由於住宅價格變動毫無預警制度，人民往往憑著個人主觀的判斷而決定何時購屋或售屋，而此種主觀判斷住宅市場利多及利空的觀念，對住宅市場的供需會產生失衡現象，因此是否可從經濟面的訊息找到住宅價格變動的答案，使住宅價格在尚未變動前，政府即已掌握資訊，提前做好穩定住宅價格的因應對策，使民眾依其需要而購屋，則是本研究之主要目的。 　　本研究從文獻中整理出影響住宅價格變動的七個總體經濟變數，這些總體經濟變數包含工資、物價、所得、貨幣供給額、股價、匯率及利率等，並利用向量自我迴歸模式(VAR)進行實證，以便較客觀的獲得變數間的落後期數及暸解變數間雙向、單向及領先、同步、落後情形，且進一步探討住宅價格與每一個總體經濟變數間影響程度大小及影響情形，以釐清各變數之間的關係。 　　本研究利用VAR模型進行住宅價格與總體經濟變數關係的研究，經由實證，得到下列的結論： 　　一、實證結果方面 　　本研究之實證主要有因果關係檢定與分析、變異數分解之分析及衝擊反應之分析三方面，其實證結果如下所述。 　　（一）因果關係檢定與分析 　　由因果關係檢定與分析中，得到股價、物價、匯率、貨幣供給額及利率均能做為住宅價格變動的領先指標。 　　（二）變異數分解之分析 　　由住宅價格之變異數分解中，得知住宅價格自身的解釋程度僅占三分之一，另三分之二被其他的總體經濟變數所解釋，顯示住宅價格受總體經濟變數的影響相當大；而從其他總體經濟變數之變異數分解中，得知住宅價格變動會干擾到總體經濟變數，而使總體經濟變數受干擾而變動變動。 　　（三）衝擊反應之分析 　　從總體經濟變數對住宅價格的衝擊反應分析圖中可以明顯看出除工資外，其餘總體經濟變數變動對住宅價格造成的衝擊均相當明顯，但匯率及利率對住宅價格的衝擊是負向的。 　　住宅價格對所得、股價、匯率及利率的衝擊相當明顯，而其對匯率的衝擊是負向。 　　二、政策應用方面 政府的決策過程中常會有時間落後的現象，而本研究實證的目的則是要使政府能事先掌握住宅價格的變動，並提前做好穩定住宅價格的因應對策，減少政府決策過程的時間落後現象，而實證結果應用至政策方面的內容則由以下說明之。 　　（一）藉由因果關係檢定與分析的實證內容，可以縮短政府對住宅價格不合理變動問題認定落後的時間。 　　（二）從變異數分解之分析的實證內容中，可以使決策者在解決住宅價格問題時，將行動落後的時間減少。 　　（三）由衝擊反應之分析中，可以使政府在執行穩定住宅價格政策時，將衝擊落後的時間縮小。 / Since there is no alarm system in the change of housing prices, people often decide when to buy or when to sell based on personal and subjective judgement. Such concept to judge subjectively whether the housing market is bull or bear will cause unequilibrium in the supply and demend of the housing market. There it is possible to find out the answers to the change of housing prices from economic side so that the government can have enough information and can be prepared in the reaction to stabilizing the housing prices, and so that the public can buy house according to their needs is the main purpose of this project. 　　Seven variables in macroeconomics influencing the change of housing prices have been taken from reative literature, including wage, commodity price, income, money supply, stock price, exchange rate, and interest rate. VAR has been employed to verify so that the more objective lagging period among variable can be known, and the bi-directional, uni-directional, leading, contemporaneous, and lagging situation among variables can be understood. Furthermore, the degree and the status of influence of each macroeconomic variable to the housing price will be investigated to clarify the relations among the variables. 　　The present project investigate the relations between housing price and macroeconomic variables. We have the following findings: 　　I、In Empirical Study: 　　The empirical study in this project includes causal relation test and analysis, the analysis of variable decompositon, and the analysis of impact response. The results are shown in the following: 　　(I) Causality Test and Analysis 　　In the causality test and analysis, we find out that stock price, commodity price, exchange rate, money supply and interest rate all can be the leading indicators in the change of housing prices. 　　(II) The Analysis of Variable Decomposition 　　It is learned from the variable decomposition of housing prices that housing price can only explain one third of the cause in its change, the other two thirds are explained by other macroeconomic variables. It shows that housing prices are subject to the influence of macroeconomic variables greatly. 　　From the variable decomposition of other macroeconomic variables, we know that the change in housing prices will affect macroeconomic variables so that the macroeconomic variables will change. 　　(III) The Analysis of Impact Response 　　It can be obviously seen from the analysis figure of the impact response of the macroeconomics to housing prices, all macroeconomic variables will cause obvious impact to housing prices expect for wage. However, both exchange rate and interest rate have negative impact to housing prices. 　　Housing prices' impact to income, stock prices, exchange rate and interest rate is quite obvious, among which, the impact to exchange rate is negative. 　　II、Policy Application 　　It is a common phenomenon that there often will be lagging in time in government's decision making. The purise of the empirical study in this project is to let the government to know in advance the change of housing prices and to let the government to know in advance the change of housing prices and to let the government be prepared in the reaction of stabilizing the housing prices to minimize the lagging in the decision making process. The contents of application of the empirical study to policy are explained in the following: 　　(I) With the empirical results of the change of the causality test and analysis, the time for the government to recognize the unreasonable changes in housing prices can be shortened. 　　(II) With the empirical results of the analysis of variable decomposition, the decision makers' lagging in the action responding to housing pricescan be minimized. 　　(III) With the analysis in impact response, the lagging in impact will be minimized when the government executing her housing price stabilizing policy.

