Thesis (M. Sc. (Statistics)) --University of Limpopo, 2014 / analysis of price indices of electrical appliances in South Africa is performed using monthly data from Statistics South Africa for the period January 1998 to December 2010, with 2005 as a base year. Time series analysis (exponential smoothing and ARIMA) and neural networks are employed in developing forecasting models. The results for single, double and triple exponential smoothing are compared and triple exponential smoothing is found to be the best model amongst the three to forecast the electrical price indices in South Africa. ARCH models were also employed for the variable that failed to pass the requirements from ARIMA. Comparing neural networks, ARIMA and triple exponential smoothing results, neural networks is found to be the best model for forecasting price indices of electrical appliances. Regression analysis was then applied to the lighting equipment variable to check for a monthly effect after its plot depicted some seasonality pattern. Only the month of February did not have an impact or an effect on time since it was found not to be significantly different from zero. Multivariate time series is also applied in checking the correlation between the variables. Keywords: Time series analysis, ARIMA, ARCH, multiple linear regression, exponential smoothing, neural networks, electrical price indices.

Developing timely and reliable house price indices is of interest worldwide, because these measures influence consumer behaviour, inflation targeting, and spot and futures markets. Several techniques for constructing a constant quality price index are available in the literature, but these methods are difficult to apply in localities where market transaction data is limited. Since house price movements are a local phenomena, improving the timeliness of a quality controlled price index at local housing market levels in small countries like New Zealand is a challenge. This thesis comprises three essays that focused on improving the timeliness of reported house price indices at the local market levels. The timeliness issue examined in this thesis has not previously been rigorously investigated and this makes the results of this thesis both important and unique for the benefit of both academic research and practical application. Essay One reviews the sale price appraisal ratio (SPAR) method, which has been applied since the 1960s for producing local house price indices at a semi-annual and quarterly basis in New Zealand. Utilizing a variety of statistical tests and comparing this index with the repeat sales and median price index result in the study highlighting the potential of, as well as the problems associated with, a price index produced by the SPAR method at a monthly level. In the following two essays, monthly price indices are tested using empirical real estate research methods in order to examine their usefulness in exploring the research questions as well as revealing the statistical differences between them. Essay Two studies the relationship between sale price and trading volume, and the ripple effect of local house price comovements. The results show that the trading volume generally leads the sale price in the long-run and the ripple effect is most likely constrained within regions. In Essay Two, the monthly SPAR index produces similar statistical results to those estimated by the repeat sales index for large cities. Essay Three is a study on the market efficiency of housing markets. It is found the local housing market is neither weak-form nor semi-strong form efficient. Local house price movements are strongly correlated and are mean reverting towards their long-run equilibrium. It is further concluded that monthly price indices for small cities are problematic due to the problem of small sample size. Overall, the findings in this thesis show monthly house price indices can be generated by using the SPAR method at local market levels. However, this potential is limited to large cities. Further research can focus on improving the quality of monthly price indices for large cities.

The aim of this thesis is to become familiar with the prices that occur in the construction industry, as well as how the price is determined for buildings through the use of computer technology. The basic principles, practices and concepts pricing buildings are defined in the theoretical section, which introduces two specialized programs. In the practical part, these methods are then applied to real buildings. Building object is a storage hall in Brno.

The improper aggregation of commodities can have important consequences when estimating a system of group demand equations. Generally, aggregates are created under the assumptions that intra-group preferences are homothetic and the consumer's utility function is weakly separable over some partition. These assumptions place severe restrictions on the model that can significantly impact parameter and elasticity estimates. An alternative to imposing weak separability is to employ the Generalized Composite Commodity Theorem, which requires the relative intra-group commodity prices to be independent of the group price index. This study compares the results of estimating a demand system for composite beef, pork, and poultry products under the assumptions of weak separability and the Generalized Composite Commodity Theorem. Another important issue related to aggregation is the specification of an appropriate group price index. Price indices consistent with linear homogeneous preferences (a subset of the homothetic class of preferences) and non-homothetic intra-group preferences are identified and it is shown that several of the commonly employed indices are biased in the absence of complete price data. / Master of Science

