Package 'SemiPar'

Title: Semiparametic Regression
Description: Functions for semiparametric regression analysis, to complement the book: Ruppert, D., Wand, M.P. and Carroll, R.J. (2003). Semiparametric Regression. Cambridge University Press.
Authors: Matt Wand <[email protected]>
Maintainer: Billy Aung Myint <[email protected]>
License: GPL (>= 2)
Version: 1.0-4.2
Built: 2024-12-09 06:34:55 UTC
Source: CRAN

Help Index


Age/income data

Description

The age.income data frame has 205 pairs observations on Canadian workers from a 1971 Canadian Census Public Use Tape (Ullah, 1985).

Usage

data(age.income)

Format

This data frame contains the following columns:

age

age in years.

log.income

logarithm of income.

Source

Ullah, A. (1985). Specification analysis of econometric models. Journal of Quantitative Economics, 2, 187-209.

References

Ruppert, D., Wand, M.P. and Carroll, R.J. (2003)
Semiparametric Regression Cambridge University Press.
http://stat.tamu.edu/~carroll/semiregbook/

Examples

library(SemiPar)
data(age.income)
attach(age.income)
plot(age,log.income)

Bronchopulmonary dysplasia data

Description

The bpd data frame has data on 223 human babies.

Usage

data(bpd)

Format

This data frame contains the following columns:

birthweight

birthweight of baby (grammes).

BPD

an indicator of presence of bronchopulmonary dysplasia (BPD): 0=absent, 1=present.

Source

Pagano, M. and Gauvreau, K. (1993). Principles of Biostatistics. Duxbury Press.

References

Ruppert, D., Wand, M.P. and Carroll, R.J. (2003)
Semiparametric Regression Cambridge University Press.
http://stat.tamu.edu/~carroll/semiregbook/

Examples

library(SemiPar)
data(bpd)
attach(bpd)
plot(birthweight,BPD)
boxplot(split(birthweight,BPD),col="green")

California air polution data

Description

The calif.air.poll data frame has 345 sets of observations ozone level and meteorological variables in Upland, California, U.S.A., in 1976.

Usage

data(calif.air.poll)

Format

This data frame contains the following columns:

ozone.level

Ozone concentration (ppm) at Sandburg Air Force Base.

daggett.pressure.gradient

Pressure gradient at Daggett, California.

inversion.base.height

Inversion base height, feet.

inversion.base.temp

Inversion base temperature, degrees Fahrenheit.

Source

Brieman, L. and Friedman, J. (1985). Estimating optimal transformations for multiple regression and correlation (with discussion). Journal of the American Statistical Association, 80, 580–619.

Examples

library(SemiPar)
data(calif.air.poll)
pairs(calif.air.poll)

Copper data

Description

The copper data frame has 442 sets of observations from a simulation based on a stockpile of mined material in the former Soviet Union. Boreholes have been drilled into the dump. The drill core is cut every 5 metres and assayed for copper and cobalt content in percentage by weight.

Usage

data(copper)

Format

This data frame contains the following columns:

sample.num

sample number.

id

sample identification number.

zone

zone code.

xcoord

x co-ordinate.

ycoord

y co-ordinate.

zcoord

z co-ordinate.

grade

grade measurement.

core.length

percentage of copper.

Source

Clark, I. and Harper, W.V. (2000). Practical Geostatistics 2000. Columbus, Ohio: Ecosse North America Llc.

Examples

library(SemiPar)
data(copper)
pairs(copper[,4:7])

Electricity usage and temperature data

Description

The elec.temp data frame has 55 observations on monthly electricity usage and average temperature for a house in Westchester County, New York, USA.

Usage

data(elec.temp)

Format

This data frame contains the following columns:

usage

monthly electricity usage (kilowatt-hours) from a house in Westchester County, New York, USA.

temp

average temperature (degrees Fahrenheit) for the corresponding month.

Source

Chatterjee, S., Handcock, M. and Simonoff, J.S. (1995). A Casebook for a First Course in Statistics and Data Analysis, New York: John Wiley & Sons.

References

Ruppert, D., Wand, M.P. and Carroll, R.J. (2003)
Semiparametric Regression Cambridge University Press.
http://stat.tamu.edu/~carroll/semiregbook/

Examples

library(SemiPar)
data(elec.temp)
attach(elec.temp)
plot(usage,temp)

Ethanol data

Description

The ethanol data frame contains 88 sets of measurements for variables from an experiment in which ethanol was burned in a single cylinder automobile test engine.

Usage

data(ethanol)

Format

This data frame contains the following columns:

NOx

the concentration of nitric oxide (NO) and nitrogen dioxide (NO2) in engine exhaust, normalized by the work done by the engine.

C

the compression ratio of the engine

E

the equivalence ratio at which the engine was run – a measure of the richness of the air/ethanol mix.

Source

Brinkman, N.D. (1981). Ethanol fuel – a single-cylinder engine study of efficiency and exhaust emissions. SAE transactions Vol. 90, No 810345, 1410–1424.

References

Ruppert, D., Wand, M.P. and Carroll, R.J. (2003)
Semiparametric Regression Cambridge University Press.
http://stat.tamu.edu/~carroll/semiregbook/

Examples

library(SemiPar)
data(ethanol)
pairs(ethanol)

Fitted values for semiparametric regression.

Description

Extracts fitted values from a semiparametric regression fit object.

Usage

## S3 method for class 'spm'
fitted(object,...)

Arguments

object

a fitted spm object as produced by spm().

...

other possible arguments.

Details

Extracts fitted from a semiparametric regression fit object. The fitted are defined to be the set of values obtained when the predictor variable data are substituted into the fitted regression model.

Value

The vector of fitted.

Author(s)

M.P. Wand [email protected] (other contributors listed in SemiPar Users' Manual).

References

Ruppert, D., Wand, M.P. and Carroll, R.J. (2003)
Semiparametric Regression Cambridge University Press.
http://stat.tamu.edu/~carroll/semiregbook/

Ganguli, B. and Wand, M.P. (2005)
SemiPar 1.0 Users' Manual.
http://matt-wand.utsacademics.info/SPmanu.pdf

See Also

spm plot.spm lines.spm predict.spm summary.spm residuals.spm

Examples

library(SemiPar)
data(fossil)
attach(fossil)
fit <- spm(strontium.ratio~f(age))
plot(fit)
points(age,fitted(fit),col="red")

Fossil data

Description

The fossil data frame has 106 observations on fossil shells.

Usage

data(fossil)

Format

This data frame contains the following columns:

age

age in millions of years

strontium.ratio

ratios of strontium isotopes

Source

Bralower, T.J., Fullagar, P.D., Paull, C.K., Dwyer, G.S. and Leckie, R.M. (1997). Mid-cretaceous strontium-isotope stratigraphy of deep-sea sections. Geological Society of America Bulletin, 109, 1421-1442.

References

Ruppert, D., Wand, M.P. and Carroll, R.J. (2003)
Semiparametric Regression Cambridge University Press.
http://stat.tamu.edu/~carroll/semiregbook/

Examples

library(SemiPar)
data(fossil)
attach(fossil)
plot(age,strontium.ratio)

Automobile data from consumer reports

Description

The fuel.frame data frame contains data on 5 variables (columns) for 117 cars (rows).

Usage

data(fuel.frame)

Format

This data frame contains the following columns:

car.name

character variable giving the name (make) of the car

Weight

the weight of the car in pounds.

Disp.

the engine displacement in litres.

Mileage

gas mileage in miles/gallon.

Fuel

a derived variable concerning fuel efficiency.

Type

a factor giving the general type of car. The levels are: Small ,Sporty , Compact , Medium , Large , Van.

Source

Consumer Reports, April, 1990, pp. 235-288.

References

Chambers, J.M. and Hastie, T.J. (eds.) (1992)
Statistical Models in S.
Wadsworth and Brooks, Pacific Grove, California.

Examples

library(SemiPar)
data(fuel.frame)
pairs(fuel.frame)
par(mfrow=c(2,2))
fuel.fit <- lm(Fuel ~ Weight + Disp.,fuel.frame)
plot(fuel.fit,ask=FALSE)
par(mfrow=c(1,1))

Janka hardness data

Description

The janka data frame has 36 observations on Australian timber samples.

Usage

data(janka)

Format

This data frame contains the following columns:

dens

a measure of density of the timber.

hardness

the Janka hardness (structural property) of the timber.