本文利用晚近發展出來的單根檢定法以及共積檢定法，實証分析美、日兩國二次大戰以後企業購併與總體經濟變數間之關係。其實証方法與實証結果如下：運用ADF 檢定方法對購併、股價、國民生產毛額、利率，作單根檢定，發現美日兩國之購併、股價與國民生產毛額呈一階差分恆定狀態。 此外，本文應用Engle and Granger(1987) 的共積模型分析，將同樣為一 階差分恆定的變數做共積檢定，發現美日兩國之購併與股價、國民生產之間，皆具有長期共同移動的趨勢，因此可以建立一包含長、短期關係之誤差修正模型。本文之實証結果顯示：美國的企業購併與股價水準有正向且顯著之長期穩定關係，而與國民生產毛額則有負向且顯著的長期穩定關係；日本的企業購併與股價及國民生產毛額也有長期穩定之關係，惟影響方向與美國相反。另外，因果關係檢定結果顯示，美國之股價與利率對購併呈單向因果關係，而日本之股價與購併則呈雙向因果關係。由這些實証結果可知，購併風潮之形成，實肇因於總體經濟之波動，而不同國家之企業，由於法令規章、經濟結構、社會制度之不同，因而會有不同之反應。

過去文獻對於房價的研究，不管是應用橫斷面分析探討個體層面影響房價之因素，或是應用時間數列分析房價的長期勢，抑或是在分析房價與總體經濟變數間的關係時，多忽略不同次級市場間的互動關係，然而不同次級市場的房價常因為替代性或者是互補性而產生波及效果。 因此本研究將次級市場以行政區域來劃分，以北部地區的四個行政區（台北市、台北縣、基隆市、桃園縣）為研究範圍，利用時空數列分析方法，首先以單根檢定與共整合方法分析四個次級區域的房價時間數列是否有穩定特性，區域房價間在長期是否具有一種穩定的線性組合關係，以說明四個次級區域間房價的異質性與相依性。其次，應用具有誤差修正機制的向量自我相關模型，亦即VECM（Vector Autoregression in Error Correction Model），利用誤差修正模型探討區域房價在次級區域短期失衡時的調整速率，並以Granger因果檢測其間的互動關係及區域房價在時間上、空間上的領先、落後關係。最後對於影響區域房價的重要總體變數納入考量，分析重要區域總體變數在空間上與時間上的相關性與互動性。

