Index

−1

estimate terms for each mean

remove the intercept

0

censoring indicator

count data

logical FALSE

replace missing values

status = censored

testing for zeros

1

logical TRUE

the intercept is parameter one

−

deletion of an explanatory variable from the model (not subtraction)

subtraction

!

logical NOT

selecting rows of a dataframe

! factorial

binomial distribution

Fisher's exact test

introduction

x! = x × (x – 1) × (x – 2)×· · ·×3 × 2

!=

not equal

!duplicated

not duplicated for dates and times

produce a set of subscripts that would select the non-duplicated values from an object

removing duplicate rows from a dataframe

removing pseudoreplication

!is.na

not missing values

!is.numeric

not numeric

""

issues with quote marks in SQL queries

"\a"

bell

"\b"

backspace

"\f"

form feed

"\n"

new line

removing using strsplit

separators with scan

"\r"

carriage return

"\t"

multiple tabs

removing using strsplit

separators with scan

tab character

"\v"

vertical tab

#

add comments to your R code

$

component selection

extracting information from summary(model)

indexing tagged lists

last character with grep

list indexing

variable names from dataframes

$fitted

function for model-checking

$infmat

jackknife

$resid

function for model-checking

%%

modulo

modulo with barplot to combine two distributions

remainder

%∗%

matrix multiplication

sum of products

%/%

integer quotients

%in%

as a subscript

character strings

sapply

set theory

&

combinations of T and F

logical AND

&&

logical AND with if

∗

inclusion of explanatory variables and interactions (not multiplication)

main effects and interactions in model formula

multiplication

wildcards in SQL queries using LIKE

. (dot)

anything character with grep

…

variable numbers of arguments (triple dot)

.Call

interface to compiled code

. convention

fit all the explanatory variables

.External

.GlobalEnv

environments in R

.Internal

interface to compiled code

.Primitive

.Random.seed

recall same random numbers

/

division

nesting of explanatory variables in the model (not division)

:

create a sequence

create factor levels

interaction term in model formula

sequence generation

;

multiple statements per line

?

help in R

??

help in R

[]

square brackets are subscripts

subscripts for subsetting

[,]

twin subscripts on dataframes

[,c]

column subscripts

[[]]

subscripts on lists have double brackets

with triple dot

[[1]]

list subscripts

[–1]

drop the first element from a vector

[1]

select the first element from a vector

[a,b)

greater than or equal to a but less than b

[A–E]

select a range of characters with grep

[r,]

row subscripts

\

backslash for quoting metacharacters

∧

caret symbol

first character with grep

highest interactions in model formula

powers and roots

{}

curly brackets with for loops

{n}

character counting in words

|

combinations of TRUE and FALSE (OR)

conditioning so y∼x | z is read y as a function of x given z

given with coplot

logical OR

∥

logical OR with if

∼

tilde, meaning ‘as a function of’

∼

statistical models

∼ . -

update

∼∼

extra spaces in expressions

∼1

estimate the intercept

fitting the null model

+

addition

continuation character

inclusion of an explanatory variable in the model (not addition)

<

less than

<

(read as “gets”)

assignment in R

destroys existing variables of the same name

<- a <- b <- c

multiple allocation

<=

less than or equal to

==

logical equals (double equals)

>

greater than

>

prompt (new command line)

>=

greater than or equal to

–1

estimate terms for each mean

remove the intercept

0

censoring indicator

count data

logical FALSE

replace missing values

status = censored

testing for zeros

0 and 1

binary response variable

0 in tables

tabulate rather than table

1

logical TRUE

the intercept is parameter one

1-β

Type II error rate (= 0.2)

2 by 2 contingency tables

log-linear model of count data

Mendel's peas

2/3 power of the response

normal errors

25th percentile

box-and-whisker plot

summary

2-parameter asymptotic exponential

non-linear models

2-parameter logistic

3D graphics

vis.gam output from gam

3-dimensional array

3-dimensional plots

introduction

3D-like object

persp or wireframe

3D surfaces

wireframe

3-parameter asymptotic exponential

non-linear models

3-parameter logistic

non-linear models

45 degree line

abline(0,1)

4-parameter logistic

non-linear models

75th percentile

box-and-whisker plot

summary

9:3:3:1 ratio

Mendel's peas

rescale.p=TRUE

95% confidence interval

introduction

a

intercept

abline

instead of grid

regression line through a scatterplot

abline(0,1), 45 degree line

abline(h=y)

horizontal line at height y

abline(model)

drawing your own piecewise lines

fit a line through a scatterplot

abline(v=x)

vertical line at location x

abline using subscripts

in ANCOVA

abs

absolute value (ignore the minus sign if present)

closest values

absolute value (ignore the minus sign if present)

abs

absolute values

rather than sum of squares

acf

autocorrelation function

for two time series

plot(ACF)

acf(type="p")

partial autocorrelation

acos

inverse cosine

add a legend to a plot

legend

add columns to a matrix or dataframe

cbind

add extra lines to a graph

lines

add extra points to a graph

points

adding a column to a dataframe

cbind

adding rows and columns to a dataframe

addition

+

additive or multiplicative errors

additivity

log response

address within vectors

which

add rows to a matrix or dataframe

rbind

add some not all of the numbers

logical subscripts

add=TRUE

with image to ensure smooth transition between frames

adequate models

introduction

adj

text justification

adjoint of a matrix

adjusted r² value

extracting from summary(model)

summary.lm

age at death

censoring

exponential errors

introduction

variance

age effects and cohort effects

longitudinal data

aggregate

alternative to tapply

dataframe summary

eliminating pseudoreplication

for summarizing dataframes

summary statistics

with length

aggregated

spatial point processes

aggregated pattern and quadrat count data

aggregation

comparing data with a Poisson distribution

Taylor's power law

AIC

Akaike's information criterion

binary response variable

comparing time series models

introductory example

from lists of models using lapply

function for model-checking

hand calculation

with offsets

Akaike's information criterion

introduction

akima

installed package

aliasing

correlation of explanatory variables

intentional aliasing

introduction

NA in summary(model)

piecewise regression

alive

last seen alive

all

logical function

logical operations

all.equal

comparing factors and characters

equality of floating point numbers

all=T

merge

along

in sequences

is.na

sequence generation

alpha

Type I error rate (= 0.05)

alphabetic order of factor levels

over-riding the default

alternative hypothesis

in one-way ANOVA

Student's t test

always look at your data

Anscombe's famous data

am/pm indicator

%p AM/PM indicator in the locale

analysis of covariance

illustration

introduction to ANCOVA

maximal model

model simplification

analysis of deviance

log-linear model of count data

Analysis of Ecological and Environmental Data

task views

Analysis of Pharmacokinetic Data

task views

Analysis of Spatial Data

task views

analysis of variance

introduction

with regression

ANCOVA

ANCOVA or mixed effects models

binary response variable

compared with mixed effects model

equivalent in gam

factorial experiment

famous five

illustration

introduction

model formulae

plots of fitted values

plots using subscripts

standard error of the intercept

survival analysis

with proportion data

AND

&

combinations of T and F

angle = 45

cross-hatching, 919–20

anisotropy

spatial autocorrelation

anonymous functions

apply

example

plot.design

sapply

tapply

anova

as summary.aov

compare two non-linear models

compare two survivorship models

comparing two regression models

contingency table analysis, 605, 609–10

for model objects

model formulae

piecewise regression

power.anova.test

ANOVA table

format using cat

in ANCOVA

in one-way ANOVA

soil data

with regression

ANOVA to compare models

gam

mixed effects models

Anscombe's famous data

always look at your data

antilog

geometric mean

transformations

antilog base e

exp

antolog

introduction

any

logical test

anything character with grep

. (dot)

aov

fit a one-way ANOVA

with Error

aov with Error

rats example

aperm

re-order a multidimensional table

transpose an array

aphids

dangers involved in contingency tables

a posteriori contrasts

apply

anonymous functions

column means

counting missing values

function to one margin of a matrix

introduction

standard deviations

a priori contrasts

apropos

vector of matching names

AR

autoregressive models

arbitrary number of arguments to a function

triple dot …

arcsine

transformation

arcsine transformation

background

area

incidence functions

Arg

argument of complex number

argument lists

introduction

argument matching

argument of complex number

Arg

arguments

exact matching on tags

arguments to a function

triple dot

arima

fits time series models

lynx example

arithmetic mean

function

maximum likelihood

arithmetic operations

introduction

ARMA

autoregressive moving average models

array

create an array with specified dimensions

arrays

changing the dimensions

introduction

arrows

adding shapes to a graph

fat arrows function

for error bars

phase planes

shape of head

as.character

coercion

names on maps

as.complex

coercion

as.data.frame

admissions data

coercion

dataframe from a table

expanding a table into a dataframe

table to dataframe

with readLines

with scan

as.data.frame.table, 3-dimensional contingency table

producing a shorter summary dataframe

as.Date

coercion

as.difftime

coercion

as.expression(substitute)

calculated values in expressions

as.factor

coercion

as.formula

for complex model formulae

as.integer

coercion

as.is

with read.table

as.list

using scan

as.numeric

coercion

factors in a dataframe

lapply

Sys.time

with unlist

as.POSIXct

coercion

as.POSIXlt

introduction

as.vector

coercion

to remove names from objects

ask = TRUE

input requested before the next graphic

assign

str of linear model

assignment

destroys existing variables of the same name

gets arrow <-

asin

inverse sine

as is I

background

introduction

model formulae

piecewise regression

polynomials

assocplot

Cohen–Friendly association plot

assumptions

additive effects

constant variance

in one-way ANOVA

independent errors

linear regression

mixed effects models

normal errors

simple is best

asymptote

Michaelis–Menten

polynomials

asymptotic exponential

behaviour at the limits

introduction

non-linear models

parameter estimation

asymptotic exponential vs. Michaelis–Menten

nonlinear regression

asymptotic regression model

SSasymp

asymptotic regression model through the origin

SSasympOrig

asymptotic regression model with an offset

SSasympOff

atan

inverse tangent

attach

dataframe from a package

dataframe operations

masking

use with instead to avoid masking

used in this book

attach or with

best practice

attributes

find levels and class of an object

of a matrix

using all.equal

attributes of a factor

contrasts

augPred

predict families of curves

auto.key

panel plots

autocorrelation

model criticism

residuals

time series

autocorrelation function

acf

autoregressive (AR) models

time series models

autoregressive moving average (ARMA) models

averaging away the pseudoreplication

example

rats example

axes

counting things on maps

axes and boxes

colour

axes=FALSE

plot with no axes

axis

graphics parameters explained

non-default labelling

non-standard labels for tick marks

phase planes

axis 1

bottom (x axis)

axis 2

left (yaxis)

axis 3

top

axis 4

right

axis colour

col.axis

azimuthal direction

persp

b

derivation of slope

parameter of the power function

slope of straight line

SSXY/SSX

background colour for plots

bg

background colour in plotting symbols

introduction

multiple time series

background colours

colour of the paper

par(bg="wheat2")

backspace

"\b"

back-transform to proportions

logits

back-transformation

logits to proportions

predict with model

bacteria data

MASS library

pseudoreplication

balls in urns

hypergeometric distribution

bandwidth

density estimation

bar chart

introduction

barchart

panels of barplots

barplot

beside=T

binomial distribution

comparing data with a Poisson distribution

count data from quadrats

cross-hatching

Daphnia data

density function of the geometric distribution

for side by side distributions 0s, 1s, etc.

