Estimation under a uniform detection function

[erex]

Question from the list Fitting a uniform without adjustments produces incorrect estimate of P_a, hence poor estimate of abundance

> library(Distance)
Loading required package: mrds
This is mrds 2.2.7
Built: R 4.2.1; ; 2022-08-22 23:51:25 UTC; windows

Attaching package: ‘Distance’

The following object is masked from ‘package:mrds’:

    create.bins

Warning messages:
1: package ‘Distance’ was built under R version 4.2.1 
2: package ‘mrds’ was built under R version 4.2.1 
> #unit conversion
> conversion.factor <- convert_units("meter", "meter", "hectare")
> #distance analysis
> dist.unif <- ds(data = distance_data, key = "unif", adjustment = "cos",
+                 truncation = "10%", convert_units = conversion.factor)
Starting AIC adjustment term selection.
Fitting uniform key function
AIC= 450.873
Fitting uniform key function with cosine(1) adjustments
AIC= 452.646

Uniform key function selected.
> summary(dist.unif)

Summary for distance analysis 
Number of observations :  45 
Distance range         :  0  -  149.86 

Model : Uniform key function 
AIC   : 450.8731 

Detection function parameters
Scale coefficient(s):  
NULL

                        Estimate
Average p           6.672895e-03
N in covered region 6.743700e+03

Summary statistics:
    Region   Area CoveredArea Effort  n  k          ER        se.ER     cv.ER
1 Creswell 296.02    454.0758  15150 45 21 0.002970297 0.0006246098 0.2102853

Abundance:
  Label Estimate      se        cv      lcl      ucl df
1 Total 4396.337 924.485 0.2102853 2848.694 6784.785 20

Density:
  Label Estimate       se        cv      lcl      ucl df
1 Total 14.85149 3.123049 0.2102853 9.623316 22.92002 20
> 1/149.86
[1] 0.006672895

stephanie.zip

[LHMarshall]

In fact the issue I discovered in mrds does appear to fix this also

[LHMarshall]

Tested with Stephanie's data and code and Pa is now 1:

> dist.unif <- ds(data = distance_data, key = "unif", adjustment = "cos",
+                 truncation = "10%", convert_units = conversion.factor)
Starting AIC adjustment term selection.
Fitting uniform key function
AIC= 450.873
Fitting uniform key function with cosine(1) adjustments
AIC= 452.646

Uniform key function selected.
> summary(dist.unif)

Summary for distance analysis 
Number of observations :  45 
Distance range         :  0  -  149.86 

Model : Uniform key function 
AIC   : 450.8731 

Detection function parameters
Scale coefficient(s):  
NULL

                    Estimate
Average p                  1
N in covered region       45

Summary statistics:
    Region   Area CoveredArea Effort  n  k          ER        se.ER     cv.ER
1 Creswell 296.02    454.0758  15150 45 21 0.002970297 0.0006246098 0.2102853

Abundance:
  Label Estimate       se        cv      lcl      ucl df
1 Total 29.33629 6.168991 0.2102853 19.00903 45.27416 20

Density:
  Label  Estimate         se        cv        lcl       ucl df
1 Total 0.0991024 0.02083978 0.2102853 0.06421537 0.1529429 20

[erex]

@LHMarshall you've likely been in touch with Stephanie and have tested your fix with her data. Will you contact her to say the fix has been implemented?