Submitted by Bruno Monsanto (bruno.monsanto@fgv.br) on 2015-09-01T17:23:32Z No. of bitstreams: 1 Dissertação Mestrado - Bruno Monsanto.pdf: 2081375 bytes, checksum: 410e2f10742d461d025f23c65d43a4f1 (MD5) / Approved for entry into archive by GILSON ROCHA MIRANDA (gilson.miranda@fgv.br) on 2015-09-02T13:59:10Z (GMT) No. of bitstreams: 1 Dissertação Mestrado - Bruno Monsanto.pdf: 2081375 bytes, checksum: 410e2f10742d461d025f23c65d43a4f1 (MD5) / Approved for entry into archive by Marcia Bacha (marcia.bacha@fgv.br) on 2015-09-04T18:27:42Z (GMT) No. of bitstreams: 1 Dissertação Mestrado - Bruno Monsanto.pdf: 2081375 bytes, checksum: 410e2f10742d461d025f23c65d43a4f1 (MD5) / Made available in DSpace on 2015-09-04T18:45:36Z (GMT). No. of bitstreams: 1 Dissertação Mestrado - Bruno Monsanto.pdf: 2081375 bytes, checksum: 410e2f10742d461d025f23c65d43a4f1 (MD5) Previous issue date: 2015-05-22 / This work presents a set of infrastructure price indices, developed with the purpose of providing specific indicators for this sector in Brazil. A survey of the major indices of this nature produced in Brazil and worldwide was held. The main international references were the Organization's for Economic Cooperation and Development - OECD and the European Union member countries. From this analysis, we identified three key issues for the development of work: i) what is the set of infrastructure works to be represented by the indexes and how to delimit this set?; ii) price indexes currently produced in Brazil represent part of this set?; iii) how to develop a set of indices, built on the same methodological basis, nationwide, able to adequately represent this body of work? As a result of work, a set of ten price indices of infrastructure was created built on the same methodological basis, nationwide and offers a range of infrastructure works, whose definition was one of working objects. In addition to the methodological basis for construction of the indices were calculated their respective historical series for the period December / 2000 (base = 100) to February / 2015, from which the indices are analyzed in several ways, for example, through comparative analysis of the ten indices between them and analysis of the behavior of the indices over time, considering the economic context by observing selected indicators. / Essa dissertação apresenta um conjunto de índices de preços de infraestrutura desenvolvidos com o propósito de fornecer indicadores específicos para este setor de atividades no Brasil. Foi realizado um levantamento dos principais índices dessa natureza produzidos no Brasil e no mundo. As principais referências internacionais foram os países membros da Organização para a Cooperação e Desenvolvimento Econômico – OCDE e da União Europeia. A partir dessa análise, foram identificadas três questões fundamentais para o desenvolvimento do trabalho: i) qual é o conjunto de obras de infraestrutura a ser representado pelos índices e como delimitar esse conjunto?; ii) os índices de preços produzidos atualmente no Brasil representam parcial ou totalmente esse conjunto?; e iii) como desenvolver um conjunto de índices, construídos sobre a mesma base metodológica, de abrangência nacional, capazes de representar adequadamente tal conjunto de obras? Como resultado do trabalho, foi desenvolvido um conjunto dez índices de preços de infraestrutura, que contempla todos os requisitos listados acima. Além da base metodológica para construção dos índices, foram calculadas suas respectivas séries históricas para o período de dezembro/2000 (base = 100) a fevereiro/2015, a partir das quais os índices são analisados sob diversos aspectos como, por exemplo, através de análise comparativa dos dez índices entre si e análise do comportamento dos índices ao longo do tempo, considerando o contexto macroeconômico através da observação de indicadores selecionados.

Submitted by André Mazini (andrecmazini@gmail.com) on 2012-04-11T14:47:21Z No. of bitstreams: 1 dissertação FGV-EESP -André Mazini-.pdf: 775030 bytes, checksum: 1fb36bcd27c98537439e2bb8cfeb74cb (MD5) / Rejected by Gisele Isaura Hannickel (gisele.hannickel@fgv.br), reason: Prezado André, O título que consta na ata está diferente do trabalho postado e não consta nenhuma observação do seu orientador no verso da mesma. Título da Ata: "Um novo teste Empírico para modelos teóricos de precificação". Se houve alguma sugestão da banca para esta alteração, seu orientador deverá enviar um e-mail para a Secretaria, a príncipio, para que possamos aprovar o arquivo postado e deverá incluir esta informação e assinar no verso da ata. Caso isto ocorra você deverá efetuar uma nova postagem do arquivo. Att, Secretaria de Registro on 2012-04-11T15:04:05Z (GMT) / Submitted by André Mazini (andrecmazini@gmail.com) on 2012-04-11T17:38:35Z No. of bitstreams: 1 dissertação FGV-EESP -André Mazini-.pdf: 775019 bytes, checksum: 5d3e0617b3f1cee5ce4ceeb549021f8b (MD5) / Approved for entry into archive by Gisele Isaura Hannickel (gisele.hannickel@fgv.br) on 2012-04-11T17:48:47Z (GMT) No. of bitstreams: 1 dissertação FGV-EESP -André Mazini-.pdf: 775019 bytes, checksum: 5d3e0617b3f1cee5ce4ceeb549021f8b (MD5) / Made available in DSpace on 2012-04-11T17:50:55Z (GMT). No. of bitstreams: 1 dissertação FGV-EESP -André Mazini-.pdf: 775019 bytes, checksum: 5d3e0617b3f1cee5ce4ceeb549021f8b (MD5) Previous issue date: 2012-03-07 / This paper proposes a new test to distinguish between macroeconomic price-setting models. We show that the usual conclusions of negative correlation between current inflation and duration of a price, an indication of state-dependency, do not survive the control for inflation expectations. When we do that, the negative correlation is between expected inflation and the duration of a price, indicating endogenous-time-dependency. We argue that the previous results were possibly suffering from omitted variable bias. / Este artigo propõe um novo teste para distinção entre modelos macroeconômicos de precificação. Onde testes antigos concluíram haver uma relação negativa entre inflação corrente e duração de um preço, indicando estado-dependência, nosso teste indica que a relação verdadeira é entre inflação esperada e duração do preço, indicando tempo-dependência-endógena. Argumentamos que os resultados previamente encontrados possivelmente sofreram de viés de variável omitida.

