management science quantitative, business and finance homework help

User Generated

bqvz

Business Finance

Description

Please write INTERPRTATION, LIMITATIONS and CONCLUSION by using the data in Master Regression Worksheet.


Introduction

New house construction has a significant impact to the US Economy.

For every new house built, 2.97 jobs are created and $110,957 are paid in taxes (Emrath, 2014). This estimate for 2014 has not drastically changed since 2008 (Liu & Emrath, 2008).

The jobs created are not only required to build the house, but also to manufacture and deliver all the products and designs for the large range of materials used in the constructing.

New house development and population movement and growth causes new public and private infrastructure. New hospitals, roads, schools, shopping malls and national retail chains etc. all use estimates of population growth and housing development to manage capital expenditure.

According to Builder Magazine, the top 100 new house construction companies had a total revenue of $90bn in 2015 (Builder_Magazine, 2016).

Residential Fixed Investment (RFI) is a measure of new single and multi-family homes and house remodeling. RFI has averaged 4.5% of GDP over the last 35 years (Logan, 2016) and was 3.6% in 2016.

Accurately forecasting the quantity of new houses enables businesses to be more efficient. They will be able to better plan and manage their capital expenditure and human resources.

The quantity of localized new housing also effects sale prices of existing housing. This influences the decision making process of buyers and sellers. If it is known that new housing in a specific area will begin to be constructed, sellers may try and move their properties earlier, and buyers may wait till the new houses are ready for sale.

Unfortunately, the number of new houses sold fluctuates each year. Over the last 50 years, the average has been 651,000, with a maximum of 1,283,000 in 2005 and a minimum of 306,000 in 2011.

(Census_Bureau, 2017)

The aim of this study is to identify variables that will help support forecasting of house sales to better improve management of capital and resources.

The methodology used was:

1. Brainstorm independent variables

2. Develop a regression model

3. Analyze the results to identify variables that will help improve forecasting of new house sales.

User generated content is uploaded by users for the purposes of learning and should be used following Studypool's honor code & terms of service.

Explanation & Answer

My question is whether I am only interpreting the analyzed data or am I running an analysis?
Hello, here is the paper and the excel data.

Running head: MANAGEMENT SCIENCE QUANTITATIVE

Management Science Quantitative

Name

Institution Affiliation

MANAGEMENT SCIENCE QUANTITATIVE

2

Introduction

The construction of new houses leads to a significant impact to economy of the United
States. The economic benefits include job creation, increased earnings, and contribution towards
national Gross Domestic Product (GDP). This paper provides and explains the factors to be used
when forecasting new house sales in the US.

Typically, For every new house built, 2.97 jobs are created and $110,957 are paid in
taxes (Emrath, 2014). This estimate for 2014 has not drastically changed since 2008 (Liu &
Emrath, 2008). The jobs created are not only required to build the house, but also to manufacture
and deliver all the products and designs for the large range of materials used in the constructing.
New house development and population movement and growth causes new public and private
infrastructure. New hospitals, roads, schools, shopping malls and national retail chains etc. all
use estimates of population growth and housing development to manage capital expenditure.
According to Builder Magazine, the top 100 new house construction companies had a total
revenue of $90bn in 2015 (Builder_Magazine, 2016).

Residential Fixed Investment (RFI) is a measure of new single and multi-family homes
and house remodeling. RFI has averaged 4.5% of GDP over the last 35 years (Logan, 2016) and
was 3.6% in 2016. Accurately forecasting the quantity of new houses enables businesses to be
more efficient. They will be able to better plan and manage their capital expenditure and human
resources. The quantity of localized new housing also effects sale prices of existing housing.
This influences the decision making process of buyers and sellers. If it is known that new
housing in a specific area will begin to be constructed, sellers may try and move their properties
earlier, and buyers may wait till the new houses are ready for sale. Unfortunately, the number of

MANAGEMENT SCIENCE QUANTITATIVE

3

new houses sold fluctuates each year. Over the last 50 years, the average has been 651,000, with
a maximum of 1,283,000 in 2005 and a minimum of 306,000 in 2011 (Census_Bureau, 2017).

The aim of this study is to identify variables that will help support forecasting of house
sales to better improve management of capital and resources.

Methodology

The methodology used was meant to establish the most effective way of coming up with the right
sample size, techniques of gathering meaningful data, and the approach to the data analysis
techniques.

Brainstorming the independent variables

The main variables used include the following:


The number of new homes sold



The average 30 year FRM



NASDAQ composite beginning price



Closing price of gold



GDP in current dollars



The mean house income

From the list of the above variables, the dependent variable the number of new houses sold.
The correct forecast on the sale of new houses is based on the other variables, which are
considerably the independent variables.

