Dissertation > Excellent graduate degree dissertation topics show

Prediction models and empirical analysis of real estate based on the gray theory and multiple linear regression analysis

Author: DingZuo
Tutor: GanXiaoRong
School: Kunming University of Science and Technology
Course: System theory
Keywords: Grey Theory Multiple linear regression analysis Real estate
CLC: F293.3
Type: Master's thesis
Year: 2009
Downloads: 466
Quote: 0
Read: Download Dissertation

Abstract

The classic multivariate linear regression model as a commonly used multivariate statistical methods, its principle is clear, simple model, ease of application, and a very wide range of applications in the industrial and agricultural production and scientific research. For example, in many areas of medicine and health, weather forecasting, geological exploration, have to use the classic multiple linear regression model. Since the housing reform in 1998, China's real estate industry has been rapid development, has made a significant contribution to the growth of the national economy and gradually become the pillar industry of China's national economy. But China's real estate market due to a late start, combined with the imperfect development, while showing a more obvious fluctuations ups and downs and some other typical primary market characteristics. In this case, the government will take some measures to guide the real estate business to make the right investment. A city's commercial housing sales price (yuan / square meter) is usually subject to the city's residential land premium ($ / sq m), the average wage ($ / year), urban residents per capita disposable income ($ / year) affected and constrained. Before deciding to invest in, the real estate business will often predict the city's commercial housing sales price (yuan / square meter), the traditional forecasting methods is the classic multiple linear regression analysis, that the city's residential land premium ($ / m2 ), the average wage ($ / year), urban residents per capita disposable income ($ / year) as the independent variable, response variable commodity housing sales price (yuan / square meter) to the least squares estimation to predict prices . Although this method is easy to understand, but there are also some problems: First, it is not real-time tracking of the response variable changes; Second, the classic multiple linear regression analysis model minority sample morbidly sensitive data, often due to a small amount of morbid data affect the fitting effect; Third, the amount of data required by the the classic multiple linear regression model. These problems are likely to result in the real estate business to make the wrong decision analysis, thus affecting the healthy development of China's national economy. Solve the above problem, we propose a new method, which is based on the gray theory and multiple linear regression analysis of the real estate forecast model to forecast prices. This method is the first by the GM (1,1) model in the gray theory to accurately forecast residential land premium ($ / sq m), the average wage ($ / year), the per capita disposable income of urban residents ($ / year ), and then using the classic multiple linear regression model to predict prices. The advantage of this method is that it is not only to avoid a small number of pathological data for fitting the effect of impact, and the little amount of data required. Finally, select Xi'an, Shaanxi Province, Xianyang City's real estate industry as analysis objects and verify the correctness of the real estate forecast model based on gray theory and multiple linear regression analysis, analysis results show that this method can be used to predict the real estate commercial housing sales The average price to make the right decisions, the real estate business has important reference value and guiding significance.

Related Dissertations

CLC: > Economic > Economic planning and management > Urban and municipal economy > Urban Economics and Management > The real estate economy
© 2012 www.DissertationTopic.Net Mobile