Re: [R] Time series (trend over time) for irregular sampling dates and multiple sites

[Abs Spurdle]

This is possibly off topic now...
However, given that it involves mgcv, I think that it's relevant to R.

> to test if there is a change over the years on the amount of debris in
these locations and more specifically a change after the implementation of
a mitigation strategy

> My debris items per effort (Ieffort) are fishing and shipping related
items that can be due to an intentional discharge or an accidental
discharge. It is very common to find a great amount of these items together
in the beach (from where we collected these data (beach clean-ups),
possibly having origin from the same ship. I was thinking that this can be
a problem but still don't know how to overcome or if it makes sense to
include in the model.

I could be wrong on this.
If your goal is simply to determine whether the MARPOL term in significant
or not (or how strong the effect is), I don't think the above issue is
important.
However, you could do a separate spatial analysis, which could be very
interesting...

> This does not apply along the different years.

Are you sure (there's no long term effect)?
Note that you could combine Year and nMonth into one variable, say t.
However, if I understand your variables correctly, this would be correlated
with DaysIa.
So, if you try to fit a model with both Year and DaysIa, then Year is less
likely to be significant, and you probably don't need both.

Note that another approach, is to regard month as a categorical variable.

Also, note that it may be worthwhile testing for interactions, between
MARPOL and Location or Site.
If you want to be fancy, you could test for interactions between MARPOL and
your time variables.

It's possible that there are higher order interactions, however, these sort
of models are difficult for most people to interpret, so are probably a bad
idea.

[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

Re: [R] Time series (trend over time) for irregular sampling dates and multiple sites

[Abs Spurdle]

> > My data has a few problems: (1) I think I will need to fix the effects
of
> > seasonal variation (Monthly) and (2) of possible spatial correlation
> > (probability of finding an item is higher after finding one since they
can
> > come from the same ship). (3) How do I handle the fact that the
> > measurements were not taken at a regular interval?
>
> Can I ask two questions:
> (1) Is the data autocorrelated (or "Seasonal") over time?
> If not then this problem is a lot simpler.
> (2) Can you expand on the following statement?
> "possible spatial correlation (probability of finding an item is higher
after finding one since they can come from the same ship"

I just had a closer look at your example.

You've tried to model nMonth (presumably in {1, 2, ..., 12}) but is there a
long term trend, over Year?
Also, I'm not an expert on mgcv, but I was wondering if you want bs="cp"
rather than bs="ps"?

When you say "measurements were not taken at a regular interval" are you
referring to the variable "DaysIa"?
In which case, my previous question about autocorrelation applies to this
variable.

[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

Re: [R] Time series (trend over time) for irregular sampling dates and multiple sites

[Abs Spurdle]

> My data has a few problems: (1) I think I will need to fix the effects of
> seasonal variation (Monthly) and (2) of possible spatial correlation
> (probability of finding an item is higher after finding one since they can
> come from the same ship). (3) How do I handle the fact that the
> measurements were not taken at a regular interval?

Can I ask two questions:
(1) Is the data autocorrelated (or "Seasonal") over time?
If not then this problem is a lot simpler.
(2) Can you expand on the following statement?
"possible spatial correlation (probability of finding an item is higher
after finding one since they can come from the same ship"

[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

Re: [R] Time series (trend over time) for irregular sampling dates and multiple sites

[Bert Gunter]

I have 0 expertise, but I suggest that you check out the SPatioTemporal
taskview on CRAN (or possibly others, like environmetrics). You might also
want to move this to the R-Sig-geo list,where you probably are more likely
to find relevant expertise.

Cheers,
Bert

Bert Gunter

"The trouble with having an open mind is that people keep coming along and
sticking things into it."
-- Opus (aka Berkeley Breathed in his "Bloom County" comic strip )


On Tue, Apr 30, 2019 at 8:13 AM Catarina Serra Gonçalves <
catarin...@gmail.com> wrote:

> I have a dataset of marine debris items (number of items standardized per
> effort: Items/(number of volunteers*Hours*Lenght)) taken from 2 main
> locations (WA and Queensland) in Australia (8 Sub Sites in total: 4 in WA
> and 4 in Queensland) at irregular sampling intervals over a period 15
> years.
>
> I want to test if there is a change over the years on the amount of debris
> in these locations and more specifically a change after the implementation
> of a mitigation strategy (in 2013).
> Here’s the head of the data:[image: enter image description here]
> Description of each one of the
> varables in the dataframe:
>
> *eventid *= each sampling (clean-up) event Location = Queensland and New
> South Wales Sites = all the 9 sampling beaches
>
> *Date *= specific dates for the clean-up events (day-month-year)
>
> *Date1 *= specific dates for the clean-up events (day-month-year) on the
> POSICXT format Year= Year of sampling event (2004 to 2018)
>
> *Month*= Month of the sampling event (jan to dec)
>
> *nMonth*= a number was determined to the respective month of the sampling
> event (1 to 12)
>
> *Day*= Day of sampling (1 to 31) Days = Days since the first date of clean
> up = just another way of using the dates
>
> *MARPOL *= before and after implementation (factor with 2 levels)
>
> *DaysC *= days between sampling events for the same sites = number of days
> since the previous clean-up event
>
> *DaysI *= Days since intervention, all the dates before implementation are
> zero, and after we count the number of days since the implementation date
> (1 jan 2013)
>
> *DaysIa*= same as DayI but instead of zero for before the intervention we
> have negative values (days)
>
> *Items *= number of fishing and shipping items counted in each clean-up
> event
>
> *Hours *= hours spent by all volunteers together at each clean up event
>
> *Lenght *= Lenght of beach sampled by all volunteers together at each clean
> up event volunteers = all volunteers at each clean up event
>
> *HoursVolunteer *= hours spent bt each volunteer at each clean up event
> (Hours/volunteers)
>
> *Ieffort *= the items standarized by the effort (hours, volunteers and
> lenght)
>
> *GrossWeight & **GrossTotal are not relevant *
> --
> Problems:
>
> My data has a few problems: (1) I think I will need to fix the effects of
> seasonal variation (Monthly) and (2) of possible spatial correlation
> (probability of finding an item is higher after finding one since they can
> come from the same ship). (3) How do I handle the fact that the
> measurements were not taken at a regular interval?
>
> I was trying to use GAMs to analyse the data and see the trends over time.
> The model I came across is the following:
>
> m4<- gamm(Ieffort ~ s(DaysIa)+MARPOL+ s(nMonth, bs = "ps", k = 12),
> random=list(Site=~1,Location=~1),data = d)
>
> *thank you in advance.*
> -
> *Catarina Serra Gonçalves *
> PhD candidate
>
> Adrift Lab  
> University of Tasmania  | Institute for Marine
> and
> Antarctic Studies  
> Launceston, TAS | Australia
>
> Personal website 
> | E-mail   |
> Twitter 
> Research Gate
>  | Google
> Scholar 
>
> [[alternative HTML version deleted]]
>
> __
> R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>

[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.