×

zbMATH — the first resource for mathematics

Alternative mean-squared error estimators for synthetic estimators of domain means. (English) Zbl 07281635
Summary: In forest management surveys, the mean of a variable of interest (\(Y\)) in a population composed of \(N\) equal area spatial compact elements is increasingly estimated from a model linking \(Y\) to an auxiliary vector \(\mathbf{X}\) known for all elements in the population. It is also desired to have synthetic estimates of the mean of \(Y\) in spatially compact domains (forest stands) with no or at most one sample-based observation of \(Y\). We develop three alternative estimators of mean-squared errors (MSE) that reduce the risk of a serious underestimation of the uncertainty in a synthetic estimate of a domain mean in cases where the employed model does not accounts for domain effects nor spatial autocorrelation in unobserved residual errors. Expansions of the estimators including anticipated effects of a spatial autocorrelation in residual errors are also provided. Simulation results indicate that the conventional model-dependent (MD) population-level estimator of variance in a synthetic estimate of a domain mean underestimates uncertainty by a wide margin. Our alternative estimators mitigated, in settings with weak to moderate domain effects and relatively small sample sizes, to a large extent, the problem of underestimating uncertainty. We demonstrate applications with examples from two actual forest inventories.
MSC:
62 Statistics
Software:
nlmdl
PDF BibTeX XML Cite
Full Text: DOI
References:
[1] J. Breidenbach, E. Kublin, R. McGaughey, H.-E. Andersen, and S. Reutebuch, Mixed-effects models for estimating stand volume by means of small footprint airbrone laser scanner data, Photogramm. J. Finland. 21 (2008), pp. 4-15.
[2] J. Breidenbach, R.E. McRoberts, and R. Astrup, Empirical coverage of model-based variance estimators for remote sensing assisted estimation of stand-level timber volume, Remote. Sens. Environ. 173 (2015), pp. 274-281. doi: 10.1016/j.rse.2015.07.026
[3] K.D. Brosofske, R.E. Froese, M.J. Falkowski, and A. Banskota, A review of methods for mapping and prediction of inventory attributes for operational forest management, Forest. Sci. 60 (2014), pp. 733-756. doi: 10.5849/forsci.12-134
[4] G. Casella, and R.L. Berger, Statistical Inference, 2nd ed., Duxbury Press, Pacific Grove, 2002.
[5] R.L. Chambers, and R.G. Clark, An Introduction to Model-based Survey Sampling with Applications, Oxford Statistical Science Series, Oxford University Press, New York, 2012.
[6] P. Corona, L. Fattorini, S. Franceschi, G. Chirici, F. Maselli, and L. Secondi, Mapping by spatial predictors exploiting remotely sensed and ground data: A comparative design-based perspective, Remote. Sens. Environ. 152 (2014), pp. 29-37. doi: 10.1016/j.rse.2014.05.011
[7] J. Costa e Silva, G.W. Dutkowski, and A.R. Gilmour, Analysis of early tree height in forest genetic trials is enhanced by including a spatially correlated residual, Can. J. Forest Res. 31 (2001), pp. 1887-1893. Available at http://www.nrcresearchpress.com/doi/abs/10.1139/x01-123 doi: 10.1139/x01-123
[8] M. Davidian, and R.J. Carroll, Variance function estimation, J. Amer. Statist. Assoc. 82 (1987), pp. 1079-1091. doi: 10.1080/01621459.1987.10478543 · Zbl 0648.62076
[9] H.J. De Knegt, F. van Langevelde, M.B. Coughenour, A.K. Skidmore, W.F. de Boer, I.M.A. Heitkönig, N.M. Knox, R. Slotow, C. van der Waal, and H.H.T. Prins, Spatial autocorrelation and the scaling of species-environment relationships, Ecology 91 (2010), pp. 2455-2465. Available at http://www.scopus.com/inward/record.url?eid=2-s2.0-77955460517&partnerID=40&md5=f37c225d44f6051181525adba4421178 doi: 10.1890/09-1359.1
[10] N.R. Draper and H. Smith, Applied Regression Analysis, 3rd ed., Wiley, New York, 2014.
[11] A.O. Finley, S. Banerjee, A.R. Ek, and R.E. McRoberts, Bayesian multivariate process modeling for prediction of forest attributes, J. Agr. Biol. Environ. St. 13 (2008), pp. 60-83. doi: 10.1198/108571108X273160 · Zbl 1306.62272
[12] W.A. Fuller, Sampling Statistics, Wiley, New York, 2009. · Zbl 1179.62019
[13] A.R. Gallant, Nonlinear Statistical Methods, Wiley, New York, 1987.
[14] M.E. Goerndt, V.J. Monleon, and H. Temesgen, Relating forest attributes with area- and tree-based light detection and ranging metrics for Western Oregon, West. J. Appl. For. 25 (2010), pp. 105-111.
[15] A. Grafström, S. Saarela, and L.T. Ene, Efficient sampling strategies for forest inventories by spreading the sample in auxiliary space, Can. J. Forest Res. 44 (2014), pp. 1156-1164. doi: 10.1139/cjfr-2014-0202
[16] T.G. Gregoire, Design-based and model-based inference in survey sampling: Appreciating the difference, Can. J. Forest Res. 28 (1998), pp. 1429-1447. doi: 10.1139/x98-166
[17] T.G. Gregoire, Q.F. Lin, J. Boudreau, and R. Nelson, Regression estimation following the square-root transformation of the response, Forest Sci. 54 (2008), pp. 597-606. Available at http://www.ingentaconnect.com/content/saf/fs/2008/00000054/00000006/art00004
[18] T.G. Gregoire, G. Ståhl, E. Næsset, T. Gobakken, R. Nelson, and S. Holm, Model-assisted estimation of biomass in a LiDAR sample survey in Hedmark county, Norway, Can. J. Forest Res. 41 (2010), pp. 83-95. doi: 10.1139/X10-195
[19] T.J. Hastie and R.J. Tibshirani, Generalized Additive Models, Chapman & Hall, London, 1990. · Zbl 0747.62061
[20] P. Holmgren, T. Thuresson, and S. Holm, Estimating forest characteristics in scanned aerial photographs with respect to requirements for economic forest management planning, Scand. J. Forest Res. 12 (1997), pp. 189-199. doi: 10.1080/02827589709355400
[21] V. Junttila, A.O. Finley, J.B. Bradford, and T. Kauranne, Strategies for minimizing sample size for use in airborne LiDAR-based forest inventory, Forest Ecol. Manage. 292 (2013), pp. 75-85. doi: 10.1016/j.foreco.2012.12.019
[22] A. Kangas, On the bias and variance in tree volume predictions due to model and measurement errors, Scand. J. Forest Res. 11 (1996), pp. 281-290. doi: 10.1080/02827589609382937
[23] A. Kangas, Small-area estimates using model-based methods, Can. J. Forest Res. 26 (1996), pp. 758-766. doi: 10.1139/x26-085
[24] A. Kangas and M. Maltamo, Forest Inventory: Methodology and Applications, Vol. 10, Springer, Dordrecht, 2006.
[25] V. Kint, M. Van Meirvenne, L. Nachtergale, G. Geudens, and N. Lust, Spatial methods for quantifying forest stand structure development: A comparison between nearest-neighbor indices and Variogram analysis, Forest Sci. 49 (2003), pp. 36-49.
[26] J.W. Lichstein, T.R. Simons, S.A. Shriner, and K.E. Franzreb, Spatial autocorrelation and autoregressive models in ecology, Ecol. Monographs 72 (2002), pp. 445-463. Available at http://dx.doi.org/10.1890/0012-9615(2002)072[0445:SMI]2.0.CO;2 doi: 10.1890/0012-9615(2002)072[0445:SAAAMI]2.0.CO;2
[27] N.T. Longford, Missing Data and Small-area Estimation, Springer, New York, 2005.
[28] R. Lucas, A. Lee, J. Armston, J. Breyer, P. Bunting, and J. Carreiras, Advances in forest characterisation, mapping and monitoring through integration of LiDAR and other remote sensing datasets, in Proceedings of SilviLaser 2008, 8th International Conference on LiDAR Applications in Forest Assessment and Inventory, R. Hill, J. Rosette and J. Suárez eds., Forestry Commission, Edinburgh, 2008, pp. 11.
[29] S. Magnussen, Application and comparison of spatial models in analyzing tree-genetics field trials, Can. J. Forest Res. 20 (1990), pp. 536-546. doi: 10.1139/x90-070
[30] S. Magnussen, Fast pre-survey computation of the mean spatial autocorrelation in large plots composed of a regular array of secondary sampling units, Math. Modell. Scient. Comput. 13 (2001), pp. 204-217.
[31] S. Magnussen, Arguments for a model based inference? Forestry Int. J. Forest Sci. 88 (2015), pp. 317-325.
[32] D. Mandallaz, Design-based properties of some small-area estimators in forest inventory with two-phase sampling, Can. J. Forest Res. 43 (2013), pp. 441-449. Available at http://dx.doi.org/10.1139/cjfr-2012-0381 doi: 10.1139/cjfr-2012-0381
[33] R.E. McRoberts, A model-based approach to estimating forest area, Remote Sens. Environ. 103 (2006), pp. 56-66. doi: 10.1016/j.rse.2006.03.005
[34] R.E. McRoberts, G.R. Holden, M.D. Nelson, G.C. Liknes, and D.D. Gormanson, Using satellite imagery as ancillary data for increasing the precision of estimates for the Forest Inventory and Analysis program of USDA Forest Service, Can. J. Forest Res. 36 (2006), pp. 2968-2980.
[35] R.E. McRoberts, W.B. Cohen, E. Næsset, S.V. Stehman, and E.O. Tomppo, Using remotely sensed data to construct and assess forest attribute maps and related spatial products, Scand. J. Forest Res. 25 (2010), pp. 340-367. Available at http://search.ebscohost.com/login.aspx?direct=true&db=lah&AN=20103283977&site=ehost-live doi: 10.1080/02827581.2010.497496
[36] R.E. McRoberts, E. Næsset, and T. Gobakken, Inference for lidar-assisted estimation of forest growing stock volume, Remote Sens. Environ. 128 (2013), pp. 268-275. doi: 10.1016/j.rse.2012.10.007
[37] F. Montes, M.J. Hernández, and I. Cañellas, A geostatistical approach to cork production sampling estimation in Quercus suber forests, Can. J. Forest Res. 35 (2005), pp. 2787-2796. Available at http://dx.doi.org/10.1139/x05-197 doi: 10.1139/x05-197
[38] E. Næsset, Accuracy of forest inventory using airborne laser scanning: evaluating the first Nordic full-scale operational project, Scand. J. Forest Res. 19 (2004), pp. 554-557. Available at http://search.ebscohost.com/login.aspx?direct=true&db=lah&AN=20053002983&site=ehost-live doi: 10.1080/02827580410019544
[39] E. Næsset, Practical large-scale forest stand inventory using a small-footprint airborne scanning laser, Scand. J. Forest Res. 19 (2004), pp. 164-179. Available at ISI:000220748000006. doi: 10.1080/02827580310019257
[40] E. Næsset, Area-based inventory in Norway – from innovation to an operational reality, in Forestry Applications of Airborne Laser Scanning, M. Maltamo, E. Naesset, and J. Vauhkonen, eds., Springer, Dordrecht, NL, 2014, pp. 215-240.
[41] E. Næsset, O.M. Bollandsås, and T. Gobakken, Comparing regression methods in estimation of biophysical properties of forest stands from two different inventories using laser scanner data, Remote Sens. Environ. 94 (2005), pp. 541-553. Available at <GO to ISI>://CCC:000227046700010. doi: 10.1016/j.rse.2004.11.010
[42] E. Næsset, T. Gobakken, J. Holmgren, H. Hyyppä, M. Maltamo, H. Olsson, Å. Persson, and U. Söderman, Laser scanning of forest resources: The Nordic experience, Scand. J. Forest Res. 19 (2006), pp. 482-499. doi: 10.1080/02827580410019553
[43] J.D. Opsomer, F.J. Breidt, G.G. Moisen, and G. Kauermann, Model-assisted estimation of forest resources with generalized additive models, J. Amer. Statist. Assoc. 102 (2007), pp. 400-409. Available at CCC:000246859200002. doi: 10.1198/016214506000001491 · Zbl 1134.62389
[44] D. Pfeffermann, New important developments in small area estimation, Statist. Sci. 28 (2013), pp. 40-68. doi: 10.1214/12-STS395 · Zbl 1332.62038
[45] J.N.K. Rao, Small Area Estimation, Wiley Series in Survey Methodology, Wiley & Sons, Hoboken, NJ, 2003.
[46] J.N.K. Rao, Inferential issues in small area estimation: Some new developments, Stat. Transition. 7 (2005), pp. 513-526.
[47] S. Saarela, A. Grafström, G. Ståhl, A. Kangas, M. Holopainen, S. Tuominen, K. Nordkvist, and J. Hyyppa, Model-assisted estimation of growing stock volume using different combinations of LiDAR and Landsat data as auxiliary information, Remote Sens. Environ. 158 (2015), pp. 431-440. Available at http://www.sciencedirect.com/science/article/pii/S0034425714004726 doi: 10.1016/j.rse.2014.11.020
[48] S. Saarela, S. Schnell, A. Grafström, S. Tuominen, K. Nordkvist, J. Hyyppä, A. Kangas, and G. Ståhl, Effects of sample size and model form on the accuracy of model-based estimators of growing stock volume, Can. J. Forest Res. 45 (2015), pp. 1524-1534. doi: 10.1139/cjfr-2015-0077
[49] C. Salas, L. Ene, T.G. Gregoire, E. Næsset, and T. Gobakken, Modelling tree diameter from airborne laser scanning derived variables: A comparison of spatial statistical models, Remote Sens. Environ. 114 (2010), pp. 1277-1285. Available at http://search.ebscohost.com/login.aspx?direct=true&db=lah&AN=20103135895&site=ehost-live doi: 10.1016/j.rse.2010.01.020
[50] P. Snowdon, A ratio estimator for bias correction in logarithmic regressions, Can. J. Forest Res. 21 (1991), pp. 720-724. doi: 10.1139/x91-101
[51] P. Treitz, K. Lim, M. Woods, D. Pitt, D. Nesbitt, and D. Etheridge, LiDAR sampling density for forest resource inventories in Ontario, Canada, Remote Sens. 4 (2012), pp. 830-848. Available at http://www.mdpi.com/2072-4292/4/4/830 doi: 10.3390/rs4040830
[52] J.M. Ver Hoef and H. Temesgen, A comparison of the spatial linear model to nearest neighbor (k-NN) methods for forestry applications, PLoS ONE 8 (2013), pp. e59129. Available at http://dx.doi.org/10.1371%2Fjournal.pone.0059129 doi: 10.1371/journal.pone.0059129
[53] H. Wackernagel, Multivariate Geostatistics, Springer Science & Business Media, Heidelberg, 2003.
[54] N.A. Weiss, A Course in Probability, Addison-Wesley, Boston, 2006.
[55] H. White, A heteroskedasticity-consistent covariance matrix estimator and a direct test for heteroskedasticity, Econometrica 48 (1980), pp. 817-830. doi: 10.2307/1912934 · Zbl 0459.62051
[56] K.M. Wolter, Introduction to Variance Estimation, Statistics for Social and Behavioral Sciences, 2nd ed., Springer, New York, 2007.
[57] M. Woods, D. Pitt, M. Penner, K. Lim, D. Nesbitt, D. Etheridge, and P. Treitz, Operational implementation of a LiDAR inventory in Boreal Ontario, Forestry Chronicle 87 (2011), pp. 512-528. Available at http://pubs.cif-ifc.org/doi/abs/10.5558/tfc2011-050 doi: 10.5558/tfc2011-050
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.