Farms are highly heterogeneous and never identical. No two farms are ever alike in terms of (1) the basic resources, land, labour, or capital that are available, (2) the way these resources or factors of production are combined, or (3) in terms of the amounts of various crops and livestock produced. There are numerous factors that influence the price of a farm and some of these factors are not monetary related. This makes the task of the valuer complex, and it increases the possibility of large differences in the estimated market value determined and the actual selling price. The development and use of AVM (Automated Valuation Method) models in the valuation of especially residential property, is a worldwide phenomenon. The majority of AVM models use MRA (Multiple Regression Analysis) as a basis. The accuracy of a MRA relies heavily on the quality and accuracy of the data that are used. Thus, the availability of quality and accurate data has a significant impact on the potential accuracy of a MRA. Accurate MRA valuation estimates will be fair to individual farm owners regarding their municipal tax assessments and it will lead to a wider use of MRAs for the valuation of farms, with the associated benefits of lower valuation costs and speedier valuations, especially by financial institutions. This study analyses the unique and distinctive attributes of farms, which must be taken into account when a MRA model is developed. By following a stepwise regression approach, a regression model is developed which is fairly accurate, but it does not achieve a high level of accuracy. Furthermore, the results of the study show that it is difficult to have enough appropriate and accurate data available to develop a regression analysis for agricultural property to satisfy accuracy requirements. Although it is difficult, it is possible to develop MRA models that are fairly accurate. Therefore, if MRA models are currently used for the municipal valuation of farms, which are not fairly accurate, it should be possible to improve the accuracy. However, maximum accuracy cannot be achieved with MRA models. Thus, it cannot replace a valuation done by a skilled and knowledgeable professional valuer, when maximum accuracy is required. / Dissertation (MSc)--University of Pretoria, 2017. / Construction Economics / MSc / Unrestricted

This thesis extends the use of artificial neural networks (ANNs) optimisation and training algorithms including the Powell-Beale conjugate gradient (PBCG), scaled conjugate gradient (SCG) and a hybrid system of particle swarm optimisation (PSO) with the traditional back propagation (BP) in mass appraisal as a first attempt. The goal is to verify the comparative performance of ANNs with the traditional hedonic regression and some other modelling techniques including geographically weighted regression (GWR), spatial error model (SEM), spatial lag model (SLM), additive nonparametric regression (ANR), M5P trees and the support vector machines (SVMs). The methodologies are applied to data of 3232 sales transaction of single-family dwellings sold during the period, January 2012 to May 2014 in Cape Town, South Africa. The analysis was done in categories such that the best performing method in each category is selected for a final comparative analysis. The results reveal that semi-log model, SEM, normalised polynomial kernel function support vector machines (NPKSVMs), ANR and the Levenberg-Marquardt trained artificial neural networks (LMANNs) performed best in their respective category. The study also demonstrates the practicability of building hybrid systems in mass appraisal, unfortunately, the hybrid models produces an unexpected results relative to the standalone ANN models. Furthermore, the five best performed models were subjected to three different tests namely, prediction accuracy within the 10 and 20%, model performance and reliability ranking order and lastly explicit explainability ranking order. The final results reveal the LMANNs to outperform the ANR, semi-log, SEM and SVMs in the first two tests, but when the explicit explainability ranking order test which consist of simplicity, consistency, transparency, locational and applicability within the mass appraisal environment was performed, the LMANNs failed the test. The results demonstrate the SEM as the most preferred technique because of its transparency, locational advantage and ease of application within the mass appraisal environment. Furthermore, it is inferred from the findings that having superior predictive power is imperative, but most importantly is whether the model can practically and effectively be used in mass appraisal of properties. The black box nature of the ANNs inhibits the production of sufficiently transparent estimates that appraisers could use to explain the process when required as a defence before a tribunal or in a formal court. This thesis contributes to knowledge as follows: i. Analyse the significance of spatial variation of property prices, with Cape Town, South Africa used as case study; ii. Build a hybrid system of PSO and BP in mass appraisal; iii. Improve the training of ANNs in mass appraisal with SCG and PBCG algorithms; and, iv. Extend the use of GWR, SEM, SLM, SVMs, ANR and log transformation of variables into the South African property market context. / Thesis (PhD)--University of Pretoria, 2018. / NRF CSUR13092648264, Grant No: 90311 / Construction Economics / PhD / Unrestricted