Source

Williams, E.J. (1959) Regression Analysis, New York: John Wiley & Sons.

References

Ruppert, D., Wand, M.P. and Carroll, R.J. (2003)
Semiparametric Regression Cambridge University Press.
http://stat.tamu.edu/~carroll/semiregbook/

Examples

library(SemiPar)
data(janka)
attach(janka)
plot(dens,hardness)

LIDAR data

Description

The lidar data frame has 221 observations from a light detection and ranging (LIDAR) experiment.

Usage

data(lidar)

Format

This data frame contains the following columns:

range

distance travelled before the light is reflected back to its source.

logratio

logarithm of the ratio of received light from two laser sources.

Source

Sigrist, M. (Ed.) (1994). Air Monitoring by Spectroscopic Techniques (Chemical Analysis Series, vol. 197). New York: Wiley.

References

Ruppert, D., Wand, M.P. and Carroll, R.J. (2003)
Semiparametric Regression Cambridge University Press.
http://stat.tamu.edu/~carroll/semiregbook/

Examples

library(SemiPar)
data(lidar)
attach(lidar)
plot(range,logratio)

Add a curves to an existing plot.

Description

Takes a fitted spm object produced by spm() and adds a curve. The function is only appropriate in the case of a single predictor.

Usage

## S3 method for class 'spm'
lines(x,...)

Arguments

x

a fitted spm object as produced by spm().

...

other graphics parameters described in Appendix B of the SemiPar Users' Manual http://matt-wand.utsacademics.info/SPmanu.pdf

Details

Takes a fitted spm object produced by spm() and adds a curve. The function is only appropriate in the case of a single predictor.

Value

The function adds a curve to a plot.

Author(s)

M.P. Wand [email protected] (other contributors listed in SemiPar Users' Manual).

References

Ruppert, D., Wand, M.P. and Carroll, R.J. (2003)
Semiparametric Regression Cambridge University Press.
http://stat.tamu.edu/~carroll/semiregbook/

Ganguli, B. and Wand, M.P. (2005)
SemiPar 1.0 Users' Manual.
http://matt-wand.utsacademics.info/SPmanu.pdf

See Also

spm plot.spm predict.spm summary.spm residuals.spm fitted.spm

Examples

library(SemiPar)
data(fossil)
attach(fossil)
fit <- spm(strontium.ratio~f(age))
plot(fossil,type="n")
lines(fit)
points(fossil)

# Now do several customisations

op <- par(bg="white")
par(bg="honeydew")
plot(fossil,type="n")
lines(fit,col="green",lwd=5,shade.col="mediumpurple1")   
points(fossil,col="orange",pch=16)
par(op)

Milan mortality data

Description

The milan.mort data frame has data on 3652 consecutive days (10 consecutive years: 1st January, 1980 to 30th December, 1989) for the city of Milan, Italy.

Usage

data(milan.mort)

Format

This data frame contains the following columns:

day.num

number of days since 31st December, 1979

day.of.week

1=Monday,2=Tuesday,3=Wednesday,4=Thursday, 5=Friday,6=Saturday,7=Sunday.

holiday

indicator of public holiday: 1=public holiday, 0=otherwise.

mean.temp

mean daily temperature in degrees Celcius.

rel.humid

relative humidity.

tot.mort

total number of deaths.

resp.mort

total number of respiratory deaths.

SO2

measure of sulphur dioxide level in ambient air.

TSP

total suspended particles in ambient air.

Source

Vigotti, M.A., Rossi, G., Bisanti, L., Zanobetti, A. and Schwartz, J. (1996). Short term effect of urban air pollution on respiratory health in Milan, Italy, 1980-1989. Journal of Epidemiology and Community Health, 50, S71-S75.

References

Ruppert, D., Wand, M.P. and Carroll, R.J. (2003)
Semiparametric Regression Cambridge University Press.
http://stat.tamu.edu/~carroll/semiregbook/

Examples

library(SemiPar)
data(milan.mort)
pairs(milan.mort,pch=".")

Mercury biomonintoring data

Description

The monitor.mercury data frame has 22 observations from sampling locations around a solid waste incinerator in Warren County, New Jersey, USA

Usage

data(monitor.mercury)

Format

This data frame contains the following columns:

UTM.North

longitude of sampling location.

