Vignettemods

DESCRIPTION

@@ -16,7 +16,7 @@ Description: A simple way of fitting detection functions to distance sampling
     Horvitz-Thompson-like estimator) if survey area information is provided. See
     Miller et al. (2019) <doi:10.18637/jss.v089.i01> for more information on
     methods and <https://examples.distancesampling.org/> for example analyses.
-Version: 2.0.0.9005
+Version: 2.0.0.9006
 URL: https://github.com/DistanceDevelopment/Distance/
 BugReports: https://github.com/DistanceDevelopment/Distance/issues
 Language: en-GB

vignettes/lines-distill.Rmd

@@ -41,7 +41,7 @@ In this exercise, we use `R` [@r_core_team_r_2019] and the `Distance` package [@
 Nineteen line transects were walked twice (Figure \@ref(fig:fig)). 
 
 ```{r fig, echo=FALSE, fig.cap="Montrave study area; diagonal lines indicate line transects walked to generate these data.", outwidth='100%', eval=TRUE}
-knitr::include_graphics("montrave.JPG")
+knitr::include_graphics("montrave.jpg")
 ```
 
 The fields of the `wren_lt` data set are:

vignettes/species-covariate-distill.Rmd

@@ -34,7 +34,7 @@ options(kableExtra.html.bsTable = TRUE)
 
 Sometimes the focal species of a distance sampling survey is quite rare.  So rare that it is difficult to accumulate sufficient detections to fit a detection function for the species in question.  Likewise, it is also common for other species to be detected during the survey for the focal species.  Could the detections of the other species be useful in estimating a detection function for the focal species?
 
-One approach might be to consider the species to serve as "strata" and proceed to analyse the data as if they were from a stratified survey.  See the [example for stratified survey analysis](http://distancesampling.org/Distance/web-only/strata/strata-distill.html).  However, if a pooled detection function (one that combines data from multiple species) is fitted, it would be dubious to apply this pooled detection function to data at a lower level of aggregation (species level).  Applying the pooled detection function would lead to a biased estimate of abundance for the rare species.
+One approach might be to consider the species to serve as "strata" and proceed to analyse the data as if they were from a stratified survey.  See the [example for stratified survey analysis](https://distancesampling.org/Distance/articles/web-only/strata/strata-distill.html).  However, if a pooled detection function (one that combines data from multiple species) is fitted, it would be dubious to apply this pooled detection function to data at a lower level of aggregation (species level).  Applying the pooled detection function would lead to a biased estimate of abundance for the rare species.
 
 Instead of treating species as strata, an alternative form of analysis is to treat species as a covariate in the modelling of the detection function [@FMARBUC03].  The principle is that the general key function is shared across species, but the scale parameter $(\sigma)$ differs between species.  In this way, the detections of all species is shared, such that the estimation of the detection function for the rare species is bolstered by information from other species; yet the rare species receives its own *unique* detection function such that bias is not induced in the abundance estimation for that species.