from tapply

hypergeometric distribution

in one-way ANOVA

introduction

legend

negative binomial distribution

overlay a smooth line

rotating long bar labels to eliminate overlap

two distributions combined 0s, 1s, etc.

barplots

barchart

Bartlett's test

comparing several variances

bartlett.test

comparing several variances

comparing two variances

base e logarithms

introduction

base of natural logarithms

e = 2.71828

baseline hazard function

Cox proportional hazards model

basename

file paths

Bayesian Inference

task views

Bayesian inference Using Gibbs Sampling

BUGS

Bayesian statistics

credible interval

introduction

likelihood of our model, given the data

model choice

probability background

shrinkage

BCa

bias-corrected accelerated percentile

BCa interval

in regression

behaviour at the limits

asymptotic exponential

asymptotic function

introduction

logistic

bell

"\a"

bell-shaped

non-linear models

Bernoulli distribution

binary response variable

introduction

beside=T

barplots

best linear unbiased predictors

BLUP

beta

beta distribution

power of the test

beta distribution

beta

introduction

bg

background colour for plots

background colour in plotting symbols

bg="wheat2"

background colours

BH

multiple comparisons

bias

meta-analysis

bias-corrected accelerated percentile

Bca

biexponential

non-linear models

biexponential model

humped curves

SSbiexp

binary

function to create binary representation of a number

binary data

random-effects meta-analysis

binary data expressed as proportion data

binary representation of a number

binary response variable

ANCOVA

Bernoulli distribution

box-and-whisker plot

continuous explanatory variable

gam

introduction

no such thing as overdispersion

predict(type="response")

smooth line from a logistic model

subset

with non-parametric smoothers

binary response with pseudoreplication

binom

binomial sample size

binom.test

introduction

two-category table

binomial

deviance formula

binomial coefficients n!/(x! (n – x)!)

choose(n,x)

binomial data

quasibinomial

binomial denominator

number of attempts

binomial distribution

introduction

binomial errors

logit link

overdispersion

useful with data on proportions

binomial glm

model simplification

binomial link function

logit(p)

binomial priors

Bayesian statistics

binomial sample size

binom

binomial standard errors

for plots

binomial test

proportion data

binomial variance

illustration

bins

for count data

in histograms

bin widths

drawing a smooth curve

hist

using cut

biomass

error.bars

biplot

principal components analysis

black is rgb(0, 0, 0)

rgb

blank axes labels

xlab=""

ylab=""

blank spaces

in variable names

blank spaces in names

read.csv

blank subscripts

all rows or all columns

blocking

analysis of variance

example split plot

paired t test

BLUP

best linear unbiased predictors

Bonferroni

multiple comparisons

bookmakers' odds

p/(1-p)

boot

package for bootstrap

boot.ci

bootstrap with glm

confidence intervals from the boot object

in regression

non-linear regression

boot package

in regression

bootstrap

a family of non-linear regressions

introduction

jackknife after bootstrap

sample(replace=T)

with glm

with regression

with single samples

border = NULL

cross-hatching

bordered lines

different colours

both axes log scale

log="xy"

both points and lines

type="b"

bottom (the x axis)

axis = 1

margin = 1

bound symbols

introduction

bounded response

proportion data

box

boxcol

boxfill

boxlty

boxlwd

box-and-whisker plots

binary response variable

bwplot

competition experiment

full colour control

in one-way ANOVA

introduction

notches

single samples

variance components analysis

boxcol

line colour

Box–Cox

transformations

boxes around plots

bty

boxfill

fill colour

boxlty

line type

boxlwd

line width

boxplot

notch=T

one-way ANOVA

OrchardSprays

ordered names

break(s)

bin widths

edge effects in spatial simulations

for count data

to leave a repeat loop

to specify the bins of a histogram, 224–5

bty

boxes around plots

bubble plot

introduction

bubbles

using cex

BUGS

Bayesian inference Using Gibbs Sampling

overdispersed binomial example

regression example

temporal pseudoreplication example

butt

ends of lines

bwplot

box-and-whisker plots

illustration

panel plots

by

dataframe summary

equivalent of ANCOVA in gam

for summarizing dataframes

model fitting within categories

multiple comparisons

sequence generation

by.x

merging dataframes

by.y

merging dataframes

byrow=F

argument to the matrix function

bzfile

connections

c

concatenate character strings

concatenation

creating vector of numbers

C

cubic contrasts

cubic terms

C+

interface to compiled code

calculated values in expressions

as.expression(substitute)

calculations

introduction

calculations with dates and times

calculus

introduction

call

str of linear model

canonical link functions

glm

captial letters

toupper

car

installed package

car package

data ellipse

carriage return

"\r"

case sampling

bootstrap

case sensitive

variable names in R

cat

formatted output

categorical explanatory variables

analysis of variance

classification trees

with count data

categorical variables

background

factor

plotting

cauchy

Cauchy distribution

Cauchy distribution

cauchy

introduction

cbind

add columns to a matrix or dataframe

adding a column to a dataframe

famous five

multiple response variables

response object for glm with binomial errors

cdplot

parasite data

ceiling

next integer

censoring

background

examples

introduction

predicted mean age at death

censoring indicator

introduction

central

different measures of central tendency

central limit theorem

dice game

introduction

centred text (the default)

par(adj=0.5)

cex

character expansion (text size)

determines the size of plotting characters pch

names on maps

size of plotting symbol

stands for character expansion (relative to 1)

cex.axis

determines the size of the axis numbers

cex.lab

determines the size of the text labels on the axes

changing the look of panel plots

panel function

channel

Data Source Name

odbcConnect

chaos

period doubling route

population dynamics

simulation models

character

class

what with scan

worms

character counting in words

{n}

character expansion

cex

characteristic equation

character matching

charmatch

character rotation

srt

character strings

%in%

collapse

in dataframes

introduction

regexpr

remove quotes from character strings

reverse a character string

which

with read.table

character to numeric

coercion

characters in a string

nchar

charmatch

character matching

charplot

function

checking the dataframe

checking the model

background

Chemometrics and Computational Physics

task views

chisq

chi-squared distribution

chisq.test

contingency tables

matrix of Mendel's peas

table objects

two-category table

unequal probabilities

chisq.test(rescale.p=TRUE)

