The research topic is “the data and description statistics + Methodology + Empirical Result + Conclusion” about Renting versus Buying a house.

The research topic is “the data and description statistics + Methodology + Empirical Result + Conclusion” about Renting versus Buying a house.

I need to have information written about data with 7 pages

The Data and descriptions statistics sources must come from this website “ http://www.abag.ca.gov” or any website is published by government.

- need to know/have the sources + sources of data + time frame + statistic for all. You do not to calculate anything just get the related information.

You need to do ALL of these:

= Methodology + Empirical Result + conclusion follow the structure like example below.

The example is below. Please read and look carefully the example. This example model is exactly what I want. I would love your work will be similar to this in 7 pages with reference pages separately.

(this is just example for you to see and follow similar work like this)

THE DATA AND DESCRIPTION STATISTICS

According to the Association of Bay Area Government (also known as ABAG), there are 101 cities (see Exhibit 1 for a list of cities and city definitions) in the SF Bay Area. We use 101 observations at the city level. Our dependent variable is median house value, which implicitly incorporates aspects of appreciation and affordability. The data source for median house value and our explanatory variables of housing units, median household income, population and race is the U.S Census Bureau, specifically the 1990 and 2000 decennial census. Since this survey collects data every ten years with cross sectional data, this allows us to use different markets (the

101 cities) and time periods to construct and compare two data sets, 1990 and 2000 data sets, respectively.

Exhibit 2 presents descriptive statistics for the 101 cities in our 1990 and 2000 data sets. We use population as one of our variables to describe housing demand in the SF Bay Area. The 1990 mean population was 52,929, and in 2000 it was 59,748. This increase in demand corresponded with the increase in supply of housing over this same time period. We measure housing supply in terms of housing units. In 1990, the mean number of housing units was 20,825 and in 2000 it grew to 22,365. The population mean increased by 6,819 (12.88 percent) and housing units increased by 1,540 (7.40 percent). The changes in average housing units and population imply new housing units could accommodate the increase in population at an average household size of 4.43. However, according to the U.S. Census Bureau, the average household size for the Nation in 2000 was 2.59. It means that as demand for housing increases and supply of housing does not increase at the same level of demand, this may lead to a rise in housing prices. The average median household income, our key demand variable, was $76,581 in 2000, up from $50,994 in 1990. The average median value for all housing was $291,369 in 1990 and $433,909 in 2000.

Exhibit 3 uses 1990 and 2000 median income and house price data from all 101 cities in the SF Bay Area to illustrate the widening gap between these two variables from one period to the next indicating a housing affordability issue. With respect to the minority population, the percentage of minority has increased over this time period from 21.08 to 31.44 percent within the SF Bay Area.

METHODOLOGY

Our hypothesis is that housing price in the SF Bay Area is determined by both supply and demand variables. The supply variable is housing units and the demand variables are median

household income, population, and race. H = f(N, P, Y, R) where

H = median housing prices, N = housing units, P = population, Y = median household income, and R = race.

Equation [1] describes our house price function. [1]

To test our hypotheses, we use an OLS regression with a linear specification, as shown in Equation [2].

4. EMPIRICAL RESULTS

This section reports the OLS results and discusses how well the explanatory variables explain our dependent variable, house value, for the 1990 and 2000 data sets. The first regression consisted of the 1990 data set. Exhibit 4 shows that this regression explains approximately 62 percent of the total observed variance in median house prices in the SF Bay Area. Our second regression, which uses the 2000 data set explains about 76 percent of the total observed variance in median house prices.

The OLS results conform to our expectation that the coefficient signs for median household income and race were positive and negative, respectively. It implies that a non-majority white population in a SF Bay Area city will cause a decrease in house prices (i.e. for 2000, the median house price would decrease by $78,353); while an increase in median household income will increase house prices. These coefficients were statistically significant in both years, except for race in 1990 as shown in Exhibit 4. In particular, median household income had a coefficient estimate of 4.41 and a t-statistic of 12.24. In 2000, the income coefficient increased by almost 50 percent to 6.43 with a t-statistic of 16.75. This implies that a $1 increase in median household income would increase median housing prices by $4.41 and $6.43 in 1990 and 2000, respectively.

However, the 1990 and 2000 results were peculiar for our supply variable, housing units, and demand variable, population. These two coefficient estimates imply an opposite effect on house prices in comparison to other studies (i.e. Jud and Winkler, 2002). Our population coefficient estimate was negative while positive for housing units. This means that for a unit increase in housing units, housing prices would increase. Conversely, a unit increase in population decreases housing prices. In 1990 both coefficient estimates were statistically significant but not in 2000.

The third OLS regression uses difference between 1990 and 2000 as inputs. The result shows that the statistically significant determinant for change in housing price is the change in household income. As for the remaining three independent variables, the result shows that they are statistically insignificantly different from zero. In sum, all the three OLS results indicate that increase in household income leads to increase in demand for housing and a higher housing price.

CONCLUSION

Our study shows that median household income is a major determinant for housing values in the SF Bay Area. It is evident that an increase in income leads to an increase in housing values. Our result does not support the hypotheses that the housing units and population variables are significant factors for housing values. These findings may result from the atypical behavior of the SF Bay Area housing market in that income (perhaps “stated income” used in creative mortgage products) is the driving factor of affordability.

The population coefficient may be inferred as population sizes increase in certain SF Bay Area cities so does household sizes. Due to the high cost of living, it is common to have the non- related household formation and larger household sizes in this market in comparison to other places. Therefore, the demand effect from an increase on population coupled with larger household sizes frees up more housing units; increasing the vacant housing stock in certain areas. This results in a downward effect on housing prices. Contrarily, one story that may explain the positive supply effect of housing units on house price is the SF Bay Area developer’s financial strategy of increasing house prices for every new release in certain cities.

Typically, there are a few weeks between releases where the developer will release a few homes and increase price by several thousand dollars. Aside for gains in value for existing homeowners in the new development, the price increases spillover as higher property values for nearby areas. Although noteworthy, these atypical results for certain SF Bay Area cities may not necessarily represent every community within this market.

This phenomenon occurred in the San Francisco Bay Area during a declining mortgage interest rate environment of 2001-04 (see www.federalreserve.org). The Federal Reserve’s June 2004 meetings contributed to changing this environment. Between June 2004 and May 2006, the Federal Reserve had sixteen consecutive rate hikes taking the fed funds rate from one to five percent. Overall, the rate hikes increased bond rates; thereby, increasing mortgage interest rates.

If median household income is the demand variable, which clearly demonstrates the intuitive effects on house price, then we should focus on income in addressing housing affordability issues. Mortgage products such as interest-only loans, stated income and no ratios that are common in this market coupled with the mortgage interest tax deduction help address affordability issues. Additional policies could be put in place to head off an affordability crisis by lowering taxes to increase disposable household income and/or providing more housing investment tax incentives. An unusual housing market as the SF Bay Area can definitely provide lessons and warnings to other markets across the Nation.