UTM.East

latitude of sampling location.

mercury.concentration

mercury concentration in dry sphagnum moss grown at the sampling location.

Source

Opsomer, J.D., Agras, J., Carpi, A. and Rodrigues, G. (1995), An application of locally weighted regression to airborne mercury deposition around an incinerator site, Environmetrics, 6, 205-221.

References

Ruppert, D., Wand, M.P. and Carroll, R.J. (2003)
Semiparametric Regression Cambridge University Press.
http//stat.tamu.edu/~carroll/semiregbook/

Examples

library(SemiPar)
data(monitor.mercury)
pairs(monitor.mercury)

Onions data

Description

The onions data frame contains 84 sets of observations from an experiment involving the production of white Spanish onions in two South Australian locations.

Usage

data(onions)

Format

This data frame contains the following columns:

dens

areal density of plants (plants per square metre)

yield

onion yield (grammes per plant).

location

indicator of location: 0=Purnong Landing, 1=Virginia.

Source

Ratkowsky, D. A. (1983). Nonlinear Regression Modeling: A Unified Practical Approach. New York: Marcel Dekker.

References

Ruppert, D., Wand, M.P. and Carroll, R.J. (2003)
Semiparametric Regression Cambridge University Press.
http://stat.tamu.edu/~carroll/semiregbook/

Examples

library(SemiPar)
data(onions)
attach(onions)
points.cols <- c("red","blue")
plot(dens,yield,col=points.cols[location+1],pch=16)
legend(100,250,c("Purnong Landing","Virginia"),col=points.cols,pch=rep(16,2))

Pig weight data

Description

The pig.weights data frame has 9 repeated weight measures on 48 pigs.

Usage

data(pig.weights)

Format

This data frame contains the following columns:

id.num

identification number of pig.

num.weeks

number of weeks since measurements commenced.

weight

bodyweight of pig "id.num" after "num.weeks" weeks.

Source

Diggle, P.J., Heagerty, P., Liang, K.-Y. and Zeger, S.L. (2002). Analysis of Longitudinal Data, Second Edition, Oxord: Oxford University Press.

References

Ruppert, D., Wand, M.P. and Carroll, R.J. (2003)
Semiparametric Regression Cambridge University Press.
http://stat.tamu.edu/~carroll/semiregbook/

Examples

library(SemiPar)
data(pig.weights)
library(lattice)
xyplot(weight~num.weeks,data=pig.weights,groups=id.num,type="b")

Semiparametric regression plotting

Description

Takes a fitted spm object produced by spm() and plots the component smooth functions that make it up, on the scale of the linear predictor.

Usage

## S3 method for class 'spm'
plot(x,...)

Arguments

x

a fitted spm object as produced by spm().

...

other graphics parameters described in Appendix B of the SemiPar Users' Manual http://matt-wand.utsacademics.info/SPmanu.pdf

Details

Produces plots with each panel corresponding to a component of the semiparametric regression model.

Value

The function generates plots.

Author(s)

M.P. Wand [email protected] (other contributors listed in SemiPar Users' Manual).

References

Ruppert, D., Wand, M.P. and Carroll, R.J. (2003)
Semiparametric Regression Cambridge University Press.
http://stat.tamu.edu/~carroll/semiregbook/

Ganguli, B. and Wand, M.P. (2005)
SemiPar 1.0 Users' Manual.
http://matt-wand.utsacademics.info/SPmanu.pdf

See Also

spm lines.spm predict.spm summary.spm

Examples

library(SemiPar)
data(fossil)
attach(fossil)
fit <- spm(strontium.ratio~f(age))
plot(fit)

# Now do several customisations

op <- par(bg="white")
par(bg="honeydew")
plot(fit,ylim=range(strontium.ratio),col="green",
     lwd=5,shade.col="mediumpurple1",rug.col="blue")   
points(age,strontium.ratio,col="orange",pch=16)
par(op)

Semiparametric regression prediction.

Description

Takes a fitted spm object produced by spm() and obtains predictions at new data values.

