| Title: | Regression by Composition |
| Version: | 0.1.0 |
| Description: | Flexible statistical modelling using a modular framework for regression, in which groups of transformations are composed together and act on probability distributions. |
| License: | MIT + file LICENSE |
| Depends: | R (≥ 2.10) |
| Imports: | Formula, R6 |
| Suggests: | testthat (≥ 3.0.0) |
| Config/testthat/edition: | 3 |
| Encoding: | UTF-8 |
| LazyData: | true |
| RoxygenNote: | 7.3.2 |
| NeedsCompilation: | no |
| Packaged: | 2024-11-05 09:47:34 UTC; daniel |
| Author: | Daniel Farewell 
[aut, cre, cph],
Simon Schoenbuchner
[ctb] |
| Maintainer: | Daniel Farewell <farewelld@cardiff.ac.uk> |
| Repository: | CRAN |
| Date/Publication: | 2024-11-06 21:00:01 UTC |
Compute Akaike Information Criterion from a regression by composition
Description
Compute Akaike Information Criterion from a regression by composition
Usage
## S3 method for class 'RegressionByComposition'
AIC(object, ..., k = 2)
Arguments
object |
a RegressionByComposition object; usually the result of a call to rbc() |
... |
ignored |
k |
numeric, the penalty per parameter to be used; ‘k = 2’ is the classical AIC. |
Bernoulli distribution as a CompositeFamily
Description
Bernoulli distribution as a CompositeFamily
Usage
Bernoulli(prob = 0.5)
Arguments
prob |
the probability of a success |
Value
a new BinaryFamily object
Examples
dist <- Bernoulli()
dist$probability()
Lognormal distribution as a CompositeFamily
Description
Lognormal distribution as a CompositeFamily
Usage
LogNormal(meanlog = 0, sdlog = 1)
Arguments
meanlog |
the mean of the logarithm |
sdlog |
the standard deviation of the logarithm |
Value
a new ContinuousFamily object
Examples
dist <- LogNormal()
log(dist$quantile(0.95))
Moebius flow
Description
Moebius flow
Usage
Moebius
Format
An object of class Flow (inherits from R6) of length 6.
Normal distribution as a CompositeFamily
Description
Normal distribution as a CompositeFamily
Usage
Normal(mean = 0, sd = 1)
Arguments
mean |
the mean |
sd |
the standard deviation |
Value
a new ContinuousFamily object
Examples
dist <- Normal()
dist$quantile(0.95)
Power flow
Description
Power flow
Usage
Power
Format
An object of class Flow (inherits from R6) of length 6.
Scale flow
Description
Scale flow
Usage
Scale
Format
An object of class Flow (inherits from R6) of length 6.
ScaleOdds flow
Description
ScaleOdds flow
Usage
ScaleOdds
Format
An object of class Flow (inherits from R6) of length 6.
ScaleRisk0 flow
Description
ScaleRisk0 flow
Usage
ScaleRisk0
Format
An object of class Flow (inherits from R6) of length 6.
ScaleRisk1 flow
Description
ScaleRisk1 flow
Usage
ScaleRisk1
Format
An object of class Flow (inherits from R6) of length 6.
Translate flow
Description
Translate flow
Usage
Translate
Format
An object of class Flow (inherits from R6) of length 6.
TranslateRisk1 flow
Description
TranslateRisk1 flow
Usage
TranslateRisk1
Format
An object of class Flow (inherits from R6) of length 6.
Append a flow to a CompositeFamily object
Description
Append a flow to a CompositeFamily object
Usage
append_flow(family, flow)
Arguments
family |
a CompositeFamily object |
flow |
a Flow object |
Value
a new CompositeFamily object
Examples
append_flow(Normal(0, 1), Translate)
Reduce(append_flow, list(Scale, Translate), init = Normal(0, 1))
Extract regression coefficients from a regression by composition
Description
Extract regression coefficients from a regression by composition
Usage
## S3 method for class 'RegressionByComposition'
coef(object, ...)