Mendel's peas

chi-squared

chisq

hypothesis testing

special case of the Gamma distribution

chi squared contingency tables

introduction

chi squared distribution

choice of test

simplest is best

choose(n,x)

binomial coefficients n!/(x! (n – x)!)

choosing the right test

introduction

CI

see confidence interval

ci95

function for 95% confidence intervals

circle, 2 pi radians

function to create a circular polygon

points on random radii

circled points

highlighting

circles

drawing bubble plots

citation

of R in written work

Clark and Evans

Test for complete spatial randomness

class

character

complex

dates and times

factor

integer

list

logical

numeric

of a matrix

raw

Sys.time

vector

classification trees

categorical explanatory variables

partition.tree

class knn

identities of the k nearest neighbours

class lw

weights list object

class nb

neighbour file

class of time series objects

class polylist

polygon lists

polygons defining the outlines of regions on a map

Clinical Trial Design, Monitoring, and Analysis

task views

clipboard

connections

writeClipboard

closely packed

multipe graphs

closest

function to find the closest value in a vector

closest values

with which and abs

cloud

panel plots

three-dimensional scatterplots

clumping parameter of the negative binomial

k

cluster analysis

introduction

Cluster Analysis & Finite Mixture Models

task views

clustering

spatial point processes

cm.colors

illustration

coda

package for MCMC output

Codd, E.F.

relational database design

coef

extracting information from model objects

for model objects

with lapply

coefficient of determination

introduction to r²

coefficients

solving linear equations

str of linear model

coercion

as.character

as.complex

as.data.frame

as.difftime

as.integer

as.numeric

background

computing new factor levels

failure gives NA

logical arithmetic

piecewise regression

with logical subscripts

Cohen–Friendly association plot

assocplot

cohort effects and age effects

longitudinal data

col

colour for plotting symbols

subscripts to groups in matrices

col.axis

colour to be used for axis annotation

col.lab

colour to be used for x and y labels

col.main

colour to be used for plot main titles

col.names=F

with write.table

col.sub

colour to be used for plot subtitles

col=grey

grey scale as an alternative to colour in barplots

colatitude

persp

collapse

create a single character string

with paste

collapsing a contingency table

dangers involved

collinearity

multiple regression

colMeans

colMeans(x) column means of dataframe or matrix x

colnames

names for the columns in a matrix

naming columns of a matrix

colors()

see all the colours used by R

colour

changing screen default settings

contrasting points on graphs

factor levels for plotting

fitted values with ANCOVA

in legends

introduction

plots with many variables

plotting symbol

RColorBrewer package

staplecol

whiskcol

colour control

box-and-whisker

coloured plotting symbols with contrasting margins

illustration

pch=21 to pch=26

coloured points

coloured symbols

colouring under a curve

polygon

colour in legends

barplot

fill

colour numbers

illustration

colour of the fill of the plotting symbol

outbg

colour of the outline of the plotting symbol

outcol

colours in R

hexadecimal string of the form #rrggbb

palette()[i]

colours showing around edges

illustration

colour with curved shapes

polygon

colSums

tables of proportions

colSums(x)

column totals of dataframe or matrix x

column

removing a column using subscripts

second subscript

column added to a dataframe

cbind

columns and rows

tapply

column and row totals

dangers involved in contingency tables

margins of contingency tables

columns

select from dataframe

comparisons across columns using max.col

columns of a dataframe

selecting by name

using subscripts

column sums using apply

column-wise

default data entry for matrix

combinatorial formula

binomial coefficients

comma

as decimal point

comma delimited files

read.csv

using scan

command line

versus scripts

comment lines in R code

#

comparing data with a Poisson distribution

example

comparing Michaelis–Menten and asymptotic exponential

nonlinear regression

comparing two distributions

Kolmogorov–Smirnov

comparing two variances

Fisher's F

var.test

competition

error.bars

competition experiment

competitive exclusion

compiled code

.Call

.External

.Internal

.Primitive

complementary log-log link

binary response variable

complete.cases

check for rows with NA

complete spatial randomness

Clark and Evans test

CSR

complex

class

what with scan

complex contingency table

Schoener's lizards

complex files

using scan

complex mathematical expressions

plotmath

complex numbers

Arg

Conj

Im

introduction

Mod

Re

complicated error structures

mixed effects models

complicated formatting of axis labels

expression

component selection

$

Comprehensive R Archive Network

CRAN

Computational Econometrics

task views

computing new factor levels

factors

concatenate

use c to create a vector

concatenation

create a vector of numbers

slowness of

conditional probability

conditioning plots

coplot

multiple plotting panels

panel plots

confidence interval

as error bars

boot.ci

introduction

predicted values in linear regression

probability of parameter value

sample variance

Student's t test

what CI is, and is not

confidence interval by bootstrap

quantile

confidence intervals from the boot object

boot.ci

confint

for the parameters of a model object

Conj

conjugate of complex number

conjugate priors

Bayesian statistics

connections

introduction

connections: error messages

stderr

connections: input

stdin

connections: output

stdout

conservative tests

comparing t test and Wilcoxon test

constancy of variance

square root of the response

constant coefficient of variation data

Gamma errors

constant variance

in one-way ANOVA

linear regression assumptions

test before ANOVA

constrained margins

contingency tables

constant risk of death

Type II survivorship

contingency data

conversion to proportion data

contingency table analysis

main effects are meaningless nuisance variables

update and anova

contingency tables

background

dangers involved

d.f.