本研究係探討匯率與總體經濟之關聯性，以中國大陸1996第一季至 2013年第一季之總體經濟變數，共計樣本數為69筆季資料。先以1996第一季至 2013年第一季全期數據進行實證分析。再以2005年7月為分界點，分為1996年第一季至2005年第二季及2005年第三季至2013年第一季數據分別進行實證分析。 本論文就REER、GDP、CPI、M2、UNEMP、CHIBOR、FDI、OPEN等總體經濟變數，以單根檢定及建構向量自我迴歸模型進行實證分析，並以Granger因果關係檢定、衝擊反應分析及預測誤差變異數分解，以了解匯率與總體經濟相互間之關係。 實證結果發現，中國大陸匯率與總體經濟間的關係自2005年7月21日匯率改革後逐漸增強，但整體言之匯率與總體經濟間之傳導能力仍然不大，人民幣匯率的變動主要受其自身影響較多，受總體經濟變數的相互影響較小，顯示其外匯市場的開放程度與一個真正開放的經濟體還是有些許差距。 / This research examines the correlation between foreign exchange rates and macroeconomics by using the data of economic variables of China from the 1st quarter of 1996 to the 1st quarter of 2013. The sample contains 69 quarterly data during the entire period, while the reform of Chinese exchange rate on 21st July 2005 is a crucial division. In order to find the correlation between foreign exchange rates and macroeconomics, the research examines the economic variables such as REER, GDP, CPI, M2, UNEMP, CHIBOR, FDI, and OPEN by using unit root test, vector autoregression model, Granger causality test, impulse response function and variance decomposition impulse response function. The result of the tests indicates that after the reform of Chinese exchange rate on 21st July 2005, the correlation between exchange rates and macroeconomics has been enhanced, but the connection is not prominent. In other words, the fluctuation of Renminbi is mainly affected by the nation’s policy instead of its macroeconomic factors. Hence, the openness of the Chinese foreign exchange market is still distant from a real open economy.

In this work, we study and extend algorithms for Sparse Regression and Causal Inference problems. Both the problems are fundamental in the area of Data Science. The goal of regression problem is to nd out the \best" relationship between an output variable and input variables, given samples of the input and output values. We consider sparse regression under a high-dimensional linear model with strongly correlated variables, situations which cannot be handled well using many existing model selection algorithms. We study the performance of the popular feature selection algorithms such as LASSO, Elastic Net, BoLasso, Clustered Lasso as well as Projected Gradient Descent algorithms under this setting in terms of their running time, stability and consistency in recovering the true support. We also propose a new feature selection algorithm, BoPGD, which cluster the features rst based on their sample correlation and do subsequent sparse estimation using a bootstrapped variant of the projected gradient descent method with projection on the non-convex L0 ball. We attempt to characterize the efficiency and consistency of our algorithm by performing a host of experiments on both synthetic and real world datasets. Discovering causal relationships, beyond mere correlation, is widely recognized as a fundamental problem. The Causal Inference problems use observations to infer the underlying causal structure of the data generating process. The input to these problems is either a multivariate time series or i.i.d sequences and the output is a Feature Causal Graph where the nodes correspond to the variables and edges capture the direction of causality. For high dimensional datasets, determining the causal relationships becomes a challenging task because of the curse of dimensionality. Graphical modeling of temporal data based on the concept of \Granger Causality" has gained much attention in this context. The blend of Granger methods along with model selection techniques, such as LASSO, enables efficient discovery of a \sparse" sub-set of causal variables in high dimensional settings. However, these temporal causal methods use an input parameter, L, the maximum time lag. This parameter is the maximum gap in time between the occurrence of the output phenomenon and the causal input stimulus. How-ever, in many situations of interest, the maximum time lag is not known, and indeed, finding the range of causal e ects is an important problem. In this work, we propose and evaluate a data-driven and computationally efficient method for Granger causality inference in the Vector Auto Regressive (VAR) model without foreknowledge of the maximum time lag. We present two algorithms Lasso Granger++ and Group Lasso Granger++ which not only constructs the hypothesis feature causal graph, but also simultaneously estimates a value of maxlag (L) for each variable by balancing the trade-o between \goodness of t" and \model complexity".

