Specific Design Information - Lake Example
This section provides detailed information on creating GRTS Designs. In addition, a presentation; Monitoring Design: Component Details, by A.R. Olsen is available as a pdf file (2.5 MB)
The survey design is a plan for selecting the sample appropriately so that it provides valid data for developing accurate estimates for the entire population or area of interest. At this point in the design process it is assumed that the folloing have been completed:
- Established the monitoring objectives
- Identified Resource Characteristics
- Identified Institutional constraints requiring consideration
- Defined the target population
- Specified Subpopulations, Domains and Stratification
- Created a sampling frame for all units of the target population from which to select the sample
- Selected a GRTS survey design for the selection of sample of units from this frame
- Selected a strategy for allocation of sampling efforts in space and time
- Established sample size(s)
Additional information on each of these items is available on Design Specifics
New England Lakes Survey Design Example
Purpose: Illustrate GRTS survey designs for New England Lakes.
This information is presented as an example and recommended format for documenting a GRTS design. It is recommended that this example be followed, prior to initiating efforts to produce a design to meet a particular objective. Due to the randomization scheme within psurvey.design, each execution of the R code will produce a different set of sampling points and output files and will not exactly reproduce the example files.
Materials needed for this example:
- R version 2.2.1
- psurvey.design 2.2.1 + sp package
- R script or text file: NELakes Point Design.R
- Frame materials as ArcGis files:
- reg1_lakes.dbf
- reg1_lakes.prj
- reg1_lakes.sbn
- reg1_lakes.sbx
- reg1_lakes.shp
- reg1_lakes.shx
- Download Example Files
Example includes:
Designs | Description | Files produced |
1 | Equal Sites – 300 sites, equal wts | Equal Sites.dbf Equal Sites.prj Equal Sites.shp Equal Sites.shx |
2 | Stratified Sites – Stratification by State (n=50/State) No Oversample. |
Stratified Sites.dbf Stratified Sites.prj Stratified Sites.shp Stratified Sites.shx |
3 | Unequal Sites– Unequal probability of selection
by lake area (n=300) Oversample (n=120) |
Unequal Sites.dbf Unequal Sites.prj Unequal Sites.shp Unequal Sites.shx |
4 | Six Panels Over Time – Unequal probability based on
lake area (n=50/panel) Oversample (n=120) |
Panel Sites.dbf Panel Sites.prj Panel Sites.shp Panel Sites.shx |
Design File Documentation would routinely begin here:
Contact:
Nameaddress of person requesting the design
Voice:
Fax:
email:
Description of Sample Design
Survey Design: A Generalized Random Tessellation Stratified (GRTS) survey design for a lake resource is used for this example. Lake locations are given by the centroid. The GRTS design includes reverse hierarchical ordering of the selected sites.
Target population: All lakes and reservoirs within States of Ct, MA, ME, NH, RI, and VT.
Sample Frame: GIS Data originally from NHD. New England Lake Map
Sample Frame Summary
The number of lakes (13088) and reservoirs (85).
State | CT | MA | ME | NH | RI | VT |
Lakes & Reserviors | 2312 | 3305 | 4524 | 1725 | 504 | 803 |
area.cat (ha) | [0,1] | [1,5] | [5,10] | [10,50] | [50,500] | [500,70000] |
Lakes & Reserviors | 979 | 6070 | 2061 | 2673 | 1215 | 175 |
Frequency distribution by surface area.
I. Equal Probability GRTS Survey Design
Stratification: None
Expected sample size: 300 sites
Oversample: None
Site Use: The base design has 300 sites. Sites are listed in SiteID order and must be used in that order. All sites that occur prior to the last site used must have been evaluated for use and then either sampled or reason documented why that site was not used.
Site Selection Summary
States | Equal Sites |
CT | 51 |
MA | 75 |
ME | 103 |
NH | 40 |
RI | 11 |
VT | 20 |
Total | 300 |
Map of Equal Sites
Frequency distribution of equal sites by surface area
II. Stratified GRTS Survey Design
Stratification: Stratification by State, with equal probability selection within State.
Expected sample size: 50 sites per State, total 300 sites (see summary table).
Oversample: None.
Site Use: The stratified design has 300 sites. Sites are listed in SiteID order and must be used in that order. All sites that occur prior to the last site used must have been evaluated for use and then either sampled or reason documented why that site was not used.
Site Selection Summary
States | Equal Sites |
CT | 50 |
MA | 50 |
ME | 50 |
NH | 50 |
RI | 50 |
VT | 50 |
Total | 300 |
Map of Stratified Sites
Frequency Distribution of Stratified Sites by lake area
III. Unequal Probability GRTS Survey Design
Stratification: None, with unequal probabality of selection based on lake area
Expected sample size: 300 sites with approximate equal number of sites for lake area category.
Oversample: None.
Site Use: The unequal probability design has 300 sites. Sites are listed in SiteID order and must be used in that order. All sites that occur prior to the last site used must have been evaluated for use and then either sampled or reason documented why that site was not used.
Site Selection Summary
States | [0,1] | [1,5] | [5,10] | [10,50] | [50,500] | [500,70000] | Total |
CT | 25 | 8 | 10 | 7 | 3 | 0 | 53 |
MA | 10 | 11 | 15 | 12 | 10 | 2 | 60 |
ME | 6 | 17 | 13 | 18 | 34 | 41 | 129 |
NH | 2 | 7 | 6 | 6 | 8 | 3 | 32 |
RI | 0 | 5 | 1 | 2 | 1 | 0 | 9 |
VT | 2 | 4 | 4 | 1 | 3 | 3 | 17 |
Total | 45 | 52 | 49 | 46 | 59 | 49 | 300 |
Oversample | 20 | 22 | 25 | 17 | 21 | 15 | 120 |
Map of UnEqual Sites
Frequency distribution of unequal sites by lake area
IV. Panels for Surveys Over Time with Unequal Probability GRTS Design with Over Sample and Stratification.
Stratification: None. Unequal probability based on lake area with oversample, plus panel structure for survey over time.
Panels: Six panels: Annual, Year1, Year2, Year3, Year4, and Year5
Expected sample size: 50 sites per panel.
Oversample: 120 sites.
Site Use: The base design has 300 sites. Sites are listed in SiteID order and must be used in that order. All sites that occur prior to the last site used must have been evaluated for use and then either sampled or reason documented why that site was not used. As an example, if 250 sites are to be sampled, then the first 250 sites in SiteID order would be used.
Site Selection Summary
Annual | Year1 | Year2 | Year3 | Year4 | Year5 | Total | Oversample | |
[0,1] | 7 | 8 | 10 | 7 | 3 | 0 | 53 | 20 |
[1,5] | 10 | 11 | 15 | 12 | 10 | 2 | 60 | 24 |
[5,10] | 13 | 17 | 13 | 18 | 34 | 41 | 129 | 20 |
[10,50] | 3 | 7 | 6 | 6 | 8 | 3 | 32 | 17 |
[50,500] | 9 | 5 | 1 | 2 | 1 | 0 | 9 | 22 |
[500,70000] | 8 | 4 | 4 | 1 | 3 | 3 | 17 | 17 |
Total | 50 | 52 | 49 | 46 | 59 | 49 | 300 | 120 |
Map of Panel Sites
Frequency distribution of Panel sites by lake area