Usage

## S3 method for class 'spm'
predict(object,newdata,se,...)

Arguments

object

a fitted spm object as produced by spm().

newdata

a data frame containing the values of the predictors at which predictions are required. The columns should have the same name as the predictors.

se

when this is TRUE standard error estimates are returned for each prediction. The default is FALSE.

...

other arguments.

Details

Takes a fitted spm object produced by spm() and obtains predictions at new data values as specified by the ‘newdata’ argument. If ‘se=TRUE’ then standard error estimates are also obtained.

Value

If se=FALSE then a vector of predictions at ‘newdata’ is returned. If se=TRUE then a list with components named ‘fit’ and ‘se’ is returned. The ‘fit’ component contains the predictions. The ‘se’ component contains standard error estimates.

Author(s)

M.P. Wand [email protected] (other contributors listed in SemiPar Users' Manual).

References

Ruppert, D., Wand, M.P. and Carroll, R.J. (2003)
Semiparametric Regression Cambridge University Press.
http://stat.tamu.edu/~carroll/semiregbook/

Ganguli, B. and Wand, M.P. (2005)
SemiPar 1.0 Users' Manual.
http://matt-wand.utsacademics.info/SPmanu.pdf

See Also

spm lines.spm plot.spm summary.spm

Examples

library(SemiPar)
data(fossil)
attach(fossil)
fit <- spm(strontium.ratio~f(age))
newdata.age <- data.frame(age=c(90,100,110,120,130))
preds <-  predict(fit,newdata=newdata.age,se=TRUE)
print(preds)

plot(fit,xlim=c(90,130))
points(unlist(newdata.age),preds$fit,col="red")
points(unlist(newdata.age),preds$fit+2*preds$se,col="blue")
points(unlist(newdata.age),preds$fit-2*preds$se,col="green")

Prints semiparametric regression fit object.

Description

Prints a brief description of a semiparametric regression fit object to the screen.

Usage

## S3 method for class 'spm'
print(x,...)

Arguments

x

a fitted spm object as produced by spm().

...

other possible arguments.

Details

Prints a brief description of a semiparametric regression fit object to the screen.

Value

The function prints to the screen.

Author(s)

M.P. Wand [email protected] (other contributors listed in SemiPar Users' Manual).

References

Ruppert, D., Wand, M.P. and Carroll, R.J. (2003)
Semiparametric Regression Cambridge University Press.
http://stat.tamu.edu/~carroll/semiregbook/

Ganguli, B. and Wand, M.P. (2005)
SemiPar 1.0 Users' Manual.
http://matt-wand.utsacademics.info/SPmanu.pdf

See Also

spm plot.spm lines.spm predict.spm summary.spm residuals.spm fitted.spm

Examples

library(SemiPar)
data(fossil)
attach(fossil)
fit <- spm(strontium.ratio~f(age))
print(fit)

Ragweed data

Description

The ragweed data frame has data on ragweed levels and meteorological variables for 335 days in Kalamazoo, Michigan, U.S.A.

Usage

data(ragweed)

Format

This data frame contains the following columns:

ragweed

ragweed level (grains per cubic metre).

year

one of 1991, 1992, 1993 or 1994.

day.in.seas

day number in the current ragweed pollen season.

temperature

temperature of following day (degrees Fahrenheit).

rain

indicator of significant rain the following day: 1=at least 3 hours of steady or brief but intense rain, 0=otherwise.

wind.speed

wind speed forecast for following day (knots).

Source

Stark, P. C., Ryan, L. M., McDonald, J. L. and Burge, H. A. (1997). Using meteorologic data to model and predict daily ragweed pollen levels. Aerobiologia, 13, 177-184.

References

Ruppert, D., Wand, M.P. and Carroll, R.J. (2003)
Semiparametric Regression Cambridge University Press.
http://stat.tamu.edu/~carroll/semiregbook/

Examples

library(SemiPar)
data(ragweed)
pairs(ragweed,pch=".")

Residuals for semiparametric regression.

Description

Extracts residuals from a semiparametric regression fit object.

Usage

## S3 method for class 'spm'
residuals(object,...)

Arguments

object

a fitted spm object as produced by spm().

...

other possible arguments.

Details

Extracts residuals from a semiparametric regression fit object. The residuals are defined to be the difference between the response variable and the fitted values.

