# rhohat

##### Smoothing Estimate of Covariate Transformation

Computes a smoothing estimate of the intensity of a point process, as a function of a (continuous) spatial covariate.

##### Usage

```
rhohat(object, covariate, ...,
method=c("ratio", "reweight", "transform"),
smoother=c("kernel", "local"),
dimyx=NULL, eps=NULL,
n = 512, bw = "nrd0", adjust=1, from = NULL, to = NULL,
bwref=bw,
covname, confidence=0.95)
```

##### Arguments

- object
- A point pattern (object of class
`"ppp"`

), a quadrature scheme (object of class`"quad"`

) or a fitted point process model (object of class`"ppm"`

). - covariate
- Either a
`function(x,y)`

or a pixel image (object of class`"im"`

) providing the values of the covariate at any location. Alternatively one of the strings`"x"`

or`"y"`

signifying the Cartesian - method
- Character string determining the smoothing method. See Details.
- smoother
- Character string determining the smoothing algorithm. See Details.
- dimyx,eps
- Arguments passed to
`as.mask`

to control the pixel resolution at which the covariate will be evaluated. - bw
- Smoothing bandwidth or bandwidth rule
(passed to
`density.default`

). - adjust
- Smoothing bandwidth adjustment factor
(passed to
`density.default`

). - n, from, to
- Arguments passed to
`density.default`

to control the number and range of values at which the function will be estimated. - bwref
- Optional. An alternative value of
`bw`

to use when smoothing the reference density (the density of the covariate values observed at all locations in the window). - ...
- Additional arguments passed to
`density.default`

or`locfit`

. - covname
- Optional. Character string to use as the name of the covariate.
- confidence
- Confidence level for confidence intervals. A number between 0 and 1.

##### Details

If `object`

is a point pattern, this command assumes that
`object`

is a realisation of a Poisson point process with
intensity function $\lambda(u)$ of the form
$$\lambda(u) = \rho(Z(u))$$ where
$Z$ is the spatial covariate function given by `covariate`

,
and $\rho(z)$ is a function to be estimated.
This command computes estimators of $\rho(z)$
proposed by Baddeley and Turner (2005)
and Baddeley et al (2012).

The covariate $Z$ must have continuous values.

If `object`

is a fitted point process model, suppose `X`

is
the original data point pattern to which the model was fitted. Then
this command assumes `X`

is a realisation of a Poisson point
process with intensity function of the form
$$\lambda(u) = \rho(Z(u)) \kappa(u)$$
where $\kappa(u)$ is the intensity of the fitted model
`object`

. A smoothing estimator of $\rho(z)$ is computed.

The estimation procedure is determined by the character strings
`method`

and `smoother`

.
The estimation procedure involves computing several density estimates
and combining them.
The algorithm used to compute density estimates is
determined by `smoother`

:

- If
`smoother="kernel"`

, each the smoothing procedure is based on fixed-bandwidth kernel density estimation, performed by`density.default`

. - If
`smoother="local"`

, the smoothing procedure is based on local likelihood density estimation, performed by`locfit`

.

`method`

determines how the density estimates will be
combined to obtain an estimate of $\rho(z)$:
- If
`method="ratio"`

, then$\rho(z)$is estimated by the ratio of two density estimates. The numerator is a (rescaled) density estimate obtained by smoothing the values$Z(y_i)$of the covariate$Z$observed at the data points$y_i$. The denominator is a density estimate of the reference distribution of$Z$. - If
`method="reweight"`

, then$\rho(z)$is estimated by applying density estimation to the values$Z(y_i)$of the covariate$Z$observed at the data points$y_i$, with weights inversely proportional to the reference density of$Z$. - If
`method="transform"`

, the smoothing method is variable-bandwidth kernel smoothing, implemented by applying the Probability Integral Transform to the covariate values, yielding values in the range 0 to 1, then applying edge-corrected density estimation on the interval$[0,1]$, and back-transforming.

##### Value

- A function value table (object of class
`"fv"`

) containing the estimated values of $\rho$ for a sequence of values of $Z$. Also belongs to the class`"rhohat"`

which has special methods for`print`

,`plot`

and`predict`

.

##### Categorical and discrete covariates

This technique assumes that the covariate has continuous values.
It is not applicable to covariates with categorical (factor) values
or discrete values such as small integers.
For a categorical covariate, use
`quadratcount(X, tess=covariate)`

##### References

Baddeley, A., Chang, Y.-M., Song, Y. and Turner, R. (2012)
Nonparametric estimation of the dependence of a point
process on spatial covariates.
*Statistics and Its Interface* **5** (2), 221--236.
Baddeley, A. and Turner, R. (2005)
Modelling spatial point patterns in R.
In: A. Baddeley, P. Gregori, J. Mateu, R. Stoica, and D. Stoyan,
editors, *Case Studies in Spatial Point Pattern Modelling*,
Lecture Notes in Statistics number 185. Pages 23--74.
Springer-Verlag, New York, 2006.
ISBN: 0-387-28311-0.

##### See Also

##### Examples

```
X <- rpoispp(function(x,y){exp(3+3*x)})
rho <- rhohat(X, "x")
rho <- rhohat(X, function(x,y){x})
plot(rho)
curve(exp(3+3*x), lty=3, col=2, add=TRUE)
rhoB <- rhohat(X, "x", method="reweight")
rhoC <- rhohat(X, "x", method="transform")
fit <- ppm(X, ~x)
rr <- rhohat(fit, "y")
```

*Documentation reproduced from package spatstat, version 1.28-1, License: GPL (>= 2)*