Trade liberalization in Kenya started in the early 1980s with the structural adjustment programmes, and continued under the multilateral framework of the WTO. During the same period, the incidence of poverty and level of inequality also worsened. The government’s focus on trade negotiations has been to ensure that there is policy space for the daily running of the economy even though welfare impacts are also important. Non-state actors have argued that trade liberalization has negatively affected the poor; particularly the farmers, since they cannot compete with the developed countries whose farmers enjoy significant government support through subsidies, making their products much cheaper in the world market. Government officials, on the other hand, contend that trade liberalization is good as it brings in competition and transfer of technology which is good for an economy. It is important to examine how trade liberalization has affected household’s welfare in Kenya, given that this kind of analysis has not been conducted in Kenya. This study is unique because it does not assume the existence of a trade liberalization– poverty relationship, unlike most studies. It uses a multi-method approach to first test the hypothesis that there is no statistically significant relationship between trade liberalization and poverty, it further tests for multiplier effects of trade liberalization on poverty determinants. Trade Liberalization and poverty is found to have a stochastic relationship, furthermore investments and capital stock were found to significantly affect poverty determinants in the stochastic model. Due to unavailability of household welfare measure data in time series, a CGE model was used to establish the dynamics of trade liberalization on poverty at a point in time using the 2003 Social Accounting Matrix Data for Kenya. Overall, trade liberalization accompanied by FDI had the greatest impact on household welfare. Trade liberalization had a positive impact on household welfare since household incomes and consumption increased. Micro simulations results, based on changes in consumption, also showed that poverty incidence reduced for all households, even though the urban households experienced higher decreases. The study found that there was little difference in protecting sensitive products and not protecting them; secondly, trade liberalization accompanied by foreign direct investment had greater impact on improving the household welfare. Consumption and incomes increased, resulting in overall poverty reduction. The welfare of urban households was much higher than rural households in terms of income and consumption increases. However, income inequality was much higher in urban than rural areas. / Economics / D. Litt. et Phil. (Economics)

Exponential smoothing algorithms are very attractive for the practical world such as in industry. When considering bivariate exponential smoothing methods, in addition to the properties of univariate methods, additional properties give insight to relationships between the two components of a process, and also to the overall structure of the model. It is important to study these properties, but even with the merits the bivariate exponential smoothing algorithms have, exponential smoothing algorithms are nonstatistical/nonstochastic and to study the properties within exponential smoothing may be worthless. As an alternative approach, the (bivariate) ARIMA and the structural models which are classes of statistical models, are shown to generalize the exponential smoothing algorithms. We study these properties within these classes as they will have implications on exponential smoothing algorithms. Forecast properties are studied using the state space model and the Kalman filter. Comparison of ARIMA and structural model completes the study. / Mathematical Sciences / M. Sc. (Statistics)

This study provides evidence of the relationship between bank-granted credit and business cycles in South Africa. The study is conducted in three phases, namely qualitative research (Phase I), quantitative research (Phase II) and econometric analysis (Phase III). A sequential (connected data) mixed methodology (Phase I and II) is used to collect and analyze primary data from market participants. The qualitative research (Phase I) involves structured interviews with influential or well informed people on the subject matter. Phase I of the study is used to understand the key determinants of bank credit in South Africa and to appreciate how each of the credit aggregates behaves during alternate business cycles. Qualitative survey results suggest key determinants of commercial bank credit in South Africa as economic growth, collateral value, bank competition, money supply, deposit liabilities, capital requirements, bank lending rates and inflation. The qualitative results are used to formulate questions of the structured survey questionnaire (Quantitative research- Phase II). The ANOVA and Pearman’s product correlation analysis techniques are used to assess relationship between variables. The quantitative results show that there is direct and positive relationship between bank lending behavior and credit aggregates namely economic growth, collateral value, bank competition and money supply. On the other hand, the results show that there is a negative relationship between credit growth and bank capital and lending rates. Overall, the quantitative findings show that bank lending in South Africa is procyclical. The survey results indicate that the case for demand-following hypothesis is stronger than supply-leading hypothesis in South Africa. The econometric methodology is used to augment results of the survey study. Phase III of the study re-examines econometric relationship between bank lending and business cycles. The study employs cointegration and vector error correction model (VECM) techniques in order to test for existence of long-run relationship between the selected variables. Granger causality test technique is applied to the variables of interest to test for direction of causation between variables. The study uses quarterly data for the period of 1980:Q1 to 2013:Q4. Business cycles are determined and measured by Gross Domestic Product at market prices while bank-granted credit is proxied by credit extension to the private sector. The econometric test results show that there is a significant long-run relationship between economic growth and bank credit extension. The Granger causality test provides evidence of unidirectional causal relationship with direction from economic growth to credit extension for South Africa. The study results indicate that the case for demand-following hypothesis is stronger than supply-leading hypothesis in South Africa. Economic growth spurs credit market development in South Africa. Overall, the results show that there is a stable long-run relationship between macroeconomic business cycles and real credit growth in South Africa. The results show that economic growth significantly causes and stimulates bank credit. The study, therefore, recommends that South Africa needs to give policy priority to promotion and development of the real sector of the economy to propel and accelerate credit extension. Economic growth is considered as the significant policy variable to stimulate credit extension. The findings therefore hold important implications for both theory and policy. / Business Management / D.B.L.