Value

The vector of residuals.

Author(s)

M.P. Wand [email protected] (other contributors listed in SemiPar Users' Manual).

References

Ruppert, D., Wand, M.P. and Carroll, R.J. (2003)
Semiparametric Regression Cambridge University Press.
http://stat.tamu.edu/~carroll/semiregbook/

Ganguli, B. and Wand, M.P. (2005)
SemiPar 1.0 Users' Manual.
http://matt-wand.utsacademics.info/SPmanu.pdf

See Also

spm plot.spm lines.spm predict.spm summary.spm fitted.spm

Examples

library(SemiPar)
data(fossil)
attach(fossil)
fit <- spm(strontium.ratio~f(age))
plot(age,residuals(fit))
abline(0,0)

Retirement plan data

Description

The retire.plan data frame has data on "401(k)" retirement plans for employees of 92 firms managed by a company code-named Best Retirement Inc. (BRI).

Usage

data(retire.plan)

Format

This data frame contains the following columns:

contrib

contribution to retirement plan at end of first year

group

1=client has group life of group health insurance policy, 0=otherwise.

turnover

employee turnover rate.

eligible

number of employees eligible to participate in 401(k) plans.

vest

1=plan has immediate vesting of employer contributions, 0=otherwise.

failsafe

1=plan has a fail-safe provision, 0=otherwise.

match

percentage of contributions matched by the employer.

salary

average annual employee salary in dollars

.

estimate

underwriter's estimate of end-of-year contributions in dollars.

susan

1=plan was sold by a sales representative who has been specifically trained to deal exclusively with 401(k) plans (code-named Susan Shepard).

Source

Bryant, P.G. and Smith, M.A. (1995). Practical data analysis: case studies in business statistics. Chicago: Irwin.

References

Ruppert, D., Wand, M.P. and Carroll, R.J. (2003)
Semiparametric Regression Cambridge University Press.
http://stat.tamu.edu/~carroll/semiregbook/

Examples

library(SemiPar)
data(retire.plan)
pairs(retire.plan)

Salinity data

Description

The salinity data frame has 28 observations on hydrological measurements from Pamlico Sound, North Carolina, USA.

Usage

data(salinity)

Format

This data frame contains the following columns:

salinity

salinity in Pamlico Sound.

lagged.salinity

salinity in Pamlico Sound during the previous six weeks.

trend

trend=1 if the data is the first six-week period of the spring, and so forth. Used to detect possible effects of the seasonal warming trend.

discharge

discharge of fresh water from rivers into the sound.

Source

Ruppert, D, and Carroll, R.J. (1980), Trimmed least squares estimation in the linear model, Journal of the American Statistical Association, 75, 828-838.

References

Ruppert, D., Wand, M.P. and Carroll, R.J. (2003)
Semiparametric Regression Cambridge University Press.
http//stat.tamu.edu/~carroll/semiregbook/

Examples

library(SemiPar)
data(salinity)
pairs(salinity)

Sausage data

Description

The sausage data frame has data on 54 ‘hot dog’ sausages.

Usage

data(sausage)

Format

This data frame contains the following columns:

type

type of meat.

calories

number of calories.

sodium

measure of sodium content.

Source

Moore, D.S. and McCabe, G.P. (2003). Introduction to the Practice of Statistics, Fourth Edition, W.H. Freeman and Company.

References

Ruppert, D., Wand, M.P. and Carroll, R.J. (2003)
Semiparametric Regression Cambridge University Press.
http://stat.tamu.edu/~carroll/semiregbook/

Examples

library(SemiPar)
data(sausage)
attach(sausage)
points.cols <- c("red","blue","green")
plot(sodium,calories,col=points.cols[type],pch=16)
legend(200,180,c("beef","pork","poultry"),col=points.cols,pch=rep(16,3))

Scallop abundance data

Description

The scallop data frame has 148 triplets concerning scallop abundance; based on a 1990 survey cruise in the Atlantic continental shelf off Long Island, New York, U.S.A.

Usage

data(scallop)

Format

This data frame contains the following columns:

latitude

degrees latitude (north of the Equator).

longitude

degrees longitude (west of Greenwich).

tot.catch

size of scallop catch at location specified by "latitude" and "longitude".

