## About

36

Publications

2,256

Reads

**How we measure 'reads'**

A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more

239

Citations

Citations since 2016

Introduction

Kim Iles is a consultant in Forest Biometrics, specializing in Variable Plot and 3P sampling on the West Coast of North America. He does research in statistical techniques for forest inventory.
Email is kiles@island.net .
He is presently working on his 4th book on forest inventory. His website is currently shut down due to provider problems, but you can email him to order books. Phone is 250 616-1413.
Examples of the 3 books are available under "research".

## Publications

Publications (36)

Sector plots are fixed-angle “sector-shaped” samples of objects, typically in small irregular polygons, with a central ray extending from sector vertex or pivot point to polygon boundary. If the number of objects in the sector plot is very high, a subsample may be used. The sector angle can be reduced, or small fixed-area “subplots” can be installe...

This note gives a short discussion about using models with or without correction by field measurements in forest inventory. While modelling with LiDAR may be tempting, the author would argue that these inherently limited models are best used for their ability to distribute overall totals after the factor to assist a more general unbiased inventory...

Most sampling in Forest Inventory is Geometry, either Plane or Solid geometry and growth through time is related as well. The probabilities from their geometry connect each of them to statistics, but probabilities and equations are a poor way to see the relationships. These 3 sampling systems are based on the same concept - a base area, with sample...

A Sampler of Inventory Topics (third edition, 2015, hardback, Dark brown bonded leather) 869 pages, 17 chapters (the last 2 on Regression and Hypothesis Testing on an included CD which also includes EXCEL examples and useful calculations). The book covers the major sampling methods used in forestry, statistics, tree measurements, etc. Variable plot...

Sector sampling is a new and simple approach to sampling objects or borders. This approach would be especially useful for sampling objects in small discrete areas or "polygons" with lots of internal or external edge, but it may be extended to sampling any object regardless of polygon size. Sector plots are wedge-shaped with a fixed sector angle. Th...

Because different tree parameters are of differing importance, and have different variability, efficiency in sampling would suggest that some of the principle variables be subsampled. One convenient way to do this is to sample different numbers of items at the same sample locations. This paper is a review of some current techniques in subsampling f...

The Retread, The Reject, and the Tower Statistician. 417 pages, hardback, light brown bonded leather. Similar to the second book in style, but more material in 61 chapters. Practical issues in forest inventory and professional development. EXCEL examples are included.
The book can be ordered or questions answered by email at kiles@island.net. It...

This is a short research note with an illustrative example describing the bias inherent in the nearest neighbor method. © 2010 Publisher of the International Journal of Mathematical and Computational Forestry & Natural-Resource Sciences.

The use of "nearest-neighbor" sampling has a long history. It involves measuring the distance from a random point in an area to the nearest object. That history involves never quite solving the problem, many examinations of special cases that never occur, adjustments that were ad-hoc, and a great deal of uninformative algebra. In forestry we have a...

I describe here a method that can provide unbiased estimates and sampling errors with increasingly precise polygon information from non-sample sources that are often free and readily available. This method is extremely flexible, and it appears to be in line with the main trend of modern sampling - you first estimate using any information available,...

The Compassman, The Nun, and the Steakhouse Statistician. 359 pages, hardback, dark green bonded leather. 38 short chapters about practical measurement issues and professional development in Forest Biometrics. The longer 2 final chapters from the first book are reprinted here for reading convenience. The first few chapters are reprinted at the webs...

Sector sampling is designed to sample objects in clusters or small, irregularly shaped polygons, such as variable retention patches and associated harvested areas. A number of statistical aspects of sector sampling were examined by using real data and a resampling framework. When the sector angle is selected at random, the probability of sampling e...

The estimation procedure described is a simple technique that is applicable to virtually any plot-based sampling method and virtually any measured variable. It can be retrofitted to any existing fixed or variable plot over time by simply knowing the distance from the sampled object to the sample point. These estimators are illustrated for sampling...

The sampling method presented here uses a new type of plot, with surprising characteristics. Although useful in sampling any grouping of objects, it is illustrated here by correctly sampling small patches of trees remaining after harvest. Small patches are difficult to sample unbiasedly because of the “edge effect” caused by sampling with fixed or...

An unbiased direct estimator of total basal area for a stand is presented; stand area need not be known. Sampling can use horizontal point samples or fixed-area plots distributed on a regular grid or randomly selected. The sample space extends beyond the stand boundary. The estimator for basal area makes no distinction between plots whose centers a...

Variable plot sampling has been widely used for many years. It was recognized, early in its application, that the process of getting stand volume could be divided into two components, counting trees to get basal area per unit area and measuring trees to get volume/basal area ratios (VBARs). It was further recognized that these two components had di...

This is a publication specific to British Columbia timber cruising techniques and the need for future changes.

This is a short article about the mechanics and advantages of sampling from a sorted list, which is particularly efficient when you have previous or relative values available on a database. This form of Systematic Sampling can be very efficient.

Designing a large multiresource inventory is horribly difficult, it is not work for faint hearts, and the 250,000,000-acre size of British Columbia is not a trivial problem. Completion of the details (as opposed to stopping the work) is a process prone to collapse. After that point, implementation is also likely to fail. There have been some change...

Comments made during the gathering in honor of Lew Grosenbaugh in Gainsville Florida.

Come cautions about technology and the design of forest inventories

For those who have an interest in the history of individual sampling methods, these are two articles from the John Bell Newsletter, including the first article describing BigBAF sampling and possible alternative selection methods. Those who do practical sampling might find the newsletter to be of interest. It is still available on the Internet, and...

The problem is quite simple, covered completely by the one page DOI attached - you simply split the plot and randomly choose one half, then double the result. You can divide the plot into more than one part as well, if you wish. The division does not have to be exactly equal. The issue arose in Variable Plot sampling, leading to "switching prisms"...

Conference proceedings article reviewing Critical Height Sampling up to that time

Changing the basal area factor in variable plot or angle count sampling to give tree counts in an acceptable range is biased. The very reasonable sounding assumption that changing basal area factors will cause an inverse and proportional change in tree count will "prove" that there is no bias, but this assumption is not likely to be true in actual...

A system for graphically comparing multivariate similarity between a large number of sample plots is presented. Two-dimensional nonmetric (rank order) multidimensional scaling is used to generate maps. These maps display either stand variables (site index, basal area, normality (used as a measure of stocking), change in normality, age and stems per...

Detailed measurements on approximately 900 "borderline trees" verified that professional cruisers are precise in their use of wedge prisms, and that errors cancel. The fact that trees are not round gives variable plots that are not round but of the correct size. Noncancelling errors were mostly due to steep slope corrections and difficulty in seein...

Estimating growth from Variable Plots

This paper show how to decide the numbers of tree counts and tree measurements in Variable Plot Sampling. A spreadsheet for this is available on the John Bell & Associates
Inventory & Cruising Newsletter.

Some algebra helps show how five different means can be included on one figure.

This is the first widely available paper on my work with Critical Height Sampling, along with some history of the technique.

The root mean square will add to your repertoire of means from the Maor article.

## Projects

Project (1)