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / Globalization provoked in financial markets by means stock exchanges an interchange among the markets over the world. The aim of this study was to examine the relationship of the ten major main economic index of the world represented in New York (DJIA, S&P500 e Nasdaq), Tokyo (NIKKEI 225), London (FSTE 100), São Paulo (IBOV), Shanghai (SSE180), Paris (CAC-40), Frankfurt (DAX-30) and Buenos Aires (Merval) and looking for its co-integration, to demonstrate the behavior of these indexes and the long run equilibrium, from January of 2010 to March of 2011. To investigate the equilibrium and the long rum behavior the error correction model was used jointly with co-integration test and impulse response based on Cholesky decomposition. The results of this study show that the index of stock markets has long term equilibrium, and American markets, Argentina and English showed a strong influence over other markets. With this research we can infer that a relationship exists between the stock markets under study, confirming that the economy in a country can influence the others. In this sense, the contribution of this study, given this range of discussions involving the interconnection of economies with respect to trades made on the stock exchanges, was to show the relationships and influences in the world. / A internacionalização somada à abertura dos mercados financeiros transformou as economias antes fechadas em economias abertas, provocou um intercâmbio entre as economias mundiais por meio das bolsas de valores. O objetivo deste estudo é examinar a relação entre os dez principais índices econômicos do mundo, sendo eles: Nova York (DJIA, S&P500 e Nasdaq), Tóquio (Nikkei 225), Londres (FSTE 100), São Paulo (IBOV), Shangai (SSE180), Paris (CAC), Frankfurt (DAX-30) e Bueno Aires (Merval), por meio da análise de co-integrações para demonstrar o comportamento desses índices e seus equilíbrios no período de janeiro de 2010 a março de 2011. Para investigar e verificar o comportamento em longo prazo, foi utilizado o modelo de correção de erros e teste de impulso-resposta baseado na decomposição de Cholesky. Os resultados deste estudo mostram que existe equilíbrio em longo prazo entre os índices do mercado de ações. Os mercados americano, argentino e inglês mostraram forte influência sobre os demais mercados. Com esta pesquisa, verifica-se que existe uma relação entre os mercados de ações estudados, confirmando que a economia de um país influencia as demais. A contribuição deste estudo é verificar a assertiva das discussões atuais sobre a dependência das economias mundiais com as negociações por meio da bolsa de valores.

This study aims to analyse the precrisis period on the oil markets with a primary objective of assessing the role of speculation in the commodity's price development and its volatility. First it depicts the rapidly increasing speculative activity on the futures market together with the parallel oil price surge. The speculation is initially proxied by non-commercial traders' positions and subsequently quantified by Working's T-index. The paper then uses speculative traders' positions and both spot and futures prices to test for Granger causality within the framework of VAR models. For the sake of consistency it also evaluates causal links between speculation and inventories level. Further the study investigates the speculation impact on volatility of oil prices by employing various approaches in volatility quantification including GARCH models. Contrary to expectations we find that the speculatio's impact on both prices and their volatility is rather insignificant. In the last chapter we therefore seek for an explanation of the oil price developments by examining the market fundamentals. The interaction of supply and demand finally gives substantial evidence for understanding the price developments in the precrisis period.