed an example where they selected between the two by plotting mean squared residuals vs. the mean.^[4]

Another common problem with Poisson regression is excess zeros: if there are two processes at work, one determining whether there are zero events or any events, and a Poisson process determining how many events there are, there will be more zeros than a Poisson regression would predict. An example would be the distribution of cigarettes smoked in an hour by members of a group where some individuals are non-smokers.

Other generalized linear models such as the negative binomial model or zero-inflated model may function better in these cases.

Use in survival analysis

Poisson regression creates proportional hazards models, one class of survival analysis: see proportional hazards models for descriptions of Cox models.

Extensions

Regularized Poisson regression

When estimating the parameters for Poisson regression, one typically tries to find values for θ that maximize the likelihood of an expression of the form

\sum _{i=1}^{m}\log(p(y_{i};e^{\theta 'x_{i}})),

where m is the number of examples in the data set, and $p(y_{i};e^{\theta 'x_{i}})$ is the probability mass function of the Poisson distribution with the mean set to $e^{\theta 'x_{i}}$ . Regularization can be added to this optimization problem by instead maximizing

\sum _{i=1}^{m}\log(p(y_{i};e^{\theta 'x_{i}}))-\lambda \left\|\theta \right\|_{2}^{2},

for some positive constant $\lambda$ . This technique, similar to ridge regression, can reduce overfitting.

References

↑ Greene, William H. (2003). Econometric Analysis (Fifth ed.). Prentice-Hall. pp. 740–752. ISBN 0130661899.
↑ Paternoster R, Brame R (1997). "Multiple routes to delinquency? A test of developmental and general theories of crime". Criminology. 35: 45–84. doi:10.1111/j.1745-9125.1997.tb00870.x.
↑ Berk R, MacDonald J (2008). "Overdispersion and Poisson regression" (PDF). Journal of Quantitative Criminology. 24 (3): 269–284. doi:10.1007/s10940-008-9048-4.
↑ Ver Hoef, JAY M.; Boveng, Peter L. (2007-01-01). "Quasi-Poisson vs. Negative Binomial Regression: How should we model overdispersed count data?". Ecology. 88 (11): 2766–2772. Retrieved 2016-09-01.

Cameron, A. C.; Trivedi, P. K. (1998). Regression analysis of count data. Cambridge University Press. ISBN 0-521-63201-3.
Christensen, Ronald (1997). Log-linear models and logistic regression. Springer Texts in Statistics (Second ed.). New York: Springer-Verlag. ISBN 0-387-98247-7. MR 1633357.
Gouriéroux, Christian (2000). "The Econometrics of Discrete Positive Variables: the Poisson Model". Econometrics of Qualitative Dependent Variables. New York: Cambridge University Press. pp. 270–83. ISBN 0-521-58985-1.
Greene, William H. (2008). "Models for Event Counts and Duration". Econometric Analysis (8th ed.). Upper Saddle River: Prentice Hall. pp. 906–944. ISBN 978-0-13-600383-0.
Hilbe, J. M. (2007). Negative Binomial Regression. Cambridge University Press. ISBN 978-0-521-85772-7.
Jones, Andrew M.; et al. (2013). "Models for count data". Applied Health Economics. London: Routledge. pp. 295–341. ISBN 978-0-415-67682-3.

Statistics

Descriptive statistics

Continuous data

Center	Mean arithmetic geometric harmonic Median Mode

Dispersion	Variance Standard deviation Coefficient of variation Percentile Range Interquartile range

Shape	Moments Skewness Kurtosis L-moments

Count data

Index of dispersion

Summary tables

Dependence

Graphics

Data collection

Study design	Population Statistic Effect size Statistical power Sample size determination Missing data

Survey methodology	Sampling Standard error stratified cluster Opinion poll Questionnaire

Controlled experiments	Design control optimal Controlled trial Randomized Random assignment Replication Blocking Interaction Factorial experiment

Uncontrolled studies	Observational study Natural experiment Quasi-experiment

Statistical inference

Statistical theory

Frequentist inference

Point estimation	Estimating equations Maximum likelihood Method of moments M-estimator Minimum distance Unbiased estimators Mean-unbiased minimum-variance Rao–Blackwellization Lehmann–Scheffé theorem Median unbiased Plug-in

Interval estimation	Confidence interval Pivot Likelihood interval Prediction interval Tolerance interval Resampling Bootstrap Jackknife

Testing hypotheses	1- & 2-tails Power Uniformly most powerful test Permutation test Randomization test Multiple comparisons

Parametric tests	Likelihood-ratio Wald Score

Specific tests

Z (normal) Student's t-test F

Goodness of fit	Chi-squared Kolmogorov–Smirnov Anderson–Darling Normality (Shapiro–Wilk) Likelihood-ratio test Model selection Cross validation AIC BIC

Rank statistics	Sign Sample median Signed rank (Wilcoxon) Hodges–Lehmann estimator Rank sum (Mann–Whitney) Nonparametric anova 1-way (Kruskal–Wallis) 2-way (Friedman) Ordered alternative (Jonckheere–Terpstra)

Bayesian inference

Correlation	Pearson product–moment Partial correlation Confounding variable Coefficient of determination

Regression analysis	Errors and residuals Regression model validation Mixed effects models Simultaneous equations models Multivariate adaptive regression splines (MARS)

Linear regression	Simple linear regression Ordinary least squares General linear model Bayesian regression

Non-standard predictors	Nonlinear regression Nonparametric Semiparametric Isotonic Robust Heteroscedasticity Homoscedasticity

Generalized linear model	Exponential families Logistic (Bernoulli) / Binomial / Poisson regressions

Partition of variance	Analysis of variance (ANOVA, anova) Analysis of covariance Multivariate ANOVA Degrees of freedom

Categorical / Multivariate / Time-series / Survival analysis

Categorical

Multivariate

Time-series

General	Decomposition Trend Stationarity Seasonal adjustment Exponential smoothing Cointegration Structural break Granger causality

Specific tests	Dickey–Fuller Johansen Q-statistic (Ljung–Box) Durbin–Watson Breusch–Godfrey

Time domain	Autocorrelation (ACF) partial (PACF) Cross-correlation (XCF) ARMA model ARIMA model (Box–Jenkins) Autoregressive conditional heteroskedasticity (ARCH) Vector autoregression (VAR)

Frequency domain	Spectral density estimation Fourier analysis Wavelet

Survival

Survival function	Kaplan–Meier estimator (product limit) Proportional hazards models Accelerated failure time (AFT) model First hitting time

Hazard function	Nelson–Aalen estimator

Test	Log-rank test

Applications

Biostatistics	Bioinformatics Clinical trials / studies Epidemiology Medical statistics

Engineering statistics	Chemometrics Methods engineering Probabilistic design Process / quality control Reliability System identification

Social statistics	Actuarial science Census Crime statistics Demography Econometrics National accounts Official statistics Population statistics Psychometrics

Spatial statistics	Cartography Environmental statistics Geographic information system Geostatistics Kriging

Category
Portal
Commons
WikiProject

Least squares and regression analysis

Computational statistics

Correlation and dependence

Regression analysis

Regression as a
statistical model

Linear regression	Simple linear regression Ordinary least squares Generalized least squares Weighted least squares General linear model

Predictor structure	Polynomial regression Growth curve (statistics) Segmented regression Local regression

Non-standard	Nonlinear regression Nonparametric Semiparametric Robust Quantile Isotonic

Non-normal errors	Generalized linear model Binomial Poisson Logistic

Decomposition of variance

Model exploration

Background

Design of experiments

Numerical approximation