Skip to Main Content
Comparison of Imputation Procedures for Replacing Denied-access PlotsAuthor(s): Susan L. King
Source: In: McRoberts, Ronald E.; Reams, Gregory A.; Van Deusen, Paul C.; McWilliams, William H.; Cieszewski, Chris J., eds. Proceedings of the fourth annual forest inventory and analysis symposium; Gen. Tech. Rep. NC-252. St. Paul, MN: U.S. Department of Agriculture, Forest Service, North Central Research Station. 155-162
Publication Series: General Technical Report (GTR)
Station: North Central Research Station
PDF: Download Publication (479.82 KB)
DescriptionIn forest inventories, missing plots are caused by hazardous terrain, inaccessible locations, or denied access. Maryland had a large number of denied-access plots in the latest periodic inventory conducted by the Northeastern Forest Inventory and Analysis unit. The denial pattern, which can introduce error into the estimates, was investigated by dropping the 1999 denied-access plots in the 1986 periodic inventory. The denied-access plots represented the population in terms of percentages of forest and nonforest, ownership, land use, and cubic-foot volume. Board-foot volume was less representative. Several single imputation group means??Euclidean type? distance measures, multiple regression imputation, and listwise deletion with the adjustment of the stratum weights?are compared for estimating the missing cubic- and board-foot volume on forest land. Information on the forested condition of the denied-access plot can be found only through photointerpretation (PI) or satellite imagery such as Multi-Resolution Land Characteristics, (MRLC). Results were inconclusive following an examination of the standard and sampling errors for the state or the root mean square errors for the denied-access plots. As a result, 2 to 12 percent of the data in increments of 2 percent were dropped randomly in a simulation study; the missing plot attributes estimated using each technique. The best simulation study procedure for PI-based forest/nonforest stratification is PI stratum classification. The best simulation study procedure for satellite-based forest/nonforest stratification is the listwise deletion alternative.
- Check the Northern Research Station web site to request a printed copy of this publication.
- Our on-line publications are scanned and captured using Adobe Acrobat.
- During the capture process some typographical errors may occur.
- Please contact Sharon Hobrla, firstname.lastname@example.org if you notice any errors which make this publication unusable.
- We recommend that you also print this page and attach it to the printout of the article, to retain the full citation information.
- This article was written and prepared by U.S. Government employees on official time, and is therefore in the public domain.
CitationKing, Susan L. 2005. Comparison of Imputation Procedures for Replacing Denied-access Plots. In: McRoberts, Ronald E.; Reams, Gregory A.; Van Deusen, Paul C.; McWilliams, William H.; Cieszewski, Chris J., eds. Proceedings of the fourth annual forest inventory and analysis symposium; Gen. Tech. Rep. NC-252. St. Paul, MN: U.S. Department of Agriculture, Forest Service, North Central Research Station. 155-162
- Stratifying to reduce bias caused by high nonresponse rates: A case study from New Mexico’s forest inventory
- A comparison of stratification effectiveness between the National Land Cover Data set and photointerpretation in western Oregon
- Comparing Forest/Nonforest Classifications of Landsat TM Imagery for Stratifying FIA Estimates of Forest Land Area
XML: View XML