Hi Brian,
Thank you very much for your response. I haven't tried the approach you
suggested yet, but it seems it does offer a great deal of flexibility.
So far, I looked into censored (MLE) regression as implemented via the function
cenreg in the NADA package.
Do you have any examples of R code that you would be able to point me to for
the quantreg() approach? Or know of any articles where this approach was used?
If yes, I would love to read up more on it.
I always get frustrated when I have to apply statistical methods originally
developed in the context of assessing trends in water quality parameters.
Their implementation in R
seems to be patchy and often reduced to cases where either no censoring is
present or there is a single censoring limit. If we start throwing in things
like seasonality, ties
within a season, temporal/seasonal correlation, data missigness, etc., things
get even more frustrating. I would imagine quantreg() itself may struggle with
correlation issues, for
example. There are some useful USGS packages out there, but many of them seem
to be "orphaned" so one feels a bit unsure about how reliable they are if they
are no longer
maintained.
Thank you again,
Isabella
Isabella R. Ghement, Ph.D.
Ghement Statistical Consulting Company Ltd.
301-7031 Blundell Road, Richmond, B.C., Canada, V6Y 1J5
Tel: 604-767-1250
E-mail: isabe...@ghement.ca
Web: www.ghement.ca
On Mon 28/01/19 2:50 PM , "Cade, Brian" ca...@usgs.gov sent:
> An alternative to consider would be to use the censored quantile
> regression option available in the quantreg package. This handles
> left or right censoring with or without multiple censoring values.
> You could just estimate the censored conditional median (0.50
> quantile) to provide an estimate similar to Mann-Kendall trend test,
> but have the option of estimating censored estimates for other
> quantiles that may provide additional insight to relationships if
> there is substantial heterogeneity. You would have to include the
> necessary predictors and functions to handle the seasonal adjustments
> but that should be quite doable. The censored quantile regression
> approach has much greater modeling flexibility (inclusion of other
> predictors, splines on predictors, etc) than the Mann-Kendall testing
> approach.
> Brian
>
> Brian S. Cade, PhD
> U. S. Geological SurveyFort Collins Science Center2150 Centre Ave.,
> Bldg. CFort Collins, CO 80526-8818
> email: cadebtel: 970 226-9326
> On Mon, Jan 28, 2019 at 1:00 PM wrote:
>
>
> BODY { font-family:Arial, Helvetica,
> sans-serif;font-size:12px; }
> Hi everyone,
> I am working on a project where I need to conduct non-seasonal and
> seasonal trend tests of multiply censored data (i.e., data with
> multiple detection
> limits).
> An old thread on this mailing list
> (http://r-sig-ecology.471788.n2.nabble.com/Seasonal-Mann-Kendall-with-multi
> ple-detection-limits-td7578991.html[3]
> [1])
> suggests that it is possible to perform these types of trend tests
> in
> R using functions from USGS packages:
> 1. USGSwsQW package has a function called
> kendallATS.test
> that performs a non-seasonal Mann-Kendall trend test;
> 2. restrend package has a function called censSeaken
> that
> performs a seasonal Kendall trend test.
> Now, I looked for the USGSwsQW package and couldn't find it.
> Instead, I found the USGS package smwrQW
> (https://rdrr.io/github/USGS-R/smwrQW/ [4]), [2] which
> includes the function kendallATS.test. The restrend package I
> could
> find and it does include the censSeaken function.
> The syntax of the kendallATS.test function is kendallATS.test(x, y,
> na.rm = TRUE), where in my case x will stand for year and y will be a
> concentration
> subjected to multiple detection limits. According to the help
> file,
> y needs to be 'any data that can be converted to a left-censored
> data
> object'.
> The USGS packages seem to have an as.lcens() function which would
> enable me to specify y as a left-censored vector of concentration
> values subjected to
> a single censoring limit. But they also have an as.mcens()
> function
> which would accept multiple censoring/detection limits.
> Initially, I thought that kendallATS.test would accept both lcens
> and
> mcens data values. But it only accepts lcens data values, so I am
> not
> sure
> whether we are supposed to somehow convert mcens to lcens data
> values
> prior to feeding them to kendallATS.test? If we are supposed to do
> this
> conversion, I am also not sure how the conversion should work as
> far
> as as.lcens is concerned.
> As an example, if y consists of the values "
> Links:
> ------
> [1]
> http://r-sig-ecology.471788.n2.nabble.com/Seasonal-Mann-Kendall-with-multip
> le-detection-limits-td7578991.html[5]
> [2] https://rdrr.io/github/USGS-R/smwrQW/ [6]),
> [3] mailto:
> [4] http://sitemail.wvthosting.com/ [8]
>
> Links:
> ------
> [3]
> http://r-sig-ecology.471788.n2.nabble.com/Seasonal-Mann-Kendall-with-multip
> le-detection-limits-td7578991.html[4] https://rdrr.io/github/USGS-R/smwrQW/
> [5]
> http://r-sig-ecology.471788.n2.nabble.com/Seasonal-Mann-Kendall-with-multip
> le-detection-limits-td7578991.html[6] https://rdrr.io/github/USGS-R/smwrQW/
> [8] http://sitemail.wvthosting.com/
> [10] https://stat.ethz.ch/mailman/listinfo/r-sig-ecology
>
>
_______________________________________________
R-sig-ecology mailing list
R-sig-ecology@r-project.org
https://stat.ethz.ch/mailman/listinfo/r-sig-ecology
