Summary Paper of Research Paper
Analysis to Study Housing Values in Boston
Introduction
The analysis of company activities, as well as the enactment of its plans, applies the concept of linear regression as the technique of analysis. Boston is a place in England that covers both the Boston Municipality, as well as the metropolitan region (Bluestone et al. 41). The area is famous as Combined Statistical Area, consisting of the Manchester Municipality, the Cape Cod in Massachusetts, the Worcester, the Providence, as well as the South Coast Region. The metropolitan statistical area entails the part of Massachusetts, the south coast region, and the Cape Cod region.
The population of the people of Boston is 4, 732, 161 based on the United States metropolitan statistical records, 2014. The Boston attracts a large number of individuals because it is one of the most commercial and cultural zones in the United States (Bluestone et al. 41). The region is well developed because it has educational facilities well known across the world, like the Harvard University in Cambridge, and Massachusetts Institute of Technology.
Additionally, the region is home to various communities from different parts of the world (HUD Sustainable Communities Initiatives, Para 3). Housing in the area became of great concern, with the Standard & Poor's Case-Shiller Home Price Indices attracting attention from various parties. Statistical procedures aided the process home valuation, focusing on the suburb regions.
The factors to consider in the process include transport, where the area is accessible by some highways, airports, bridges and tunnels, and the modern railway and bus stations (Bluestone et al. 41). Many factors influence the value of a house in Boston like the distance from the main terminal like a bus station. Other factors to consider include the duration of the construction of the house, space available, the security of the area, as well as the drainage system for the home.
The features of the region as mentioned above makes it paramount to study the topic. The economic growth and other factors associated with the development in Boston makes it necessary to explore the topic. Additionally, the analysis encourages the application of the linear regression techniques for data analysis, a method that attaches quality skills on the study (Correa et al. 2-3). The topic also presents the way of life of the various groups that make up the community living in Boston. Additionally, the issue investigates issues about life for example matters relating to housing or home valuation.
The predictive analysis protocols like the simple linear regressions are the most suitable for achieving the goal. The house prediction analysis in the Boston suburb, it is imperative to consider the data on the various variables. Additionally, it is also important to examine variability between the three significant components of the multiple linear regression (Correa et al. 2-3).
Importance of the Methods Used
Linear regression is important in economics because it enables the quantification of the relationship between certain economic variables (Fitzenberger, Roger, & José 8). For instance, the linear regression contributes in the analysis of home valuation in Boston by enabling the determination of the relationship between the Case-Shiller Home Price Index, rates of rental vacancy, growth in real output, rate of civil unemployment, and the average weekly income as the dependent variables against the housing values in Boston, as the independent variable (Fitzenberger, Roger, & José 8). The economic importance of such comparison is to help one to make a good investment choice by assessing the characteristics of Boston community about the home valuation process.
The R programming leads to the determination of the R-value in each section of the linear regression process, to help in monitoring the accuracy of the regression equation (Cameron, & Pravin 275). The accurate regression equation tends to give a reliable information that is helpful in making good economic decisions.
Moreover, the comparison of the p-values with the R-values for each analysis makes it possible for one to choose to either accept or reject the respective hypothesis depending on its economic sense relative to the topic of study (Cameron, & Pravin 275). Therefore, it gives an avenue for one to assess the effects of both outcomes of the process, through analyzing the economic impacts of the issue under study. The hypothesis is acceptable for p-values above 0.05 and rejected for p-values below 0.05.
The linear regression model aids the forecasting of the values in the model. It enables the determination of the extent of changes observed in the dependent variables when an alteration of the independent variables occurs (Y). The regression model shows point estimates, as the price of housing in Boston after the next five years by application of the linear regression model.
Additionally, the linear regression model helps in identifying the extent of effects of the independent variables on the dependent variable. Linear takes the form of Y= c + bx. Y represents the secondary factors; c is a constant factor, b stands for regression and x is the independent variable. The next part of the paper involves a summary of the events and findings of the analysis.
The Influence and Summary of the Results
For each of the values obtained in the results and findings section, it is prudent to attach the economic sense onto the outcome of the analysis. To begin with, it is evident that the home valuation process in Boston creates a convergence of many variables that determine the conclusion and decision based on the R-values and P-values of each outcome.