MANAGEMENT SCIENCE QUANTITATIVE

4

Regression model

The study utilized both correlation and reparation. Correlation was used to show the
various aspects of the collected data relate to each other. The correlation model depicted the
dependency among the following aspects of the housing markets and industry:


Previous Year Average 30 Year FRM (%)



Previous Year NASDAQ Composit Beginning Price



Previous Year Closing Price Of Gold



Previous Year GDP in Current Dollars



Previous Year Mean Household Income



Previous Year House Sales

Regression model was also used in the analysis to show the statistical relationship
between the dependent and independent variable. The model in this case is used to check how
the sale of new houses would be influences by the other variables including the number of new
homes sold, the average 30 year FRM, NASDAQ composite beginning price, closing price of
gold, GDP in current dollars, and the mean house income. In this regard, the dependent variables
represents the output on which the variation is being analyzed.

Analysis

From the data analysis, the variables likely to affect the forecasting of the sale of new
houses include the following:


The number of new homes sold

MANAGEMENT SCIENCE QUANTITATIVE


The average 30 year FRM



NASDAQ composite beginning price



Closing price of gold



GDP in current dollars



The mean house income

5

Typically, the volume of previous sales for new houses would be used to project the number of
new sales to be sold in the future. The same projection is also based on all the other variables.

Interpretation
The first step in the data analysis process was to find the correlation between each of the
independent variables. The correlation analysis was done in the form of a correlation matrix.
Table 1: Correlation matrix between variables
Previous

Previous

Previous

Previous

Previous

Previous

Year

Year

Year

Year

Year

Year

Average

NASDAQ Closing

GDP in

Mean

House

30 Year

Composit

Current

Household Sales

FRM (%)

Beginning Gold

Dollars

Income

Column 4

Column 5

Price Of

Price
Column 1

Column 2

Column
3

Previous Year Average 30

Column

Year FRM (%)

1

1

Column
6

MANAGEMENT SCIENCE QUANTITATIVE
Previous Year NASDAQ

Column

Composit Beginning Price

2

Previous Year Closing Price

Column

Of Gold

3

Previous Year GDP in

Column

Current Dollars

4

Previous Year Mean

Column

Household Income

5

Previous Year House Sales

Column

6

-0.73351

1

-0.54211

0.580396

-0.83014

0.894688 0.751495

-0.81898

0.893031

0.67369

0.98818

1

-0.13553

0.077922

-0.53126

-0.00495

0.067231

1

1

6

Correlation Results

A correlation of 1 shows that the variables are positively correlated and dependent.
However, not all variables are positively correlated. The correlation between the Pevious Year
Average 30 Year FRM (%) and Previous Year NASDAQ Composit Beginning Price is negative
with a correlation coefficient of -0.73351. This means that the variables are negatively
correlated. All the other variables are negatively correlated to the Previous Year Average 30
Year FRM (%). While the Previous Year House Sales is the key variable that can be used to
forecast the number of new houses to be sold, some of the other influencing variables negatively
affect it. This further implies that the sale of new houses in future could be affects by the same
variables. In this regard, the Previous Year House Sales are negatively correlated with Previous
Year Average 30 Year FRM (%), Previous Year Closing Price Of Gold, and Previous Year Mean
Household Income. These same factors would be negatively correlated with the future sale of

1

MANAGEMENT SCIENCE QUANTITATIVE

7

new houses. As such, the forecast has to treat them as having negative impact on the projected
sale of new houses. However, factors such as the Previous Year NASDAQ Composit Beginning
Price and the Previous Year Mean Household Income would have a positive effect on the sale of
new houses because they are positively correlated to the Previous Year House Sales, which
provides the primary data to run the forecasting analysis. A chart representing the trend of the
data between 1975 and 2016 is shown below.

Fig. 1: Trend of the variable data between 1975 and 2016

From the trend of the data shown in fig. 1 above it is clear that the sale of new houses has
been fluctuating over time. The highest sale of new houses was recorded between 2003 and
2006. The lowest sale of new houses was recorded in 2011. The sale of new houses has since
then been increasing with the curve further depicting a further increase in the sale of new houses
in 2017 and beyond. Factors like the GDP in current dollars and the mean house income have

MANAGEMENT SCIENCE QUANTITATIVE
been increasing consistently since 1975, which depict that they have little or no impact on the
sale of new houses. The other fact with no impact on the sale of new houses is the Pevious Year
Average 30 Year FRM (%). The chart thus confirms the coefficients of correlation matrix
between the variables depicted in table 1 above (Ganczarski, 2009).

Regression results

The regression results for the data analysis are as follows:

Table 2: Summary output

SUMMARY
OUTPUT

Regression Statistics
Multiple R

1

R Square

1

Adjusted R
Square

1
4.67E-

Standard Error

11

Observations

40

The summary output depicts an R2 of 100% with a 100% of adjusted R2 as well. This
means that the regression model explains all the data variability around the mean (Lewis-Beck,
1995). All variables are well explained by the model.