Arguments
object |
a RegressionByComposition object; usually the result of a call to rbc() |
... |
ignored |
Compute fitted values from a regression by composition
Description
Compute fitted values from a regression by composition
Usage
## S3 method for class 'RegressionByComposition'
fitted(object, ...)
Arguments
object |
a RegressionByComposition object; usually the result of a call to rbc() |
... |
further arguments passed to the R6 method $fitted() associated with the model's CompositeFamily |
Extract log-likelihood from a regression by composition
Description
Extract log-likelihood from a regression by composition
Usage
## S3 method for class 'RegressionByComposition'
logLik(object, ...)
Arguments
object |
a RegressionByComposition object; usually the result of a call to rbc() |
... |
ignored |
Compute predicted values from a regression by composition
Description
Compute predicted values from a regression by composition
Usage
## S3 method for class 'RegressionByComposition'
predict(object, newdata, ...)
Arguments
object |
a RegressionByComposition object; usually the result of a call to rbc() |
newdata |
data.frame containing new data |
... |
further arguments passed to the R6 method $fitted() associated with the model's CompositeFamily |
Fit a regression by composition model
Description
Fit a regression by composition model
Usage
rbc(formula, init, flows, family, data, par, hessian = TRUE)
Arguments
formula |
a formula object, with model components separated by '|' |
init |
the initial distribution |
flows |
a list of flows |
family |
(optional) an object of class 'CompositeFamily'; if supplied, 'init' and 'flows' are ignored |
data |
a data frame |
par |
a vector of starting values |
hessian |
logical; use Hessian matrix in model fitting? |
Value
an rbc object
Examples
## Annette Dobson (1990)
## "An Introduction to Generalized Linear Models".
## Page 9: Plant Weight Data.
ctl <- c(4.17, 5.58, 5.18, 6.11, 4.50, 4.61, 5.17, 4.53, 5.33, 5.14)
trt <- c(4.81, 4.17, 4.41, 3.59, 5.87, 3.83, 6.03, 4.89, 4.32, 4.69)
dobson <- data.frame(
weight = c(ctl, trt),
group = gl(2, 10, 20, labels = c("Ctl", "Trt"))
)
dobson_fit <- rbc(weight ~ 1 | 1 + group,
init = Normal(0, 1),
flows = list(Scale, Translate),
data = dobson
)
starr_fit <- rbc(
height ~ 1 | 0 + I((280 + age)^(-1)) | 1 | 1,
init = LogNormal(),
flows = list(Power, Moebius, Scale, Translate),
data = subset(starr, id %in% unique(id)[1:10])
)
Compute 'residuals' from a regression by composition
Description
Compute 'residuals' from a regression by composition
Usage
## S3 method for class 'RegressionByComposition'
residuals(object, ...)
Arguments
object |
a RegressionByComposition object; usually the result of a call to rbc() |
... |
ignored |
Value
a vector of probabilities of the same length as the data
Growth from birth to 3 years in healthy babies in the US
Description
Growth from birth to 3 years in healthy babies in the US
Usage
starr
Format
starr
A data frame with 104,798 rows and 5 columns:
- id
Anonymized identifier
- sex
Sex of baby
- age
Age of baby, in days
- height
Jittered height of baby, in cm
- weight
Jittered weight of baby, in kg
...
Source
References
doi:10.1186/s12874-024-02145-1
Summary of a regression by composition
Description
Summary of a regression by composition
Usage
## S3 method for class 'RegressionByComposition'
summary(object, compact = FALSE, ...)
Arguments
object |
a RegressionByComposition object; usually the result of a call to rbc() |
compact |
logical; should coefficients from all flows be compressed into a single matrix? |
... |
ignored |
Extract variance-covariance matrix from a regression by composition
Description
Extract variance-covariance matrix from a regression by composition
Usage
## S3 method for class 'RegressionByComposition'
vcov(object, ...)
Arguments
object |
a RegressionByComposition object; usually the result of a call to rbc() |
... |
ignored |