Regarding the Case-Shiller Home Price Index, the p < 0.05, means that there is no economic sense in accepting the null hypothesis, because there exists no significant statistical relationship between the price index and housing values in Boston. Hence, the index is not applicable in determining the price of houses in the region. The same case applies to the sale of condominiums, total housing permits and the permits for 5+ unit housing, the sale of single-family homes, and home ownership rates have p-values that are below 0.05. Therefore, they cannot be factors to consider in the assessment of the economic effects of housing values in Boston because there are no statistically significant relationships between the factors and the housing values.
However, the rental vacancy rates, growth in real output, civil unemployment rates, the sale to two unit and three unit structures, as well as annual foreclosure petitions and deeds, possess the p-values that are above 0.05. Hence, they are the factors determining the housing valuation in Boston, because they affect the economy of the region. The hypotheses relating to the factors mentioned show a statistically significant correlation with housing values in Boston. Therefore, based on the statistics that follow, I suppose the economic fluctuation of the factors with greater p-values than 0.05, lead to changes in housing values in Boston. Finally, the small deviations from the 0.05 make the research conducted very realistic and occur with high-level accuracy.
Results and Findings
The hypothesis is that the Case-Shiller Home Price Index relates to the housing values in Boston. The Multiple R value (0.90634069) indicates that there exist a strong positive linear relationship between housing values in Boston and the Case-Shiller Home Price Index (O'Rourke, Larry, & Edward 351). The process of testing the hypothesis, the p-value of 0.012747307 is less than 0.05. Therefore, there is the rejection of the hypothesis that there is no statistically significant relationship between the values of houses in Boston and Case-Shiller Home Price Index
Rental Vacancy Rates
The null hypothesis entails the premise that there exists no significant relationship between the rates of rental vacancy and the housing values in Boston. Hence, the multiple R statistics of 0.510123215, shows the presence of a relatively positive linear relationship between the housing values within Boston (O'Rourke, Larry & Edward 351). In that regard, the p-value of 0.301188762 supersedes 0.05. As a result, the null hypothesis is accepted, and the one stating that there exists a statistically significant relationship between the rental vacancy rates and housing values in Boston is overruled.
Growth in Real Output
The growth in the output was hypothesized as one of the factors affecting the housing values in Boston region (Bureau of Economic Analysis). The hypothesis is that growth in the production has not statistically significant concerning the accommodation in Boston. Multiple R statistics of 0.216199484 indicates that ere there exists no relationship between the increase in the output and the housing values in Boston (O'Rourke, Larry, & Edward 351). As a result, the p-value of 0.680753595 larger than 0.05 implies that if a linear relationship exists, then the null hypothesis that the growth in real output lacks the statistically significant association with the housing values in Boston would be acceptable. Therefore, the alternative hypothesis is rejected.
Civil Unemployment Rate
The null hypothesis is that there exists no statistically significant relationship between the civil unemployment rate and housing in Boston. The Multiple R statistic is 0.753193906, which indicates a strong correlation between unemployment and housing values (O'Rourke, Larry, & Edward 351). The p-value is 0.083852992 is larger than 0.05. Therefore, the null hypothesis that there is no statistically significant relationship between the local unemployment rate and the housing values in Boston is accepted, and the contrary hypothesis is rejected.
Real Average Weekly Income
The Multiple R statistic of 0.849403791 shows that there exists a strong linear relationship between real average weekly income and the housing values in Boston (O'Rourke, Larry, & Edward 351) the p-value is 0.032311125. Hence p<0.05 .
Sales of Single Family Homes
The Multiple R Statistic is 0.818045758, confirming the existence of a positive relationship between sales of single-family homes and housing values in Boston (O'Rourke, Larry, & Edward 351). Additionally, the p-value is 0.046154034, a value that is less than 0.05.
Home Ownership Rates
The Multiple R statistics 0.837600583, confirming that there is a positive linear relationship between home ownership and housing values (O'Rourke, Larry, & Edward 351). P-value was 0.03741883, smaller than 0.05, confirming the existence of the relationship between homeownership rates and the housing values and rejection of the hypothesis.
