generalized linear models
DESCRIPTION
Generalized Linear models. GENERALIZED LINEAR MODELS. Overview. overview. general linear models. Actually, proc glm. overview. GENERALIZED LINEAR MODELS. The distribution of the observations can come from the exponential family of distributions. - PowerPoint PPT PresentationTRANSCRIPT
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
GENERALIZED LINEAR MODELS
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
GENERALIZED LINEAR MODELSOVERVIEW
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
OVERVIEW GENERAL LINEAR MODELS
0 1 1i i k ki iy x x 2~ . . . (0, )i i i d N
2var( )iy
Actually, proc glm
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
OVERVIEW GENERALIZED LINEAR MODELS
• The distribution of the observations can come from the exponential family of distributions.
• The variance of the response variable is a specified function of its mean.
• X is fit to a function of E(y) (called a link function) suggested by the distribution of the observations:
g(E(y)) = g() = X
0 1 1( ( )) Xi i k kig E y x x …
Link function
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
OVERVIEW LOGIT LINK FUNCTION FOR BINARY RESPONSE
Logit (pi)
Predictor
LogitTransform
Predictor
pi
logit( ) log1
pp
p
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
OVERVIEW LOG LINK FUNCTION FOR COUNT DATA
Count Log(count)
LogTransform
Predictor Predictor
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
OVERVIEW EXAMPLES OF GENERALIZED LINEAR MODELS
*Models often use the LOG link in practice.
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
POISSON REGRESSION
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
POISSON REGRESSION PROPERTIES AND EXAMPLES
• is one type of generalized linear model
• assumes that the response variable follows a Poisson distribution conditional on the values of the predictor variables
• can be used to model the number of occurrences of an event of interest or the rate of occurrence of an event of interest as a function of some predictor variables
• is most appropriate for rare events
Examples include • number of ear infections in
infants• number of equipment failures• colony counts for bacteria or
viruses• counts of a rare disease in a
population• number of fatal crashes at an
intersection• homicide rates in a given state• rate of insurance claims• number of infected areas per
unit volume of a tree• response rates to a marketing
campaign
• Response dist. should have small mean (<10 or even <5 and ideally ~1)
• If no, gamma and lognormal could be better choice
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
POISSON REGRESSION POISSON VERSUS NORMAL DISTRIBUTION
Poisson distribution• is skewed to the right for rare events• is for nonnegative integer values• has only one parameter (the mean)• has a variance that is equal to the mean
Normal distribution• is symmetric• can be for negative as well as positive real values• has two unrelated parameters (mean and variance)
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
POISSON REGRESSION MODEL
0 1 1 2 2log( ) ... k kX X X
0 1 1 2 2
0 1 1 2 2
( ... )k k
k k
X X X
XX X
e
e e e e
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
POISSON REGRESSION PARAMETER ESTIMATES
ˆe multiplicative effect on ̂
for a one-unit change in X.
1̂e 1.20, then a one-unit increase in X1 yields a 20% increase in the estimated mean.
0.80, then a one-unit increase in X2 yields a 20% decrease in the estimated mean.
Example 1, if
Example 2, if
2ˆe
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
POISSON REGRESSION ПРИМЕР: ДАННЫЕ
Gender
Number of Self-Diagnosed Ear Infections Age in Years
Frequent or Occasional Ocean Swimmer
Typical Swimming Location
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
POISSON REGRESSION CATEGORICAL
GenderFrequent or Occasional Ocean Swimmer
Typical Swimming Location
Occ
asio
nal
Fre
q
Bea
ch
no
nB
each
Mal
e
Fem
ale
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
POISSON REGRESSION INTERVAL
Age in Years
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
POISSON REGRESSION ПРИМЕР
proc genmod data=sasuser.earinfection; class Swimmer (param=ref ref='Freq') Location (param=ref ref='Beach') Gender (param=ref ref='Male'); model infections = swimmer location gender age age*age / dist=poisson link=log type3;run;
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
POISSON REGRESSION ПРИМЕР: PROC GENMOD OUTPUT
Scale = 1*
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
POISSON REGRESSION
• Poisson regression models assume the variance is equal to the mean.
• Count data often exhibit variability exceeding the mean.
• Overdispersion leads to underestimates of the standard errors of parameter estimates.
• Overdispersion results in overestimates of the test statistic and liberal p-values.
OVERDISPERSION
• Subject heterogeneity due to an under-specified model• Outliers in the data• Positive correlation between the responses in clustered data
WHAT TO DO• Use the negative binomial
distribution [NOW]• Apply a multiplicative adjustment
factor (PSCALE or DSCALE option in the MODEL statement) [HW]
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
NEGATIVE BINOMIAL REGRESSION
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
NEGATIVE BINOMIAL REGRESSION
DISTRIBUTION AND MODEL
The negative binomial distribution• is the distribution for count data that permits the variance to exceed
the mean• enables the model to have greater flexibility in modeling the
relationship between the mean and the variance of the response variable than the Poisson model
Natural LogNegative
Binomial
Count
Variance Function
Link Function
DistributionResponse Variable
2k
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
NEGATIVE BINOMIAL REGRESSION
DISPERSION PARAMETER K
• The dispersion parameter k is not allowed to vary over observations.
• The limiting case when the parameter k is equal to 0 corresponds to a Poisson regression model.
• When the parameter is greater than 0, overdispersion is evident and the standard errors will increase. The fitted values are similar, but the larger standard errors reflect the overdispersion uncaptured with the Poisson model.