introduction

observed and expected

plot methods

Schoener's lizards as an example of a complex contingency table

contingency tables of intermediate complexity

continuation character

+

continuous explanatory variable

binary response variable

linear regression

continuous to categorical variable

cut

ifelse

continuous variables

background

contour

three-dimensional plots

contour plots

contourplot

contour(add=T)

illustration

contourplot

contour plots

panel plots

contr.helmert

in ANCOVA

contr.sum

contr.treatment

contrast coefficients

introduction

contrast sum of squares

contrasts

in ANCOVA

in one-way ANOVA

introduction

multiple comparisons

orthogonal polynomial contrasts

planned comparisons

standard error of the difference between two means

three kinds compared

contrasts=c("contr.helmert","contr.poly")

Helmert contrasts

contrasts=c("contr.sum","contr.poly")

sum contrasts

contrasts=c("contr.treatment","contr.poly")

treatment contrasts

convex hull

colour fill

Cook's distance

model checking

coplot

ethanol data

graphics for mixed effects models

introduction

species with productivity

cor(x,y)

correlation between vectors x and y

cor.test

non-parametric tests of correlation

species with productivity

corAR1

non-linear time series models

corExp

exponential spatial correlation

corGaus

Gaussian spatial correlation

corLin

linear spatial correlation

corRatio

rational quadratic spatial correlation

corrected sums of products

corrected sums of squares

correction factor

matrix notation

correlated explanatory variables

non-orthogonal data

correlation

and variance

and covariance

at different lags

background

between polynomial terms

dredging for significance

partial

scale-dependent correlations

shared common cause

variance of a difference

correlation between explanatory variables

multiple regression

correlation coefficient

cor(x,y)

from SSXY

in terms of variances

correlation is not causation

scatterplots

correlation of explanatory variable(s)

intrinsic aliasing

multiple regression

correlations

multiple time series

switch off in lmer output

correlations in lmer output

suppressing correlations using print(cor=F)

correlation structure

time series analysis

correlogram

illustration

introduction

corSpher

spherical spatial correlation

corSymm

general correlation matrix

cos

cosine in radians

drawing bubble plots

introduction

polynomial approximation

cosine in radians

cos

cost–complexity measure

model simplification in tree models

count characters

table

count data

ANCOVA

background

contingency tables

generalized linear mixed models

introduction

Poisson distribution

Poisson errors

regression

strictly bounded

count data in tables

introduction

count data on proportions

successes and failures

counting missing values

table

counting specific characters

gregexpr

counting things on maps

cut(right=FALSE)

counts

tables of counts

counts to proportions

admissions data

count the occurrences of each value

table

coupled map lattice

spatial dynamics of host–parasite interaction

cov(x,y)

covariance

covariance

and correlation

autocorrelation

background

multivariate normal distribution

variance of a difference

covariance of x and y

var(x,y)

Cox proportional hazards model

ANCOVA example

survival analysis

coxph

roaches data

coxph and survreg

comparison on same data

coxph or survreg

model choice

CRAN

Comprehensive R Archive Network

contents

craps

dice game

create a time series object

ts

create character string

paste

create file paths

paste

creating a vector

concatenation

creating labels from factor levels

ifelse

creating level plots (similar to image plots)

levelplot

creating new factors

logical arithmetic

model.matrix

credible interval

Bayesian statistics

highest posterior density

critical value

comparing two variances

contingency tables

critical value of Student's t

qt

critical values for contingency tables

qchisq

criticism

model criticism

crossdist

distances between points in two patterns

cross-hatching

angle = 45

border = NULL

density = NULL

in polygons

instead of colour in barplots

cross tabulations

xtabs for the admissions data

CSR

complete spatial randomness

cube root transformation

Box–Cox

cubic regression spline

generalized additive models

cummax

vector of non-decreasing numbers which are the cumulative maxima of the values in x up to that point

cummin

vector of non-increasing numbers which are the cumulative minima of the values in x up to that point

cumprod

for factorials

vector containing the product of all of the elements up to that point

cumsum

cumulative distribution functions

vector containing the sum of all of the elements up to that point

cumulative distribution function(s)

cumsum

ecdf

Kolmogorov–Smirnov

cumulative probability

p

cumulative probability of chi-squared distribution

pchisq

cumulative probability of Gaussian distribution

pnorm

cumulative probability of Student's t distribution

pt

cumulative probability of the F distribution

pf

current model

definition

current working directory

getwd

curvature

changed by transformation

model checking

multiple regression

test for

curvature in response

generalized additive models

curve

compared with plot

density of the standard normal distribution

draw mathematical functions

curved lines

linear models

nonlinear regression

non-parametric smoothers

predict with model

quadratic terms

curved shapes

polygon

customized palettes

using rgb

cut

continuous to categorical variable

for creating quadrats on a map

function to create bins of specified width

right=FALSE

testing the random number generator

to compute empirical probabilities for plots

to created histogram bins

cycle length

pi ∗2

seasonal data

cycles

Nicholson's blowflies

population dynamics

cyclic time series

sin-cos models

cylindrical or tapered timber

Offsets

D

function for differentiation

probability density

d.f. (degrees of freedom)