The last General Valuation in Cyprus, in 1980, took about twelve years to be completed by the Lands and Surveys Department. The comparison method was adopted and no computerised (mass appraisal) method or tool was used to assist the whole process. Although the issue of mass appraisal was raised by Sagric International, who had been invited to Cyprus as consultants, and recently by DataCentralen A/S with the development of a mass appraisal system based on regression analysis, there has been little literature and no research directly undertaken on the problems and the analysis of immovable property taxation in Cyprus and the development of an artificial neural networks valuation system for houses and apartments. The research project approached the issue of property taxation and mass appraisal through an investigation into Cyprus's needs for an up-dated tax base for equitabileness and for an assessment system capable of performing an effective revaluation at a certain date, with minimum acceptable mean error, minimum data and minimum cost. Investigation within Cyprus and world-wide indicated that this research project is a unique study in relation to Cyprus's property taxation and the development of a computer assisted mass appraisal system based on modular artificial neural networks. An empirical study was carried out, including prototyping and testing. The system results satisfy IAAO criteria for mass appraisal techniques, compare favourably with other studies and established a framework upon which future research into computer assisted mass appraisal for taxation purposes can be developed. In conclusion, the project has contributed significantly to the available literature on the immovable property taxation in Cyprus and the development of a computer assisted mass appraisal system for houses and apartments based on modular artificial neural network method. The proposed approach is novel not only in the context of Cyprus but also world-wide.

預售屋價格長久受到台灣產業界與學術界密切關注，然而預售屋價格資訊卻相對成屋缺乏，本研究希望釐清預售屋的特性並建立預售屋大量估價模型，提供預售屋價格資訊。預售屋具期貨交易性質，其價格形成受周遭成屋價格影響，其基差(預售屋與成屋價格差)關係顯得格外重要；另一方面，預售屋為完工前銷售之產品，有品質不易掌握之特性，消費者傾向透過商譽來評斷產品優劣，商譽因而相對凸顯，加上預售屋具有以個案方式為中心之定價模式，相對成屋其個案特徵顯得更加強烈，基差與建商商譽成為預售屋估價上必要考量的兩個重心。 本文以特徵價格方式納入基差與商譽因素進行實證分析與建立模型，研究期間為台北市2012年第3季至2015年第4季，在資料處理上透過座標整合內政部實價登錄資料以及國泰建設市調資料，解決實價登錄資料中缺乏個案屬性的去識別化問題，將預售屋「個案」特徵納入「個戶」估計中，突破過往預售屋研究限縮於個案的限制。實證結果顯示，台北市預售屋單價平均比周圍成屋多出35.5%的水準、而屬於上市上櫃建商的預售產品則相較非上市櫃產品平均高出5.7%的價格；模型估計表現上，本研究實證模型解釋力達到65.1%，模型之絕對平均誤差為10.56%、±10%及±20%的命中率分別為57.86%、88.25%，達到大量估價模型要求水準，值得參考使用。

隨著電腦及統計模型的發展、原本用於稅賦評估工具的大量估價逐漸受到重視。美國更利用完善的國家層級資料，將大量估價改良為自動估價模型（Automated Valuation Model, AVM）。由於估值估算快速、成本低廉及龐大的資料庫等優點，受到美國私部門的歡迎。另一方面，不動產市場仍有存在著個別估價的客觀性的質疑，而估價行為學也證實了個別估價有偏離估價程序的可能。市場上存在著兩者的支持者，但由於兩者特性迥然不同，甚難比較。 本研究以一致的資料庫及衡量標準，將交易價格做為市場價值表徵，以估值的準確性作為衡量兩者的準則，找出兩者的特性及適用範圍。實證結果顯示當勘估標的數量達到一定程度，可忽略不動產的異質性時，個別估價與大量估價準確性並沒有顯著的差異。但個別估價準確性的分配較大量估價集中、且偏誤程度也較低。個別估價較不受不動產特性的影響，適用的範圍較廣；而大量估價較易受到不動產特性影響，適用範圍視資料庫的內容而定。另一方面，個別估價的估價認知具有時間性，表示不動產估價師需更新估價認知，以保持高度的估值準確性。此說明了國內不動產市場的變化快速及國內不動產估價師的專業能力。 / With the development of computer and statistical model, the mass appraisal as assessment tool has been paid attention gradually. Americans utilize the national data to develop Automated Valuation Models (AVMs).For its advantages of faster valuation , less cost and huge database, mass appraisal is used as assessment but also appraisal tool . On the other hand, the real estate market stills have query with objectivity of individual appraisers. The study of appraisers’ behavior suggest that the possibility of deviate from standard procedure of appraising. In a matter of fact, the real state market is filled with supporters of appraisers and mass appraisals. Because of these different characteristic, it’s difficult to compare with. This research will trade selling-prices to seek for the market value form with unanimous database and criterion, regard accuracy of valuation as and weigh the criterion of the two, and find out the characteristic of the two and scope of application .Although the result showed that the accuracy is no difference between appraiser and mass appraisal significantly when the amount of real estates is large enough to neglect heterogeneity. Compare with mass appraisal, the distribution of appraiser’s accuracy is more centralized and the standard deviation is smaller. The accuracy of appraiser is steady, and the scope of application is relatively wide. But the accuracy of mass appraisal is affected by the characteristic of real estate, and the scope of application depends on content of the database.On the other hand, the appraisal cognition has timeliness, it shows appraiser needs to upgrade the appraise cognition and the market condition , in order to keep the valuation accuracy of the height. This has stated the fast-change market and domestic the professional ability of appraisers.