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
NEGATIVE BINOMIAL REGRESSION
ПРИМЕР
proc genmod data=sasuser.earinfection; class Swimmer (param=ref ref='Freq') Location (param=ref ref='Beach') Gender (param=ref ref='Male'); model infections = swimmer location gender age age*age / dist=negbin link=log type3;run;
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
NEGATIVE BINOMIAL REGRESSION
ПРИМЕР: PROC GENMOD OUTPUT
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
POISSON REGRESSION FOR RATES
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
POISSON REGRESSION: RATES
RATES DATA: DEFINITION & EXAMPLES
• When events occur over time, space, or some other index of exposure, it is more relevant to model the rate at which they occur rather than the number of events.
• Rates provide the necessary standardization to make the outcomes comparable.
• You use the OFFSET= option in the MODEL statement in PROC GENMOD.
• How crime rates are related to the city’s unemployment rate
• How melanoma incidence rates are related to demographic variables
• How the rate of loan defaults is related to region of the country
• How response rates to marketing campaigns relate to known characteristics of the recipients
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
• Log(T) is called the offset variable that has a coefficient equal to 1.
• The offset variable makes the fitted rate proportional to the index of exposure.
• For example, using the log of the population as an offset variable is the same as modeling the mean number of events proportional to population size.
POISSON REGRESSION: RATES
RATES DATA: OFFSET
0 1 1log k kx xT
…
0 1 1log( ) log( ) k kT x x …
0 1 1( )* k kx xT e …
OFFSET = Variable
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
POISSON REGRESSION: RATES
SKIN CANCER IN TEXAS AND MINNESOTA
Incidence of nonmelanoma
skin cancer
City: Minneapolis-St. Paul Dallas-Fort Worth
Age_ 15-24Group: 25-34
35-44 45-54 55-64 65-74 75-84 85+
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
POISSON REGRESSION: RATES
ПРИМЕР
proc genmod data=sasuser.skin; class City (param=ref ref='MSP') Age (param=ref ref='85+'); model cases = city age / offset=log_pop dist=poisson link=log type3;run;
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
ZERO-INFLATED POISSON MODEL
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
ZIP PURPOSE
• In some settings, the incidence of zero counts will be much greater than expected for the Poisson distribution.
• Poisson regression models will exhibit overdispersion when they are fit to data with an excess number of zeros.
• Zero-inflated Poisson (ZIP) models might be a better fit to the data.
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
ZIP MODEL
• The population that can be modeled with the zero-inflated Poisson distribution is considered to consist of two types of responses.
• The first type gives Poisson distributed counts, which can produce the zero outcome or some other positive outcome.
• The second type always gives a zero count.
• Therefore, the relevant distribution is a mixture of a Poisson distribution and a distribution that is constant at zero.
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
ZIP COMPONENTS
( )i ih z
( )i ig x MODEL statement
ZEROMODEL statement
proc genmod data=sasuser.roots; class bap photoperiod; model roots = photoperiod | bap
/ dist=zip link=log type3; zeromodel photoperiod;run;
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
ZIP ПРИМЕР: ДАННЫЕ
photoperiod (hour)
concentration (M)
2.2 4.4 8.8 17.6
8 Number of roots
Number of roots
Number of roots
Number of roots
16 Number of roots
Number of roots
Number of roots
Number of roots
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
ZIP ПРИМЕР
16 h
ours
8 ho
urs
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
ZIP ПРИМЕР: РЕЗУЛЬТАТЫ
dist=zinb
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
GAMMA REGRESSION
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
GAMMA DISTRIBUTION
• is a skewed distribution for positive values• has a variance that is proportional to the squared mean• has lighter tails than a lognormal distribution
Var(y) [E(y)]2
gamma
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
DISTRIBUTIONS COMPARISON
Normal (truncated)constant*
Poisson E(Y)
Gamma (E(Y))2
Lognormal (E(Y))2
Distribution Variance
100x
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
GAMMA REGRESSION ПРИМЕР
proc univariate data=car; var price; histogram / gamma (alpha=est sigma=est theta=est color=blue w=2) vaxis=0 to 14 by 2 midpoints=8 to 50 by 2;run;
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
GAMMA REGRESSION REG AND GENMOD RESULTS: RESIDUAL
PROC REG
PROC GENMOD, link=log PROC GENMOD, link=identity
proc genmod data=car; model price = hwympg hwympg2 horsepower / dist=gamma link=log /*identity*/ obstats id=model;run;
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
SUMMARY
• Problem: • nonconstant variance
• Approaches: Transform the dependent variable Price (log). Fit a gamma regression model with the log link function. Fit a gamma regression model with the identity link
function.
PROBLEM for OLS
?
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
СТРАХОВАНИЕ CASE STUDY
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
GENMOD СТРАХОВАНИЕ
• Frequency - how often claims are made• Severity
• A typical way to model severity (claim amount) is by using a gamma distribution with a log link function
• Pure premium - it is the portion of the company’s expected cost that is “purely” attributed to loss• does not include the general expense of doing
business• Tweedie distribution
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved .
GLM СТРАХОВАНИЕ: FREQUENCY & PURE PREMIUM
• ZIP• Tweedie distribution –
• PROC SEVERITY SAS/ETS
Copy r igh t © 2013 , SAS Ins t i t u t e I nc . A l l r i gh t s res erved . sas.com
СПАСИБО!