ANOVA table for regression

contingency tables

count data from quadrats

efficient regression designs

example split plot

extracting information from summary(model)

in ANCOVA

in factorial experiments

in one-way ANOVA

introduction

mixed effects models

multiple regression

observed vs. expected frequencies

spotting pseudoreplication

Student's t test

d.f. = 0

saturated model

dangers involved in contingency tables

example

dangers of extrapolation

illustration

Daphnia

data file

dashed lines

lty = 2

data

Ancovacontrasts

berks.accdb

bioassay

bloodcells

blowfly

bowens.csv

box

cancer

car.test.frame

cases

catdata

cellcounts

chicks

childfull

classic

clusters

competition

compexp

Daphnia

das

dates

decay

diminish

disease

dups

epilobium

f.test.data

farms

fertilizer

fisher

fishes

fltimes

fol

fungi

gain

gales

gardens

germination

growth

herbicides

houses

induced

infection

ipomopsis

isolation

jaws

kmeansdata

ksdata

lackoffit

lifeforms

light

lizards

logplots

longdata

lynx

manova

map.places.csv

metadata

metadata2

mm

murders

naydf

nested2

nonlinear

occupation

ozone

ozone.data

pa.csv

panels

para

parasites

pgfull

pgr

pHDaphnia

piedata.csv

plotcol

plotfit

pollute

productivity

quine

ragwortmap

ragwortmap2006

rats

reaction

refuge

regdat

regression

roaches

rt

sales

sapdecay

sasilwood

scatter1

seedlings

seedwts

sexratio

SilwoodWeather

skewdata

sleep

smoothing

soaysheep

spatialdata

species

spending.csv

spino

splityield

sslogistic

streams

sweepdata

t.test.data

tabledata

tannin

taxon

taxonomy

temp

temperatures

timber

timereg

trees

trial

twosample

twoseries

vc22outline

weibull.growth

worldfloras

worms

worms.missing

wtable

yield

yields

data()

built-in data sets

view available packages

data.frame

creating a dataframe

for displaying several vectors as columns

producing a shorter summary dataframe

to create column-wise table of vectors

database management systems

DBMS

data dredging

introduction

data editor

data ellipse

illustration

data entry from file

read.table

data entry from keyboard

scan

data exploration

first things first

tree models

dataframe(s)

certain columns

changing the names of the columns

character variables as factors

compared to matrix

comparison of read.table and readLines

complete.cases

converting to a table

dates and times

drop rows using negative subscripts

from column data using stack

head

initial checks

introduction

logical subscripts

match

merging

missing values

NA

producing a shorter summary frame

removing a column using subscripts

removing rows using subscripts

select certain columns

selecting columns in a dataframe

selecting only certain rows

sort

stack

str

strptime

summary

sweep

time differences between rows

unlist

using logical subscripts

using subscripts

write.table

dataframe operations

attach

head

names

tail

view the entire contents

dataframes attached

search

dataframe summary

aggregate

by

summary

data input

using scan

data input from a file

readLines

data input from the web

URL

data inspection

Anscombe's famous data

statistical models

datasets

built-in

data sets in packages

data series

stl

Data Source Name

DSN

dates and times

%c Date and time, locale-specific

%x Date, locale-specific

class

dataframe rows

differences between two dates

from component hours, minutes and seconds

in dataframes

introduction

mode

reading data from file

reading from file

regression

sequence generation

sorting

strptime

summary

day of the month

%d Day of the month as decimal number (01–31)

day of the year

%j Day of year as decimal number (0–366)

DBMS

database management systems

dead or alive

proportion data

death rate

hazard

introduction

death risk with age

exponential

extreme value

Gompertz

Makeham

model choice

Rayleigh

Weibull

decay

exponential model

mechanistic model

decimal places

in columns of a matrix

round

decimal point options

declining sequences

using : or seq

decomposition of time series by loess

stl

Deevey survivorship curves

illustration

default parameter

graphics

degree symbol

TEX-like rules

degrees of freedom

see d.f. (see p. 992, above)

degrees to radians

conversion

Delaunay triangulation

Voronoi tesselation

deletion p values

summary.lm tables

deletion tests

model simplification

delimitors in files

demo

demonstration of R function

demonstration of R function

demo

denominator

proportion data

density

density estimation

example split plot

of shading

density = NULL

cross-hatching

density dependent processes

population dynamics

density estimation

introduction

density function

for Fisher's F

Gamma distribution

over a histogram

Weibull distribution

density function of the geometric distribution

dgeom

density function overlay

hist

density of cross hatching

illustration

density.ppp

kernel smoothed density

densityplot

kernel density plots

panel plots

posterior distribution

deparse

drawing bubble plots

introduction

departures from the mean

scale

derivatives

examples

derived variable analysis

dealing with pseudoreplication

DerSimonian and Laird estimate

between-study variance tau-squared

designed experiments

random effects

Design of Experiments (DoE) & Analysis of Experimental Data

task views

design plots

plot.design

deSolve

package for solving differential equations

det

determinant of a matrix

detach

avoid masking

example

remove a dataframe from the search path

detection of thresholds

efficient regression designs

determinant

of a matrix

de-trending

differencing

Nicholson's blowflies

dev.off()

end pdf or postcript session

switch off a pdf or post script file

deviance

Akaike's information criterion

binary response variable

introduction

of a linear regression object

deviance > residual d.f.

overdispersion

deviance formula

binomial

Gamma

Gaussian

inverse Gaussian

Poisson

deviance test

contingency tables

df (for degrees of freedom, see d.f.)