Nekilnojamojo turto objektų savininkai turtą parduoda, dovanoja ar kitaip perleidžia kitų asmenų nuosavybėn. Todėl yra labai svarbu nustatyti kuo tikslesnę nekilnojamojo turto vertę, kuri būtų naudojama privatizuojant valstybinę žemę žemės reformos metu, sudarant nekilnojamojo turto sandorius, apskaičiuojant nekilnojamojo turto mokesčius. Straipsnyje analizei panaudoti 2007 metų siūlomų parduoti žemės ūkio paskirties ir namų valdos žemės sklypų, esančių Prienų rajone, duomenys, siekiant įvertinti masinio vertinimo tikslumą. Išanalizavus pasirinktame rajone esančius žemės ūkio paskirties ir namų valdos žemės sklypus ir jiems pritaikius masinio vertinimo modelį, taikomą verčių žemėlapiams sudaryti (2008 m.), matyti, kad sudaryti pagal vertinimo modelį žemės verčių žemėlapiai neatitinka rinkoje siūlomų žemės ūkio paskirties ir namų valdos žemės sklypų kainų. / Owners of real property often sell give as a present or make their property over to somebody else in some other way. So, it is very important to define the accurate value of the real estate, which could be used during the privatization of the state-owned land (during land reform), as well as making real property transactions or calculating real estate taxes. Land market in Prienai district was analyzed in this thesis work. The data about premise and agricultural land plots in Prienai district during 2007 has been collected for this research work. On purpose to evaluate the accuracy of mass appraisal of land, the prices of these plots were compared to those received while calculating according to the value model used for the compiling of value maps. According to the received data, market prices do not correspond to those presented in the land value maps.

Baigiamojo darbo apimtis - 49 p. Darbe yra 20 paveikslų ir 3 lentelės, bei 4 priedai, kurie papildo tyrimo duomenis. Bibliografinį aprašą sudaro 38 literatūros šaltiniai. Tyrimo tikslas – išanalizuoti skirtingos paskirties nekilnojamojo turto masinio vertinimo tikslumą Kauno mieste. Tyrimo objektas – skirtingos paskirties nekilnojamojo turto masinio vertinimo metodu nustatytos vidutinės rinkos vertės. Tyrimo uždaviniai: 1. Ištirti literatūrą nekilnojamojo turto rinkos ir vertinimo klausimais. 2. Išanalizuoti masinio nekilnojamojo turto vertinimo motodiką.. 3. Ištirti Kauno miesto skirtingos paskirties nekilnojamojo turto vertes. 4. Įvertinti vidutinių pasiūlos kainų ir nustatytų pagal masinio vertinimo metodiką, verčių skirtumus. Tyrimų metodai – mokslinės literatūros, kurioje nagrinėjamas nekilnojamo turto masinis vertinimas ir jo tikslumas, analizė ir sintezė, tiesioginės apklausos, statistinių duomenų rinkimo, analizės, grupavimo, palyginimo ir grafinio vaizdavimo metodai. Nekilnojamojo turto vertinimas yra būtinas turto pirkėjams ir pardavėjams, , kreditų davėjams, hipotekos įstaigoms, investuotojams ir kiekvienam savininkui. Nekilnojamojo turto įvertinimas negali būti absoliučiai teisingas, tačiau siekti tikslumo, vertinant turtą, yra būtina. Tyrimo analizei panaudoti 2010 – 2012 metų 160 nekilnojamojo turto objektų, esantys Kauno mieste. Išanalizavus nekilnojamojo turto objektus ir jiems pritaikius masinio vertinimo modelį, nustatyta, kad pasiūlos kainos... [toliau žr. visą tekstą] / Final work of University Master Studies: 49 pages, 20 figures, 3 tables, 4 appendices, 38 reference sources. Aim of the research: analysis of mass appraisal accuracy of different real estate in the City of Kaunas. Subject of the research: average market values of different real estate, determined by mass appraisal method. Objectives of the research: 1) To review the reference sources on the real estate market and valuation; 2) To analyze the methods of real estate mass appraisal; 3) To survey the values of different real estate in the Kaunas City; 4) To assess the differences in values between average supply costs and those calculated by the mass appraisal methodology; Research methods: analysis and synthesis of scientific literature dealing with the mass appraisal of real estate and its accuracy, direct questioning, statistical data collection, analysis, grouping, comparison, and graphical visualization techniques. Real estate appraisal is necessary for property buyers and sellers, credit grantors, mortgage institutions, investors, and for every owner. Real estate appraisal can not be absolutely correct, but here it is necessary to seek precision. 