Sale of Condominiums
The above analysis entailed the testing of the null hypothesis of the relationship that the relationship was not significant. The Multiple R statistic was 0.834209712 confirming the existence of a positive correlation (O'Rourke, Larry, & Edward 351). The p-value is 0.038951139. Since the value is less than 0.05, leading to the rejection of the null hypothesis.
Sale of Two Unit Structures
The operating null hypothesis involved the claim that there was no statistical linear relationship between the sale of unit structures and housing in Boston (O'Rourke, Larry & Edward 351). The Multiple R value is 0.398308862 meaning that a positive relationship exists, and the p-value of 0.434132548, confirming the validity of the hypothesis.
Sale of Three Unit Structures
The analysis of the information gave a Multiple R statistic of 0.557306391, proving the existence of a moderate positive relationship between the sale of three unit houses and the housing values in Boston (O'Rourke, Larry, & Edward 351). The ANOVA test showed a p-value of 0.557306391, confirming the acceptance of the hypothesis.
Total Housing Permits
The null hypothesis was that there existed no statistically significant relationship between the total housing permits and the housing values in Boston. The analysis of the information gave a Multiple R statistic of 0.929186047, confirming a linear relationship between the total housing permits and the housing values in Boston (O'Rourke, Larry, & Edward 351). The p-value of 0.007344372 proposes the rejection of the null hypothesis because the value is less than 0.05.
Permits for 5+ Housing Units
Annual Foreclosure Petitions
The petitions were hypothesized to affect the housing values in Boston. The application of the regression test indicated the existence of a moderate as well as a positive linear relationship between the annual foreclosure of petitions and housing values in Boston. The evidence is Multiple R statistic of 0.678054237 (O'Rourke, Larry, & Edward 351). The p-value of 0.138788921 from the ANOVA test above 0.05 meaning that the hypothesis that there exists a statistically significant relation between the annual foreclosure petitions and the housing in Boston is rejected.
Annual Foreclosure Deeds
The use of the linear regression analysis indicates that the correlation coefficient of 0.767221536. It shows a direct linear relationship between annual foreclosure deeds and housing values in Boston. The p-value of 0.074972075 from ANOVA test indicates the lack of a statistically significant relationship between annual foreclosure deeds and the housing values in Boston is accepted (O'Rourke, Larry, & Edward 351).
In conclusion, the results obtained give a preview of the state and level of home valuation in Boston. The statistics places more facts about the information and enables comparisons of the various aspects of the process of home valuation. The statistics enables the assessment of the economics of the process, by enabling the determination of specific information regarding home valuation for example permits, foreclosure deeds and many other aspects. The determination of the R and P values for each set of data further confirms its validity. The values aided the determination of the inferences, involving the grounds for rejection or the acceptance of the respective hypothesis raised in each of the issues relative to the scope of housing valuation in Boston.
Works Cited
Bluestone, Barry, Huessy, James, White, Eleanor, Eisenberg, Charles, and Davis, Tim. The greater Boston housing report card. Nov. 2015. Web. 28 Dec. 2016.
Cameron, A. Colin, and Pravin K. Trivedi. Regression analysis of count data. Vol. 53. Cambridge university press, 2013.
Correa, Carlos, Chan, Yu-Hsuan, and Ma, Kwan-Liu, “A Framework for Uncertainty-Aware Visual Analytics,” the University of California at Davis, [Online], Available at < http://vis.cs.ucdavis.edu/papers/vast09.pdf> [21) October 2016]
Fitzenberger, Bernd, Roger Koenker, and José AF Machado, eds. Economic applications of quantile regression. Springer Science & Business Media, 2013.
HUD Sustainable Communities Initiatives, “Boston MA; Metro Future,” [Online], Available at < http://portal.hud.gov/hudportal/documents/huddoc?id=Bostoncasestudy.pdf> [222 October 2016].
O'Rourke, Norm, Larry Hatcher, and Edward, Stepanski. A Step-by-Step Approach to Using Sas for Univariate & Multivariate Statistics. New York: Wiley-Interscience, 2005. Print.
