Sampling in iTree

1
Sampling in i-Tree

• Concepts, techniques and applications

2
Introduction

• Sampling is so pervasive in
• i-Tree that we have factored it out for a
  separate discussion
• Overview
• Concepts
• Techniques
• Applications

3
Concepts I

• Random sample
• Data collection in which every member of the
  population has an equal chance of being selected
• Population the set of people or entities to
  which findings are to be generalized.
• The population must be defined explicitly before
  a sample is taken
• Can sometimes break population into subgroups
  (stratification) for better numbers
• Mind tricks easily, so need rigorous method

4
Source http//www.negrdc.org/counties/madison/com
prehensive-plans/newcomp/maps/8_01ExistLandUseMadi
sonCo.jpg
5
Concepts II

• Variance
• (SD)2
• Measure of how spread out the distribution is,
  i.e., how much individual samples vary
• The less the individual measurements vary from
  the mean (average), the more reliable the mean
• In an urban forest, different traits to
  investigate (variables) may have different
  variances
• Species distribution (high?) vs. population size
  (low)
• Hurricane debris (high?) vs. ice storm debris
  (low)

6
Source Dave Nowak and Jeff Walton, personal
communication (DRG data)
7
Concepts III

• Sample size
• Will need to be larger
• the weaker the relationships to be detected
• the higher the significance level being sought
• the smaller the population of the smallest
  subgroup
• the greater the variance of the variables
• Can be smaller as these factors change,
  especially as variance goes down

8
Source Dave Nowak, personal communication
9
Concepts IV

• Standard error (SEM)
• The Standard Error (Standard Error of the Mean)
  calculates how accurately a sample mean estimates
  the population mean.
• Formula SEM SD/?N , where SD standard
  deviation of the sample, and N sample size.
• Note that as SD goes down or N goes up, SEM gets
  smalleri.e., estimate becomes better.
• Commonly represented by after a number.

10
(No Transcript)
11
Source blogaloutre http//www.ontabec.com/fatigue
.jpg
12
Techniques I

• Get random numbers
• Tables
• Telephone book (final digits!)
• Electronic randomizers
• Online
• Desktop
• PDA

13
Techniques II

• Select plots
• Use map techniques
• Grid overlay for maps/photos
• Simple edge rulers also work
• Pick randomly from list
• Street, with replacement
• Block number
• Create random coordinates
• Spreadsheet
• GIS

14
Techniques II

• Easy way to get random list of street segments
• Bring TIGER/Line files as shape file from ESRI
  into a GIS
• Details in Appendix B of the Manual

15
Techniques III

• Reserve
• Create more plots than needed
• Something like 10
• Take replacements from list in order when plot
  must be thrown out
• Non-existent
• Unfindable
• Inaccessible
• No bias!

16
Application I

• Inventory types
• Complete Inventory
• Costly, time-consuming
• Partial Inventory
• Complete inventory of some forest segment
• Sample Inventory
• Randomly-selected trees inventoried for
  large-scale interpretation
• Cost-efficient
• Good for planning
• Not suitable for day-to-day field management

17
Application I

• Sample inventory benefits
• Increase public safety
• Facilitate short- and long-term planning
• Improve public relations
• Justify budgets
• Estimate tree benefits
• Large gain for small investment
• i-Tree promotes the value of sampling

18
Applications II

• Manual sampling techniques valid, but tedious for
  larger areas
• i-Tree v. 1.0 will include applications to
  automate the process for two types of plots
• Linear (street) plots/segments
• STRATUM/MCTI, SDAP
• Spatial (park, any area) plots
• UFORE

19
Applications II

• Linear plot selector
• STRATUM/MCTI
• SDAP
• Final testing
• Requirements
• ArcMap 8.3 or 9.0
• Polygon file delimiting study area boundary
• Road shape file (TIGER/Line data)

20
(No Transcript)
21
Applications II

• Spatial plot selector
• UFORE
• Final testing
• Requirements
• ArcMap 8.3 or 9.0
• Polygon file delimiting study area boundary
• Raster-based file of strata (e.g., land uses)
  within study area
• Digital aerial photos (optional)

22
(No Transcript)
23
Final sampling thoughts

• Sampling is our friend
• Both tool and product in i-Tree
• Understanding of validity of what i-Tree offers
  will depend critically on understanding the
  process and capability of sampling