160 units of real estate, located in the City of Kaunas and evaluated in 2010 - 2012, were chosen for the survey. The analysis of real estate units when their values were determined by a mass appraisal model evidence that the market supply prices are higher. It was found that the smallest difference in prices of... [to full text]

2011 metų pabaigoje Seime priimti Žemės mokesčio įstatymo pakeitimai. Priėmus naują žemės mokesčio įstatymo pakeitimo įstatymą nuo 2013 metų pereita prie žemės mokesčio skaičiavimo nuo vidutinės žemės rinkos vertės, kuri nustatoma masinio arba individualaus vertinimo būdu. Iš esmės keičiasi ne pats žemės mokestis, o vertė, nuo kurios šis mokestis skaičiuojamas. Teisę nustatyti žemės mokesčio tarifus ir taip reguliuoti mokesčio dydį nuo 0,01 iki 4 procentų (vietoje buvusio 1,5 proc. tarifo) žemės vertės ribose įstatymas suteikia savivaldybėms. Panašūs įgaliojimai savivaldybėms vykdyti savarankišką mokesčių politiką yra suteikti nekilnojamojo turto mokesčio srityje bei nuomojant valstybinę žemę, kur jau eilę metų mokesčiai skaičiuojami nuo rinkos vertės, o savivaldybės turi kompetenciją spręsti dėl konkrečių tarifų nustatytose ribose. Ištyrus pasikeitimus galime pastebėti, jog naujas įstatymas nebuvo paruoštas iki galo, kadangi neaišku pagal kokias taisykles savivaldybės nustatinėja tarifus ar kaip bus nustatyta nenaudojama žemė. Taip pat dėl plataus žemės mokesčio tarifo intervalo, bei palikto tik vieno žemės apmokestinimo vertę mažinančio koeficiento šis įstatymas kai kuriems žemės savininkams mokesčius išaugino po kelis ar keliolika kartų. Magistratūros baigiamąjį darbą (MBD) sudaro: įvadas, 5 skyriai, 8 poskyriai, 4 skirsniai, išvados bei literatūros sąrašas. Darbo apimtis – 55 puslapiai, jame yra 11 paveikslų ir 7 lentelės. Bibliografinį aprašą sudaro 35 šaltiniai. / At the end of 2011 Seimas has adopted changes in land taxation system. Since 2013, after a new enactment came into force, the land was taxed according to the average land’s value in the market. The value was determined in a way of mass or individual appraisal. Generally, the tax on the land remained the same, just the value has changed, which resulted in different calculation of the taxes. The enactment provided the municipalities with the right to appraise and control the tariffs of the taxes on the land from 0.01 to 4 percent (instead of the former 1.5 percent tariff). Moreover, very similar enactments which enable the municipalities to implement an independent taxing policy have been provided in the real-estate and leasehold of government’s land areas, where the taxes used to be calculated according to the market value and the municipalities used to have the competence to decide on the certain tariffs within the limits for years. After having performed the analysis of the changes, it is noticeable that the new enactment has not been fully prepared as it is not clear according to what canon the municipalities appraise the tariffs or how they will identify the unexploited land. Finally, this enactment has caused the increase on the land taxes for some of the landlords in several or even more times, because of the wide interval of land tariff and only one coefficient which reduces the land’s taxation value left. This graduate work contains: preface, 5 chapters, 18... [to full text]

There are different ways in how to assess a value to a property and which assessment technique that is used differs due to circumstances in each country, leading to different views of what is the best and most effective way. At the moment Botswana is suffering from obsolete valuation rolls and is in the position where the system could benefit of a reform. The overall purpose with this study is to gain knowledge about how Botswana and Sweden differ in terms of property tax assessment. By clarifying the similarities and differences between how values are allocated and by determining the most value-influencing factors in Botswana, improvements of the system could be suggested. The research methods that were used to fulfil the study consisted of a review of relevant literature together with a case study performed in Gaborone. The case study contained semi-structured interviews with applicable staff and questionnaires responded by twelve valuers. The findings of this study show that there are similarities between the countries way of assessing properties since they both base their values on market value, use comparable sales method and assess both land and buildings. However, there are also differences in terms of the approach of assessment. The main difference is that Botswana applies an individual assessment method and Sweden mass appraisal. Other differences are the ones responsible for performing the assessment, and the structure of the assessment in terms of collecting data and the periods of assessment. Furthermore, the results from the questionnaires demonstrated that the most value-influencing factors for residential properties in Botswana are water, electricity and site amenities. The main conclusions drawn from this study is that Botswana could benefit from a movement towards mass appraisal and apply parts of the Swedish system. To make this possible to implement our recommendations are; to change the mindset of the stakeholders, increase awareness among property owners, base the valuation on a few important factors and computerize the cadastral register. A future research topic could be to investigate how a mass appraisal could be implemented as a step-by-step process. / Det finns olika sätt att bedöma ett värde på en fastighet och de bedömningstekniker som används varierar beroende på varje lands förutsättningar, vilket leder till olika uppfattningar om vad som är det bästa och mest effektiva sättet att värdera på. Botswana lider för närvarande av föråldrade taxeringsvärden och systemet skulle gynnas av en reform. Det huvudsakliga syftet med denna studie är att utveckla kunskap om hur fastighetstaxeringen i Botswana och Sverige skiljer sig åt. Genom att tydliggöra likheter och skillnader i hur fastigheterna i länderna tilldelas ett taxeringsvärde och genom att klarlägga de mest värdepåverkande faktorerna för fastigheterna i Botswana, kunde förbättringar av det botswanska systemet föreslås. För att genomföra studien utfördes en litteraturstudie baserad på relevant litteratur samt en fallstudie i Gaborone, som är huvudstaden i Botswana. Fallstudien innehöll dels semistrukturerade intervjuer med affärsmän inom området samt enkäter som besvarades av tolv värderingsmän. Resultaten av denna studie visar att den främsta likheten mellan länderna är att fastighetstaxeringsvärdet baseras på marknadsvärdet, detta är i sin tur baserat på ortsprismetoden och både mark och byggnader värderas. De skillnader som visade sig rörde tillvägagångssättet för bedömningen. Den största skillnaden är att Botswana tillämpar en individuell värdering och Sverige massvärdering. Andra skillnader som visade sig var bland annat vem det är som utför värderingen, hanteringen av insamlad data samt när värderingarna äger rum. Vidare visar resultaten från enkäterna att de mest värdepåverkande faktorerna för småhus i Botswana är vatten, el och tillgång till service. Slutsatsen av denna studie blev att Botswana skulle kunna gynnas av att implementera delar av det svenska fastighetstaxeringssystemet och i och med det gå mer mot massvärdering. För att kunna göra detta genomförbart är våra rekommendationer; att ändra tänkesätten hos de berörda parterna, öka medvetenheten bland fastighetsägare, basera värderingen på färre faktorer och datorisera fastighetsregistret. Ett framtida område för forskning skulle kunna vara att undersöka hur en massvärdering skulle kunna implementeras steg för steg.