Bewertungen von Immobilien sollen den Marktwert einschätzen und sind notwendig für Kauf-, Verkaufs- und Bauentscheidungen, für die Kreditvergabe und für die Besteuerung. Trotz dieser eindeutigen Aufgabenstellung existierten unterschiedliche Verfahren, mit welchen Marktwerte ermittelt werden können. Ein Bewertungsverfahren soll einerseits mit ökonomischer Theorie vereinbar sein und andererseits Bewertungen generieren, die beobachtete Transaktionspreise gut vorhersagen. Die Dissertation analysiert die drei wichtigsten Bewertungsansätze Sachwert-, Vergleichswert- und Ertragswertverfahren, zeigt das jeweils zugrundeliegende Marktmodell und evaluiert die kodifizierten Verfahren nach der Wertermittlungsverordnung (WertV) anhand von beobachteten Transaktionen. Darüber hinaus gibt die Dissertation einen Überblick zu Immobilienpreisindizes und zu hedonischen Methoden. Für die ökonometrischen Analysen wurden umfangreiche Daten zum Berliner Immobilienmarkt verwendet. / Appraisals should assess the market value of properties and are necessary for buying, selling or building decisions, for lending and for taxation. Despite this unambiguous task different techniques exist for ascertaining market values. An valuation approach should be in accordance with economic theory and should generate appraisals, which are reliable estimates for transaction prices. This dissertation analyzes the three most important valuation approaches, i.e. cost, sales comparison, and income approach, shows the underlying market models and evaluates the valuation techniques that are codified in the German Regulation on Valuation (WertV). For the latter evaluations, appraisals are compared with observed transaction prices. In addition, the dissertation gives an overview on real estate price indices and on the hedonic approach. Extensive data on Berlin's real estate market are used for the econometric analysis.

Made available in DSpace on 2016-03-15T19:26:16Z (GMT). No. of bitstreams: 1 Helene Albuquerque Rebelo 1.pdf: 1046658 bytes, checksum: 341e6608b9c7f265ac5e1303f07c7667 (MD5) Previous issue date: 2014-10-23 / Fundo Mackenzie de Pesquisa / The dissertation examines the behavior of the exchange rate in the long term from the perspective of the classical model of purchasing power parity theory (PPP), developed empirically by Cassel and the alternative model proposed by Basso originating from the Marxist benchmark, which emphasizes prices and productivities to determine the exchange rate. The exchange rate behavior is examined for three countries over the 1977-2006 period, with annual frequency. To test the models, it was used the consumer price index (CPI), the GDP, the value-added price index and gross producer price index (EU KLEMS database). The essay uses the causality tests of Johansen, the Dickey-Fuller and Phillips-Perron unit root tests, the VAR (vector autoregression) and VEC (vector error correction) models and performing a projection with the Model Confidence Set. It is ascertained that PPP was not supported for any of the 12 models generated. In Basso s approach, the 48 models generated, cointegration was found in only four models, therefore it is not possible to generalize the new model. / A dissertação examina o comportamento da taxa de câmbio no longo prazo sobre a perspectiva do modelo clássico da paridade do poder de compra (PPC) ou purchasing power parity theory (PPP), desenvolvido empiricamente por Cassel e do modelo alternativo proposto por Basso oriundo do referencial marxista, enfatizando preços e produtividades para determinar a taxa de câmbio. Examina-se o comportamento da taxa de câmbio para três países no período de 1977 a 2006, com frequência anual. Para testar os modelos, foram empregados o índice de preço ao consumidor (IPC), o deflator do PIB, o deflator dos valores agregados e o deflator de produção total (base de dados EU KLEMS). O trabalho utiliza o teste de causalidade de Johansen, os testes de raiz unitária de Dickey e Fuller e Phillips-Perron, os modelos de VAR (vetores autorregressivos) e VEC (vetores autorregressivos com correção de erro) e é feito projeção com Model Confidence Set. Constata-se que a PPP não foi corroborada para nenhum dos 12 modelos gerados. Na abordagem de Basso, dos 48 modelos gerados, encontrou-se cointegração apenas em quatro, portanto, não é possível generalizar o novo modelo.