Fisher's F

dgamma

skew

dgeom

density function of the geometric distribution

diag

matrix diagonals

dice

the game of craps

dichotomous key

classification trees

diff

length of vectors

the difference function

difference

power analysis

difference between two variances

difference equation

quadratic map

differences between intercepts

factorial ANCOVA

differences between means

summary.lm

understanding summary.lm

differences between slopes

factorial ANCOVA

differences between successive values of a vector

diff

differences rather than paired t test

difference to be detected

sample size

differencing

de-trending

effects on length

differential equations

introduction

task views

differentiation

introduction

different y axes on the same x axis

difftime

differences between two times or dates

dim, 3-dimensional contingency table

after unlist with readLines

defining a matrix from a vector

dimensions of an array

dimensional arguments

cube root transformation

dimensions of an array

array

dim

dimnames

allocated by list

allocating names to factor levels

argument to the matrix function

removal using as.vector

using paste

dir

view file names

dirname

file paths

discrete probability distributions

introduction

discriminant analysis

dissimilarity matrix

hierarchical cluster analysis

dist

hierarchical cluster analysis

distance

incidence functions

Pythagoras

distance from any location to nearest data point

exactdt

distance in the complex plane

Mod

distance map image

distmap

distance measures

hierarchical cluster analysis

to nearest neighbour

to nearest random point

distance to edge of plotting region

pmin

distances between all pairs of points

pairdist

distances between points in two patterns

crossdist

distmap

distance map image

distribution

comparing two distributions

diverging colours

RColorBrewer package

division

/

dizygotic twins

probabilities

DLL

dyn.load

dynamically loadable libraries

dlnorm

density function of the log normal

dlogis

logistic compared to normal

dnbinom

density function of a negative binomial

negative binomial distribution

dnorm

curve

density of the standard normal distribution

drawing a smooth curve

graph

dominant eigenvector

dominant species

max.col

dose.p

bioassay

dot "."

anything character with grep

smallest plotting symbol

dot . convention

fit all the explanatory variables

dot-dash line

lty = 4

dot distribution maps

introduction

dot plots

dotplot

dotplot

panel plots

dotted line

lty = 3

draw families of curves

plot(augPred)

drawing a smooth curve through a scatterplot

nonlinear regression

drawing boxes

graphical test of normality

drawing circles

bubble plot

drawing fitted curves

drawing multiple lines

for loops

drawing smooth probability density curve

dredging for significance

drop elements from a vector

negative subscripts

drop=F

keep all the dimensions of a matrix

drop rows

using negative subscripts

drop the header row

DSN

Data Source Name

dummy variables

in one-way ANOVA

duplicated

produce a set of subscripts that would select the duplicated values from an object

duplicate rows in a dataframe

eliminating

duplicates

plots with multiple copies of data points

Durbin Watson

serial correlation in the residuals

durbinWatsonTest

library("car")

dyn.load

dynamically loadable libraries

dynamically loadable libraries

DLL in C or Fortran

dynamics

simulation models

e

exponents for scientific notation

e = 2.71828

base of natural logarithms

each

option for rep

ecdf

empirical cumulative distribution function

edge correction

Ripley's K

edge effects in spatial simulations

break

wrap-around margins

edge of plotting area

edges

counting things on maps

editor

effects

str of linear model

effect size(s)

analysis of variance

background

illustration

in one-way ANOVA

introduction

log(response ratio)

meta-analysis

model.tables

odds ratio

panel plots

plot.design

power analysis

response ratio

risk difference

risk ratio

summary.lm

efficient regression designs

detection of thresholds

replication

spread of x values

tests for non-linearity

eigen

Leslie matrix

eigenvalue

eigenvector

Einstein

quote

eliminating duplicate rows from a dataframe

eliminating pseudoreplication

aggregate

ellipse

illustration

empirical cumulative distribution function

ecdf

Empirical Finance

task views

empirical probabilities

in plots of logistic regression

empirical scale parameter

overdispersion

end of line shape

lend

ending a function

return

ends of lines

butt

round

environment current names

objects

environments

evaluation environment

in R

Epilobium

classification trees

equality of floating point numbers

all.equal

identical

isTRUE

equilibrium behaviour

simulation models

Error

with aov

error.bars

function

function with one-way ANOVA

error bars

arrows angle = 90

arrows code = 3

competition data

introduction

x and y directions

error bars on empirical probabilities

logistic regression

error bars on graphs

error-checking plot

single samples

error checks

plot(y)

error d.f.

spotting pseudoreplication

error rate

multiple comparisons

error recovery

try function

errors

additive or multiplicative

linear regression assumptions

errors correlated

gls

error structures

generalized linear models

pseudoreplication in nested designs and split plots

statistical models

error sum of squares

illustration

errors with read.table

error terms

multiple error terms

pseudoreplication in nested designs and split plots

error variance

efficient regression designs

illustration

in one-way ANOVA

multiple error terms

summary.aov

Error with aov

rats example

esoph

built-in dataframe

estimation

parameter values from data

estimators

maximum likelihood

ethanol data

humped data

illustration

panel plots

evaluation environment

evaluation frame

even numbers

modulo %%

subscripts from a vector

exact binomial test

binom.test

exactdt

distance from any location to nearest data point

exact mean

generating random numbers

example

worked examples of function

examples of function

example

Excel readable file from R

exp

antilog base e

exponential

for geometric mean

polynomial approximation

Ricker curves

smooth line from a log-linear model

expand.grid

introduction

expanding a dataframe

subscripts

expanding a table into a dataframe

lapply

expectation

Bernoulli distribution

expectation of the vector product

covariance

expected values from chisq.test

experimental design

randomization is better than ANCOVA

randomization using sample

experiments

factorials

explained variation in ANOVA

SSA

explained variation in regression

SSR

explanatory variables and principal components

illustration

explanatory variable(s)

choosing the right test

error bars in x and y directions

interaction

log transformation

optimal transformation

exponential

asymptotic function

death risk with age

exp

special case of the gamma distribution

exponential decay

example

mechanistic model

exponential distribution

illustration

introduction

pdf for mortality data

exponential errors

survreg

useful with data on time to death

exponential function

introduction

exponential growth

Leslie matrix

exponential spatial correlation

corExp

exponents

introduction

large and small numbers

expression

complicated formatting of axis labels

introduction

mathematical and other symbols on plots

produce more complex titles

extinction rate in metapopulation models

extracting information

model objects

extracting information using list subscripts [[]]