Submitted by Jorge Silva (jorgelmsilva@ufrrj.br) on 2018-05-18T17:57:14Z No. of bitstreams: 1 2016 - Marlene Salete Uberti.pdf: 4547445 bytes, checksum: 0815ad8e3c8b5cdf64206ec60d91619c (MD5) / Made available in DSpace on 2018-05-18T17:57:14Z (GMT). No. of bitstreams: 1 2016 - Marlene Salete Uberti.pdf: 4547445 bytes, checksum: 0815ad8e3c8b5cdf64206ec60d91619c (MD5) Previous issue date: 2016-07-11 / Traditionally the Classical Linear Regression Models (CLRMs) have been used for mass appraisal of property bulk value, however, it has been noticed the need to take into account the data spatial variation. This modeling for the geographic effects has been used mainly in urban area appraisals, while farmland values are also affected by geographic location. The lack of methodologies for mass evaluation of farmland has led to tax evasion of farmland tax revenue (ITR), as it has been inefficiently and inexpressively collected since its enactment in 1964. The objective of this paper is to use econometrics models of spatial regression in farmland comparables to produce a map of standard ground value for the Northern Region of Rio de Janeiro State, Brazil. The proposed methodology includes the investigation and modeling the effects of spatial autocorrelation on the CLRMs, to evaluate their performance comparing them with the spatial models and to produce a map of standard ground value through ordinary Kriging and kernel estimator. The sample of comparables was comprised of 113 observations for model development and 25 observations for validation. To evaluate the performance of obtained maps of values were used the validation samples to calculate the Root Mean Square Error (RMSE) values and the metrics recommended by the International Association of Assessing Officers (IAAO). The results showed that the spatial autocorrelation can have its effect predicted by the Conditional AutoRegressive model (CAR) and by the Geographically Weighted Regression (GWR). By using the values predicted with the GWR model and the validation comparables, the Kernel estimator presented the best performance on map production, yielding the lowest RMSE and dispersion coefficients, median of ratios and Price Related Differential (PRD) close to IAAO recommended values. The combination of classical and spatial regression methodologies and the use of Geostatistics techniques showed to be suitable for obtaining maps of standard ground value for farmland areas. The proposed methodology has been show applicable to farmland sales market, as it can be used by municipalities to obtain representative models of real market values, as well as to produce farmland standard ground value maps. / Nas avalia??es em massa de im?veis tradicionalmente s?o utilizados os modelos cl?ssicos de regress?o linear (MCRL), entretanto tem-se verificado a necessidade de modelar os dados espacialmente. Esta modelagem dos efeitos espaciais vem sendo utilizada principalmente nas avalia??es de ?reas urbanas, sendo que os valores dos im?veis nas ?reas rurais tamb?m s?o afetados pela localiza??o geogr?fica. A inexist?ncia de metodologias de avalia??o em massa de im?veis rurais ? um dos motivos da evas?o da receita do imposto territorial rural (ITR), pois desde que foi criado em 1964, a arrecada??o deste imposto ? ineficiente e inexpressiva. O objetivo deste trabalho foi a utiliza??o de modelos econom?tricos de regress?o espacial na modelagem dos efeitos espaciais em uma amostra de im?veis rurais para a elabora??o da Planta de Valores Gen?ricos (PVG) em uma ?rea da Regi?o Norte Fluminense, estado do Rio de Janeiro. A proposta metodol?gica consistiu em investigar e modelar os efeitos causados pela autocorrela??o espacial sobre os MCRL, avaliar seus desempenhos comparando-os com os modelos espaciais e produzir a PVG por meio da Krigagem ordin?ria e do estimador Kernel. A amostra utilizada contou com 113 observa??es e 25 amostras de verifica??o. Para avaliar o desempenho das superf?cies de valores obtidas foram utilizadas as amostras de verifica??o e calculados os valores da Raiz Quadrada do Erro M?dio Quadr?tico (REMQ) e das m?tricas recomendadas pela International Association of Assessing Officers (IAAO). Os resultados mostraram que a autocorrela??o espacial pode ter seus efeitos reduzidos pelo Modelo do Erro Espacialmente Correlacionado (Conditional Auto Regressive - CAR) e pela Regress?o Geograficamente Ponderada (RGP). A superf?cie gerada pelo estimador Kernel, utilizando-se os valores preditos da amostra de verifica??o pelo modelo RGP foi a que obteve o melhor desempenho com menor REMQ e valores do coeficiente de dispers?o (COD), da mediana das raz?es e do Diferencial Relativo ao Pre?o (Price Related Differential - PRD) pr?ximos dos recomendados pela IAAO. A combina??o das metodologias da regress?o cl?ssica e espacial, e a utiliza??o de t?cnicas de Geoestat?stica se mostraram adequadas para a elabora??o e obten??o da PVG para ?reas rurais. A metodologia proposta se mostrou aplic?vel nos mercados de terras rurais, pois pode ser utilizada pelos munic?pios para obter modelos representativos da realidade destes mercados, bem como para elaborar a PVG das ?reas rurais.