1 Why Use Count Plots? A Comparison of Various Count to Measure Ratios In the BC Interior Presented by: Jim Wilson RFT, ATE May 2008.

Slides:



Advertisements
Similar presentations
Statistical Techniques I EXST7005 Start here Measures of Dispersion.
Advertisements

Statistical Process Control Used to determine whether the output of a process conforms to product or service specifications. We use control charts to detect.
Population Population
Lecture 7 Forestry 3218 Forest Mensuration II Lecture 7 Forest Inventories Avery and Burkhart Chapter 9.
A Simplifying Framework for an Introductory Statistics Class By Dr. Mark Eakin University of Texas at Arlington.
Statistical Concepts (part III) Concepts to cover or review today: –Population parameter –Sample statistics –Mean –Standard deviation –Coefficient of variation.
Error Propagation. Uncertainty Uncertainty reflects the knowledge that a measured value is related to the mean. Probable error is the range from the mean.
Statistics: The Science of Learning from Data Data Collection Data Analysis Interpretation Prediction  Take Action W.E. Deming “The value of statistics.
Survey Methodology Sampling error and sample size EPID 626 Lecture 4.
Sampling Designs Avery and Burkhart, Chapter 3 Source: J. Hollenbeck.
Statistics Stratification.
Chemometrics Method comparison
10-1Quality Control William J. Stevenson Operations Management 8 th edition.
Supporting Small Communities: Doubling the Small Community Grant Program Overview of the new grant allocation formula.
UFORE Overview and Process. What is UFORE? Science-based computer model that quantifies urban forest structure, functions, and values Collection of analysis.
Steps in Using the and R Chart
MGT-491 QUANTITATIVE ANALYSIS AND RESEARCH FOR MANAGEMENT OSMAN BIN SAIF Session 13.
Graphical Analysis. Why Graph Data? Graphical methods Require very little training Easy to use Massive amounts of data can be presented more readily Can.
Slide 1 Lecture 4: Measures of Variation Given a stem –and-leaf plot Be able to find »Mean ( * * )/10=46.7 »Median (50+51)/2=50.5 »mode.
Agronomic Spatial Variability and Resolution What is it? How do we describe it? What does it imply for precision management?
Sample size vs. Error A tutorial By Bill Thomas, Colby-Sawyer College.
Sampling Distributions
V 1.0 Carbon on the stump: how forest carbon inventories are verified and why it is important Western Mensurationists’ Meeting, June 2011 Banff, Alberta,
Quantitative Skills 1: Graphing
© 2003 Prentice-Hall, Inc.Chap 13-1 Business Statistics: A First Course (3 rd Edition) Chapter 13 Statistical Applications in Quality and Productivity.
Agronomic Spatial Variability and Resolution What is it? How do we describe it? What does it imply for precision management?
Comparing two sample means Dr David Field. Comparing two samples Researchers often begin with a hypothesis that two sample means will be different from.
Name: Angelica F. White WEMBA10. Teach students how to make sound decisions and recommendations that are based on reliable quantitative information During.
The Scientific Method Formulation of an H ypothesis P lanning an experiment to objectively test the hypothesis Careful observation and collection of D.
Regression Maarten Buis Outline Recap Estimation Goodness of Fit Goodness of Fit versus Effect Size transformation of variables and effect.
Vladyslav Kolbasin Stable Clustering. Clustering data Clustering is part of exploratory process Standard definition:  Clustering - grouping a set of.
1 Elizabeth McGarrigle Ph.D. Candidate University of New Brunswick Dr. John A. Kershaw University of New Brunswick.
Generic Approaches to Model Validation Presented at Growth Model User’s Group August 10, 2005 David K. Walters.
Sampling Distributions Chapter 7. The Concept of a Sampling Distribution Repeated samples of the same size are selected from the same population. Repeated.
Cruising Manual Highlights Ministry of Forests & Range 2009.
Nick Smith, Kim Iles and Kurt Raynor Partly funded by BC Forest Science Program and Western Forest Products Sector sampling – some statistical properties.
Internal Assessment Processing Data (aspects 2 & 3 of DCP)
1 Focus Last Change : June, 2003 C/Clients/Publications/p-plant.
6 - 1 © 1998 Prentice-Hall, Inc. Chapter 6 Sampling Distributions.
Issues in Estimation Data Generating Process:
Course Review FORE 3218 Course Review  Sampling  Inventories  Growth and yield.
ICCS 2009 IDB Workshop, 18 th February 2010, Madrid 1 Training Workshop on the ICCS 2009 database Weighting and Variance Estimation picture.
Data Collection & Sampling Dr. Guerette. Gathering Data Three ways a researcher collects data: Three ways a researcher collects data: By asking questions.
PPDAC Cycle.
IMPACT EVALUATION WORKSHOP ISTANBUL, TURKEY MAY
Copyright © 1998, Triola, Elementary Statistics Addison Wesley Longman 1 Assumptions 1) Sample is large (n > 30) a) Central limit theorem applies b) Can.
Agronomic Spatial Variability and Resolution What is it? How do we describe it? What does it imply for precision management?
Classification and Regression Trees
Understanding Your Data Set Statistics are used to describe data sets Gives us a metric in place of a graph What are some types of statistics used to describe.
RESEARCH METHODS Lecture 28. TYPES OF PROBABILITY SAMPLING Requires more work than nonrandom sampling. Researcher must identify sampling elements. Necessary.
Graphing Basics. Why do we graph? Visual representation of data “Short hand” for presenting large amounts of information at once Easier to visualize trends.
Data Screening. What is it? Data screening is very important to make sure you’ve met all your assumptions, outliers, and error problems. Each type of.
Line Charts (aka run charts, trend charts) Scott Davis QI Coordinator Tacoma Pierce County Health Department June 2012.
Cell Diameters and Normal Distribution. Frequency Distributions a frequency distribution is an arrangement of the values that one or more variables take.
Statistical Sampling. Sample  A subset of units selected from the population to represent it.  Hopefully it is representative.
Variable versus Fixed Costs
Nick Smith, Kim Iles and Kurt Raynor
Statistics Stratification.
Other Cruise Methods.
Agenda Review homework Lecture/discussion Week 10 assignment
The development of Variable Plot Sampling by Kim Iles
B.C. Ministry of Forests & Range – Revenue Branch Measure:Count / CGNF&LF Check Cruising Results Presentation to the Interior Timber Cruisers Spring.
CHAPTER 22: Inference about a Population Proportion
Sampling Distribution
Sampling Distribution
Sampling Distributions
DATABASE HISTOGRAMS E0 261 Jayant Haritsa
What Do You See? Message of the Day: Use variable area plots to measure tree volume.
Check Cruising Social : Science by Kim Iles : SITCA
Samples and Populations
Presentation transcript:

1 Why Use Count Plots? A Comparison of Various Count to Measure Ratios In the BC Interior Presented by: Jim Wilson RFT, ATE May 2008

2 Overview  Why are we sampling?  What are we sampling?  Why sample with count plots?  Variations of count plots  Study  Results  Recommendations

3 Why are we sampling?  Cost prohibitive to measure every tree  For appraisal purposes, we require cruise estimates to calculate the stumpage rate  Decision is based on:  What sampling error can we live with based on our budget?  unfortunately, the min 2SE is set for us

4 What are we sampling?  For appraisals – net volume ±15% 2SE  Sampling for net volume has two equal parts:  BA/ha (tree count)  VBAR (measure trees)  We could just as easily sample for any other attribute: $ value, stems/ha, etc.

5 What are we sampling? Questions:  Are the items to sample:  More or less variable?  More or less costly to collect?

6 Why sample with count plots?  More variability, more samples needed  Tree count is usually more variable than the measure trees  Counting trees is easy and cheap, measuring trees is costly  Measuring trees is 50% of the answer, getting tree count is the other 50%  You decide how much of each to sample

7 Variations of Count Plots

8  Which sample better covers the ground and covers the variability of the stand?  Selecting trees with a Big BAF better distributes measure trees – more efficient  Count:Measure plots clump measure trees into clusters – less efficient

9 Study  Selected 7 interior cutting permits  Northern and Southern Interior  Stand types: SB, FPyL, Pl(S)  All full measures:  Randomly selected plots to start  Ratios 0:1, 1:1, 2:1, 3:1, 5:1 (count:measure)  Graphed net vol/ha, ISR $/m3, cruising costs

10 Results : Net Vol/ha SB stand

11 Results: Stumpage Rate SB stand

12 Results : Net Vol/ha PlS stand

13 Results: Stumpage Rate PlS stand

14 Results Tree Count CV: SB stand: 0:1 – 5:1 86 plots - 39% PlS stand: 0:1 – 5:1 117 plots - 38%  Each of the runs by stand had the same number of plots and therefore the same CV

15 Results VBAR CV:  SB stand:  0:1 – 397 trees - 28%  1:1 – 195 trees - 28%  2:1 – 136 trees - 28%  3:1 – 107 trees - 29%  5:1 – 74 trees - 30%  PlS stand:  0:1 – 653 trees - 23%  1:1 – 337 trees - 24%  2:1 – 212 trees - 22%  3:1 – 161 trees - 24%  5:1 – 117 trees - 23%  Why are we measuring so many trees?

16 Results Trends :  Net vol/ha does not change using count plots  averaged within ± 2%  Stumpage rate does not change using count plots  averaged within ± 5%  CV is stable for VBAR (we are measuring too many!)  Cruising costs are 30% less using 1:1 ratio and 50% less using 5:1 ratio versus full measure plots

17 Results Optimal solution to reach 15% 2SE (using Kim Iles’ star_bar.xls): SB stand:  Using TC CV of 39% and VBAR CV of 28%  41 count plots & 41 VBAR trees  Equivalent to 3.5 counts to 1 measure plot PlS stand:  Using TC CV of 38% and VBAR CV of 23%  37 count plots & 31 VBAR trees  Equivalent to 7.2 counts to 1 measure plot

18 Recommendations  Use count plots in highly variable stands to meet sampling error (more counts)  Use count plots in homogenous stands to decrease effort (less measure trees)  Use count plots in partial reduction areas  Use Big BAF to select measure trees and increase efficiency  Use count plots and spread out the trees!

19 Acknowledgements Srdjan Kragulj, RPF Timberline - Vancouver  he helped provide all the stumpage calculations for each of the runs Kim Iles, PhD  for spoon feeding me time and time again  his STAR_BAR.xls program should be used by everyone to plan cruises John Bell, PhD  for his short course and newsletter ( Walter Bitterlich, PhD  for making cruising so much easier

20 Questions? Jim Wilson, RFT, ATE Cruise Compilation Manager Timberline Natural Resource Group Phone: Cell: