Articles containing the keyword 'logistic regression'

In this study, logistic regression and neural networks were used to predict non-industrial private forests (NIPF) landowners’ choice of forest taxation basis. The main frame of reference of the study was the Finnish capital taxation reform of 1993. As a consequence of the reform, landowners were required to choose whether to be taxed according to site-productivity or realized-income during the coming transition period of thirteen years.

The most important factor affecting the landowners’ choice of taxation basis was the harvest rate during the transition period, i.e. the chosen timber management strategy. Furthermore, the estimated personal marginal tax rate and the intention to cut timber during next three years affected the choice. The descriptive landowner variables did not have any marked effect on the choice of forest taxation basis.

On average, logistic regression predicted 71% of the choices correctly; the corresponding figure for neural networks was 63%. In both methods, the choice of site-productivity taxation was predicted more accurately than the choice of realized-income taxation. An increase in the number of model variable did not significantly improve the results of neural networks and logistic regression.

• Pesonen, E-mail: mp@mm.unknown
• Kettunen, E-mail: ak@mm.unknown
• Räsänen, E-mail: pr@mm.unknown

Questions of the small size of non-industrial private forest (NIPF) holdings in Finland are considered and factors affecting their partitioning are analysed. This work arises out of Finnish forest policy statements in which the small average size of holdings has been seen to have negative influence on the economics of forestry. A literature survey indicates that the size of holdings is an important factor determining the costs of logging and silvicultural operations, while its influence on the timber supply is slight.

The empirical data are based on a sample of 314 holdings collected by interviewing forest owners in 1980–86. In 1990–91 the same holdings were resurveyed by means of a postal inquiry and partly by interviewing the forest owners. The principal objective was to collect data to assist in quantifying ownership factors that influence partitioning among different kinds of NIPF holdings. Thus, the mechanism of partitioning was described and a maximum likelihood logistic regression model was constructed using seven independent holding and ownership variables.

One out of four holdings had undergone partitioning in conjunction with a change in ownership, one fifth among family owned holdings and nearly a half among jointly owned holdings. The results of the logistic regression model indicate, for instance, that the odds on partitioning is about three times greater for jointly owned holdings than for family owned ones. Also, the probabilities of partitioning were estimated and the impact of independent dichotomous variables on the probability of partitioning ranged between 0.02 and 0.01. The low value of Hosmer-Lemeshow test statistics indicates a good fit of the model, and the rate of correct classification was estimated to be 88% with a cut-off point of 0.5.

The average size of holdings undergoing ownership changes decreased from 29.9 ha to 28.7 ha over the approximate interval 1983–90. In addition, the transition probability matrix showed that the trends towards smaller size categories mostly concerned the small size categories. The results can be used in considering the effects of the small size holdings for forestry and if the purpose is to influence partitioning through forest or rural policy.

• Ripatti, E-mail: pr@mm.unknown

The presence/absence data of 27 forest insect taxa (Retinia resinella, Formica spp., Pissodes spp., several scolytids) and recorded environmental variation were used to investigate the applicability of modelling insect occurrence based on satellite imagery. The sampling was based on 1,800 sample plots (25 m by 25 m) placed along the sides of 30 equilateral triangles (side 1 km) in a fragmented forest area (approximately 100 km²) in Evo, Southern Finland. The triangles were overlaid on land use maps interpreted from satellite images (Landsat TM 30 m multispectral scanner imagery 1991) and digitized geological maps. Insect occurrence was explained using either environmental variables measured in the field or those interpreted from the land use and geological maps. The fit of logistic regression models carried between species, possibly because some species may be associated with characteristics of single trees while other species with stand characteristics. The occurrence of certain insect species at least, especially those associated with Scots pine, could be relatively accurately assessed indirectly on the basis of satellite imagery and geological maps. Models based on both remotely sensed and geological data better predicted the distribution of forest insects except in the case of Xylechinus pilosus, Dryocetes sp. and Trypodendron lineatum, where the differences were relatively small in favour of the models based on field measurements. The number of species was related to habitat compartment size and distance from the habitat edge calculated from the land use maps, but logistic regressions suggested that other environmental variables in general masked the effect of these variables in species occurrence at the present scale.

• Väisänen, E-mail: rv@mm.unknown
• Heliövaara, E-mail: kh@mm.unknown

Two operative forest site class estimation methods utilizing satellite images have been developed for forest income taxation purposes. For this, two pixelwise classification methods and two post-processing methods for estimating forest site fertility are compared using different input data. The pixelwise methods are discriminant analysis, based on generalized squared distances, and logistic regression analysis. The results of pixelwise classifications are improved either with mode filtering within forest stands or assuming a Markov random field type dependence between pixels. The stand delineation is obtained by using ordinary segmentation techniques. Optionally, known stand boundaries given by the interpreter can be applied. The spectral values of images are corrected using a digital elevation model of the terrain. Some textural features are preliminary tested in classification. All methods are justified by using independent test data.

A test of the practical methods was carried out and a cost-benefit analysis computed. The estimated cost saving in site quality classification varies from 14% to 35% depending on the distribution of the site classes of the area. This means a saving of about 2.0–4.5 million FMK per year in site fertility classification for income taxation purposes. The cost savings would rise even to 60% if that version of the method were chosen where field checking is totally omitted. The classification accuracy at the forest holding level would still be similar to that of traditional method.

The PDF includes a summary in Finnish.

• Tomppo, E-mail: et@mm.unknown

Biogeographical patterns of the Scolytidae in Fennoscandia and Denmark, based on species incidence data from the approximately 70 km x 70 km quadrats (n = 221) used by Lekander et al. (1977), were classified to environmental variables using multivariate methods (two-way indicator species analysis, detrended correspondence analysis, canonical correspondence analysis).

The distributional patterns of scolytid species composition showed similar features to earlier presented zonations based on vegetation composition. One major difference, however, was that the region was more clearly divided in an east-west direction. Temperature variables associated with the location of the quadrat had the highest canonical coefficient values on the first axis of the CCA. Although these variables were the most important determinants of the biogeographical variation in the beetle species assemblages, annual precipitation and the distribution of Picea abies also improved the fit of the species data.

Samples with the most deviant rarity and typicality indices for the scolytid species assempblages in each quadrat were concentrated in several southern Scandinavian quadrats, in some quadrats in northern Sweden, and especially on the Swedish islands (Öland, Gotland, Gotska Sandön) in the Baltic Sea. The use of rarity indices which do not take the number of species per quadrat, also resulted high values for areas near Stockholm and Helsinki with well-known faunas. Methodological tests in which the real changes in the distribution of Ips acuminatus and I. amitinus were used as indicators showed that the currently available multivariate methods are sensitive to small faunal shifts even, and thus permit analysis of the fauna in relation to environmental changes. However, this requires more detailed monitoring of the species’ distributions over longer time spans.

Distribution of seven species (Scolytus intricatus, S. laevis, Hylurgops glabratus, Crypturgus cinereus, Pityogenes salasi, Ips typographus, and Cyleborus dispar) were predicted by logistic regression models using climatic variables. In spite of the deficiencies in the data and the environmental variables selected, the models were relatively good for several but not for all species. The potential effects of climate change on bark beetles are discussed.

The PDF includes a summary in Finnish.

• Heliövaara, E-mail: kh@mm.unknown
• Väisänen, E-mail: rv@mm.unknown
• Immonen, E-mail: ai@mm.unknown

The fusion of optical satellite imagery, strips of lidar data and field plots is a promising approach for the inventory of tropical forests. Airborne lidars also enable an accurate direct estimation of the forest canopy cover (CC), and thus a sample of lidar strips can be used as reference data for creating CC maps which are based on satellite images. In this study, our objective was to validate CC maps obtained from an ALOS AVNIR-2 satellite image wall-to-wall, against a lidar-based CC map of a tropical forest area located in Laos. The reference CC values which were needed for model training were obtained from a sample of four lidar strips. Zero-and-one inflated beta regression (ZOINBR) models were applied to link the spectral vegetation indices derived from the ALOS image with the lidar-based CC estimates. In addition, we compared ZOINBR and logistic regression models in the forest area estimation by using >20% CC as a forest definition. Using a total of 409 217 30 × 30 m population units as validation, our model showed a strong correlation between lidar-based CC and spectral satellite features (root mean square error = 12.8%, R² = 0.82). In the forest area estimation, a direct classification using logistic regression provided better accuracy than the estimation of CC values as an intermediate step (kappa = 0.61 vs. 0.53). It is important to obtain sufficient training data from both ends of the CC range. The forest area estimation should be done before the CC estimation, rather than vice versa.