Source

Ecker, M.D. and Heltshe, J.F. (1994). Geostatistical estimates of scallop abundance. In Case Studies in Biometry. Lange, N., Ryan, L., Billard, L., Brillinger, D., Conquest, L. and Greenhouse, J. (eds.) New York: John Wiley & Sons, 107-124.

References

Ruppert, D., Wand, M.P. and Carroll, R.J. (2003)
Semiparametric Regression Cambridge University Press.
http://stat.tamu.edu/~carroll/semiregbook/

Examples

library(SemiPar)
data(scallop)
pairs(scallop)

Sitka spruce data

Description

The sitka data frame contains measurements of log-size for 79 Sitka spruce trees grown in normal or ozone-enriched environments. Within each year, the data are organised in four blocks, corresponding to four controlled environment chambers. The first two chambers, containing 27 trees each, have an ozone-enriched atmosphere, the remaining two, containing 12 and 13 trees respectively, have a normal (control) atmosphere.

Usage

data(sitka)

Format

This data frame contains the following columns:

id.num

identification number of tree.

order

time order ranking within each tree.

days

time in days since 1st January, 1988.

log.size

tree size measured on a logarithmic scale.

ozone

indicator ozone treatment: 0=control,1=ozone.

Source

Diggle, P.J., Heagerty, P., Liang, K.-Y. and Zeger, S.L. (2002). Analysis of Longitudinal Data, Second Edition, Oxord: Oxford University Press.

References

Ruppert, D., Wand, M.P. and Carroll, R.J. (2003)
Semiparametric Regression Cambridge University Press.
http://stat.tamu.edu/~carroll/semiregbook/

Examples

library(SemiPar)
data(sitka)
attach(sitka)
library(lattice)
ozone.char <- rep("control",nrow(sitka))
ozone.char[ozone==1] <- "ozone"
xyplot(log.size~days|ozone.char,data=sitka,groups=id.num,type="b")

Fit a SemiParametric regression Model

Description

spm is used to fit semiparametric regression models using the mixed model representation of penalized splines (per Ruppert, Wand and Carroll, 2003).

Usage

spm(form,random=NULL,group=NULL,family="gaussian",
                spar.method="REML",omit.missing=NULL)

Arguments

form

a formula describing the model to be fit. Note, that an intercept is always included, whether given in the formula or not.

random

"random=~1" specifies inclusion of a random intercept according to the groups specified by the "group" argument.

group

a vector of labels for specifying groups.

family

for specification of the type of likelihood model assumed in the fitting. May be "gaussian","binomial" or "poisson"

spar.method

method for automatic smoothing parameter selection. May be "REML" (restricted maximum likelihood) or "ML" (maximum likelihood).

omit.missing

a logical value indicating whether fields with missing values are to be omitted.

Details

See the SemiPar Users' Manual for details and examples.

Value

An list object of class "spm" containing the fitted model. The components are:

fit

mimics fit object of lme() for family="gaussian" and glmmPQL() for family="binomial" or family="poisson".

info

information about the inputs.

aux

auxiliary information such as variability estimates.

Author(s)

M.P. Wand [email protected] (other contributors listed in SemiPar Users' Manual).

References

Ruppert, D., Wand, M.P. and Carroll, R.J. (2003)
Semiparametric Regression Cambridge University Press.
http://stat.tamu.edu/~carroll/semiregbook/

Ganguli, B. and Wand, M.P. (2005)
SemiPar 1.0 Users' Manual.
http://matt-wand.utsacademics.info/SPmanu.pdf

See Also

gam (in package ‘mgcv’) lme (in package ‘nlme’) glmmPQL (in package ‘MASS’) plot.spm summary.spm

Examples

library(SemiPar)
data(fossil)
attach(fossil)
fit <- spm(strontium.ratio~f(age))
plot(fit)
summary(fit)

data(calif.air.poll)
attach(calif.air.poll)
fit <- spm(ozone.level ~ f(daggett.pressure.gradient)+
                         f(inversion.base.height) +
                         f(inversion.base.temp))
summary(fit)
par(mfrow=c(2,2))
plot(fit)

# The SemiPar User Manual contains several other examples
# and details of plotting parameters.
#
# The current version of the manual is posted on the web-site:
#
#     http://matt-wand.utsacademics.info/SPmanu.pdf

Semiparametric regression summary

Description

Takes a fitted spm object produced by spm() and summarises the fit.

Usage

## S3 method for class 'spm'
summary(object,...)

Arguments

object

a fitted spm object as produced by spm().

...

other arguments.

Details

Produces tables for the linear (parametric) and non-linear (nonparametric) components. The linear table provides coefficient estimates, standard errors and p-values. The non-linear table provides degrees of freedom values and other information.

Value

The function generates summary tables.

Author(s)

M.P. Wand [email protected] (other contributors listed in SemiPar Users' Manual).

References

Ruppert, D., Wand, M.P. and Carroll, R.J. (2003)
Semiparametric Regression Cambridge University Press.
http://stat.tamu.edu/~carroll/semiregbook/

Ganguli, B. and Wand, M.P. (2005)
SemiPar 1.0 Users' Manual.
http://matt-wand.utsacademics.info/SPmanu.pdf

See Also

spm plot.spm predict.spm

Examples

library(SemiPar)
data(onions)
attach(onions)
log.yield <- log(yield)
fit <- spm(log.yield~location+f(dens))
summary(fit)

Term structure data

Description

The term.structure data frame has 117 observations on the prices of U.S. STRIPS (Separate Trading on Registered Interest and Principal of Securities) on December 31, 1995.

Usage

data(term.structure)

Format

This data frame contains the following columns:

time.to.maturity

time in years between 31st December, 1995, and the date on which the STRIPS matures.

price

price of the STRIPS as a percent of par.

Source

University of Houston Fixed Income Database.

References

Jarrow, R., Ruppert, D., and Yu, Y. (2004). Estimating the term structure of corporate debt with a semiparametric penalized spline model, Journal of the American Statistical Association, 99, 57-66.

Ruppert, D., Wand, M.P. and Carroll, R.J. (2003)
Semiparametric Regression Cambridge University Press.
http//stat.tamu.edu/~carroll/semiregbook/

Examples

library(SemiPar)
data(term.structure)
attach(term.structure)
plot(time.to.maturity,price)

Trade union data

Description

The trade.union data frame has data on 534 U.S. workers.

Usage

data(trade.union)

Format

This data frame contains the following columns:

years.educ

number of years of education.

south

indicator of living in southern region of U.S.A.

female

gender indicator: 0=male,1=female.

years.experience

number of years of work experience

union.member

indicator of trade union membership: 0=non-member, 1=member.

wage

wages in dollars per hour.

age

age in years.

race

1=black, 2=Hispanic, 3=white.

occupation

1=management, 2=sales, 3=clerical, 4=service, 5=professional, 6=other.

sector

0=other, 1=manufacturing, 2=construction.

married

indicator of being married: 0=unmarried, 1=married.

Source

Berndt, E.R. (1991) The Practice of Econometrics. New York: Addison-Wesley.

References

Ruppert, D., Wand, M.P. and Carroll, R.J. (2003)
Semiparametric Regression Cambridge University Press.
http://stat.tamu.edu/~carroll/semiregbook/

Examples

library(SemiPar)
data(trade.union)
pairs(trade.union,pch=".")

U.S. temperature data

Description

The ustemp data frame has 56 observations on the temperature and location of 56 U.S. cities.

Usage

data(ustemp)

Format

This data frame contains the following columns:

city

character string giving name of city and state (two-letter abbreviation).

min.temp

average minimum January temperature.

latitude

degrees latitude (north of Equator).

longitude

degrees longitude (west of Greenwich).

Source

Peixoto, J.L. (1990). A property of well-formulated polynomial regression models. American Statistician, 44, 26-30.

References

Ruppert, D., Wand, M.P. and Carroll, R.J. (2003)
Semiparametric Regression Cambridge University Press.
http://stat.tamu.edu/~carroll/semiregbook/

Examples

library(SemiPar)
data(ustemp)
attach(ustemp)
grey.levs <- min.temp+20
col.vec <- paste("grey",as.character(grey.levs),sep="")
plot(-longitude,latitude,col=col.vec,pch=16,cex=3,xlim=c(-130,-60))
text(-longitude,latitude,as.character(city))