summary.aov

summary.lm

extract part of a character string

gsub

regexpr

substr

substring

extrapolation

dangers of

issues with polynomials

extreme cases

Fisher's exact test

extreme value

death risk with age

extrinsic aliasing

introduction

eye colour

contingency tables

F

Fisher's F

hypothesis testing

variance ratio test

factanal

factor analysis

factor

as.numeric

categorical variables

class factor

contrast attributes

declaring numbers as factors

display the levels of a factor

generating factor levels

mode numeric

nlevels

non-alphabetic ordering the levels

numerical factor levels

plotting

text in dataframes

factor analysis

factanal

introduction

plots

factorial

binomial distribution

Fisher's exact test

gamma(x+1)

introduction

relation to gamma function

writing a function

x! = x × (x − 1) × (x − 2)×· · ·×3 × 2

factorial ANCOVA

summary.lm

factorial experiments

ANCOVA

expand.grid

interaction plots

introduction

main effects

plot.design

factor level generation

gl

factor level names

dimnames

factor level reduction

binary response variable

logical arithmetic

model simplification

model simplification in ANCOVA

factor levels

calculation using logical arithmetic

computing new factor levels

create using :

creation using rep

expand.grid

interactions

levels gets

non-alphabetic order

producing a shorter summary dataframe

factor levels for plotting

heat.colors

order

using colour palettes

factor levels to labels

ifelse

factor(ordered=FALSE)

un-order an ordered factor

factors

analysis of variance

background

creating factor names using :

creating new factors with logical arithmetic

from continuous variables

levels to numbers with unclass

ordered factor levels

plotting

reverse sorting

factors and character strings

using all.equal

factors in a dataframe

levels

worms

failure

Bernoulli distribution

binary response variable

try function

fair dice

chisq.test

FALSE

coerces to zero

FALSE and TRUE

combinations of values

falsifiable null hypothesis

independence in contingency tables

families of curves

nlsList

plot(augPred)

family

specify the error structure in a glm

familywise error rate

multiple comparisons

famous five

background

in ANCOVA

matrix multiplication

FAQ

about R

fat arrows function

introduction

fat tails

Cauchy distribution

t compared with normal

fdr

multiple comparisons

fertilizer

example split plot

Fibonacci series

function using while

fig

split the plotting region

file

connections

reading dates and times

saving a list

saving graphics

file.exists

check existence

file.path

file paths

file delimitors

file name

file.exists

paste

file paths

dirname

file.path

introduction

paste

setwd

fill

colour in barplot legend

colour in legends

legend in a double barplot

fill colour

boxfill

filled.contour

illustration

three-dimensional plots

find

locate a package

find nearest neighbours

nnwhich

first character with grep

∧

first-order autoregressive process

time series

first-order compartment

non-linear models

first-order compartment model

SSfol

first-order neighbours

definition

first-order non-linear difference equation

quadratic map

first subscript

row

first things first

data exploration

fisher.test

Fisher's exact test

matrix of Mendel's peas

Fisher's exact test

contingency tables

fisher.test

Fisher's F distribution

distribution

F

shape of the density function

Fisher's F test

comparing two variances

var.test

fit

measuring the degree of scatter using r²

fit all the explanatory variables

dot . convention

fit perfect

saturated model

fitted

extracting information from model objects

for model objects

fitted values

patterns in residuals

str of linear model

fitted values and residuals

model-checking plot

fivenum

for residuals

summary for single samples

Tukey's five number summary

fix

data editing function

fixed

lme

fixed effects

background

introduction

fixed-effect meta-analysis of scaled differences

example

fixed or random

deciding on categorical variables

fixed versus random effects

meta-analysis

flat tables for output

ftable

fligner.test

comparing several variances

comparing two variances

test before ANOVA

Fligner–Killeen test

comparing several variances

floor

greatest integer less than

fluctuations

advantages of logarithms

font

changing screen default settings

font.axis

font to be used for axis annotation

font.lab

font to be used for x and y labels

font.main

font to be used for plot main titles

font.sub

font to be used for plot subtitles

font families for text

HersheySymbol

mono

sans

serif

font to be used for axis annotation

font.axis

font to be used for plot main titles

font.main

font to be used for plot subtitles

font.sub

font to be used for x and y labels

font.lab

foreground colours

axes and boxes

forest

forest plot

forest plot

forest

output from meta-analysis

random-effects meta-analysis of binary data

F or FALSE

for loop

drawing multiple lines

introduction

population dynamics

with sapply for simulating dynamics

form feed

"\f"

form=∼latitude+longitude

spatial errors in gls

format

complex mathematical expressions

for input and output

formatted output

cat

formatting of axis labels with complex characters

expression

formulae

model specification

Fortran

interface to compiled code

fourfoldplot

UCBAadmissions

four parameter

logistic

four-parameter logistic model

SSfpl

fractional powers

introduction

fractions

TEX-like rules

frame

environments in R

evaluation frame

F ratio

ANOVA table for regression

extracting from summary(model)

freedom

see d.f.

frequencies

comparing data with a Poisson distribution

contingency tables

count data

frequency domain

spectral analysis

frequentist approach

likelihood of the data given our model

maximum likelihood

from

sequence generation

the name of the table containing related variables in SQL

ftable, 3-dimensional contingency table

flat tables for output

Schoener's lizards

with the quine data

F test

in one-way ANOVA

introduction

function

anonymous functions

central

charplot

ci95

draw using curve

error.bars

exit using stop

factorial

harmonic mean

introduction

lists for arbitrary arguments

many.means

returning values from

standard error of a mean

switch

variance

vector functions

xy.error.bars

functions worked examples

example