• Korhonen, University of Eastern Finland, School of Forest Sciences, P.O. Box 111, FI-80101 Joensuu, Finland; (current) University of Helsinki, Department of Forest Sciences, P.O. Box 27, FI-00014 University of Helsinki, Finland http://orcid.org/0000-0002-9352-0114 E-mail: lauri.z.korhonen@helsinki.fi
• Ali-Sisto, University of Eastern Finland, School of Forest Sciences, P.O. Box 111, FI-80101 Joensuu, Finland E-mail: dheikkil@student.uef.fi
• Tokola, University of Eastern Finland, School of Forest Sciences, P.O. Box 111, FI-80101 Joensuu, Finland. E-mail: timo.tokola@uef.fi

• Korhonen, School of Forest Sciences, University of Eastern Finland, P.O. Box 111, FI-80101 Joensuu, Finland E-mail: lauri.korhonen@uef.fi
• Pippuri, School of Forest Sciences, University of Eastern Finland, P.O. Box 111, FI-80101 Joensuu, Finland E-mail: inka.pippuri@uef.fi
• Packalén, School of Forest Sciences, University of Eastern Finland, P.O. Box 111, FI-80101 Joensuu, Finland E-mail: petteri.packalen@uef.fi
• Heikkinen, School of Computing, University of Eastern Finland, P.O. Box 111, FI-80101 Joensuu, Finland E-mail: ville.heikkinen@uef.fi
• Maltamo, School of Forest Sciences, University of Eastern Finland, P.O. Box 111, FI-80101 Joensuu, Finland E-mail: matti.maltamo@uef.fi
• Heikkilä, Finnish Forest Centre, Public Services, Maistraatinportti 4 A, FI-00240 Helsinki, Finland E-mail: juho.heikkila@metsakeskus.fi

• Kangas, Department of Forest Sciences, P.O. Box 27, FI-00014 University of Helsinki, Finland E-mail: annika.kangas@helsinki.fi
• Mehtätalo, University of Eastern Finland, School of Forest Sciences, Joensuu, Finland E-mail: lm@nn.fi
• Mäkinen, Simosol Oy, Riihimäki, Finland E-mail: am@nn.fi
• Vanhatalo, Department of Forest Sciences, P.O. Box 27, FI-00014 University of Helsinki, Finland E-mail: kv@nn.fi

• Mattila, The Finnish Forest Research Institute, Joensuu Unit, P.O. Box 68, FI-80101 Joensuu, Finland E-mail: um@nn.fi
• Nuutinen, The Finnish Forest Research Institute, Joensuu Unit, P.O. Box 68, FI-80101 Joensuu, Finland E-mail: tn@nn.fi

• Vospernik, University of Natural Resources and Applied Life Sciences, Institute of Forest Growth Research, Department of Forest and Soil Sciences, Peter-Jordan-Stra§e 82, A-1190 Vienna, Austria E-mail: sonja.vospernik@boku.ac.at

• Lindén, Southern Swedish Forest Research Centre c/o Asa Experimental Forest, SLU, S-360 30 Lammhult, Sweden E-mail: magnus.linden@ess.slu.se
• Vollbrecht, Southern Swedish Forest Research Centre c/o Asa Experimental Forest, SLU, S-360 30 Lammhult, Sweden E-mail: gv@nn.se

• Jalkanen, Finnish Forest Research Institute, Unioninkatu 40 A, FIN-00170 Helsinki, Finland E-mail: anneli.jalkanen@metla.fi

• Kiffner, University Göttingen, Büsgen-Institute, Department of Forest Zoology and Forest Protection incl. Wildlife Biology and Game Management, Büsgenweg 3, 37077 Göttingen, Germany E-mail: ckiffne@gwdg.de
• Rössiger, University Göttingen, Büsgen-Institute, Department of Forest Zoology and Forest Protection incl. Wildlife Biology and Game Management, Büsgenweg 3, 37077 Göttingen, Germany E-mail: er@nn.de
• Trisl, Planungsbüro Trisl, In der Schleene 7, 36037 Waake, Germany E-mail: ot@nn.de
• Schulz, University Göttingen, Büsgen-Institute, Department of Ecological Informatics, Biometry and Forest Growth, Büsgenweg 4, 37077 Göttingen, Germany E-mail: rs@nn.de
• Rühe, University Göttingen, Büsgen-Institute, Department of Forest Zoology and Forest Protection incl. Wildlife Biology and Game Management, Büsgenweg 3, 37077 Göttingen, Germany E-mail: fr@nn.de