8

MANAGEMENT SCIENCE QUANTITATIVE

9

Table 3: Regression coefficients

Coefficients
Intercept
Previous Year Average 30

Standard Error
0

9.04

-6E-12

t Stat

9.50075E-11

0

4.66407E-12

-1.28624

Year FRM (%)
Previous Year NASDAQ

59.82

8.77E-15

1.48795E-14

0.589138

139.29

-3E-14

6.548E-14

-0.46533

1688.9

2.3E-14

1.9208E-14

1.198351

13778.6

-7.5E-15

3.82747E-15

-1.96237

549000

1

5.55098E-17

1.8E+16

Composit Beginning Price
Previous Year Closing Price
Of Gold
Previous Year GDP in
Current Dollars
Previous Year Mean
Household Income
Previous Year House Sales

The regression results shows how the sale of new houses is affected by the various
factors analyzed. A negative coefficient under each variable depicts a negative impact such that
the negative coefficient of Previous Year Average 30 Year FRM (%), for instance, means that a
hive value in the Previous Year Average 30 Year FRM (%) would depict a low sales volume of
new houses. A high value of the Previous Year Closing Price Of Gold would is also likely to
lower the volume of sales of new houses given the negative coefficient value. Similarly, low
sales of new houses would be projected when the Previous Year Mean Household Income is very
high due to the negative coefficient. However, a high value of the Previous Year NASDAQ

MANAGEMENT SCIENCE QUANTITATIVE

10

Composit Beginning Price would project an increase in the number of new houses to be sold.
Previous Year GDP in Current Dollars also would lead to a positive projection of the number of
new houses to be sold. Typically, the Previous Year House Sales provides the best forecasting
variable for new house sales. The coefficient of 1 shows that an increase in the previous sale of
new houses would have a direct impact on how the sale of new houses should be forecasted. The
standard error of each variable coefficient is significantly low, which means that the impact of
the results on forecasted sale of new houses is considerably accurate with only a negligible
margin of error. The effect of each variable on the number of new house sales is depicted in the
charted represented under fig. 2 below.

Fig. 2: Chart depicting the regression model

Typically, this chart confirms the regression coefficients presented in table 3 above. The
most noticeable effect on the projected sale of new houses is the depicted trend between the

MANAGEMENT SCIENCE QUANTITATIVE

11

number of new houses sold and the previous year sale. The two variables depict exactly the same
curves. The negativity of some of the variables further confirms the results of the correlation
matrix. Only the previous year house sales, Previous Year GDP in Current Dollars, and Previous
Year NASDAQ Composit Beginning Price would have a positive impact to the forecasted new
house sales. In fact, the previous year house sales would provide a direct impact on the foresting
accuracy (Lewis-Beck, 1995).
Limitations
The study was conducted well and provides seemingly useful results .However, it is
prone to a number of limitations that could be avoided in future study. The first limitation is that
some of the variables used have no effect on the sale of new houses in the US. Variables like the
GDP is both an effect on the general economy but it has little to do with the sale of new houses.
While it may affect the purchasing power of buyers, the buyers are influenced by other factors
than their increased ability to pay (Gallagher, Stanley, Shearer, & Klerman, 2005). This means
that the previous year mean household income could cater for people’s ability to pay. Another
limitation is that the study did not include other crucial variables such as the type of houses,
reasons for purchase, and the average cost of the house. A mixture of both qualitative and
quantitative data could have made the results more applicable to real-life situation. Aspects like
what people are looking for in a house and the features of the new houses in the current and
future market would give a bigger picture of the market and help in forecasting the trend of
future sales for the new houses. The change in average cost of new houses would also show the
exact picture of how people have been reacting to the cost of new houses and how they are likely
to react. Addition of these aspects or variables would make the results more applicable.

MANAGEMENT SCIENCE QUANTITATIVE

12

Conclusion
The sale of new houses in the United States has been influenced by multiple factors. This
study has only addressed some of the factors, which can be used as the foundation for projecting
the sale of new houses in the US local market. Typically, investors and consumers make various
considerations when deciding whether to purchase or not to purchase a new house. The basic
factors are the buyer’s ability to buy, the cost of the new house, and its specification. Among
these three factors, only the buyer’s ability to pay for a new house has been considered through
changes in the national GDP and average household income over the previous years. While this
variable is crucial, the changes in the prices of new house over the same period should be
considered as well as how the cost has been affecting demand. It would be then possible to yield
more accurate results than in the current study when the trend in cost of new houses has been
since 1975 until 2016 and how the average cost of a new house may change in future.
Nevertheless, the results have shown that the previous data/trend on the sales of new houses is
the most useful variable in forecasting the sale of new houses. The results shows that future sales
of new houses would be more than the house sales in 2016.

MANAGEMENT SCIENCE QUANTITATIVE

13

References
Gallagher, K., Stanley, A., Shearer, D., & Klerman, L. (2005). Challenges in data collection,
analysis, and distribution of information in community coalition demonstration projects.
Journal of Adolescence Health, 37(3), 53-60.
Ganczarski, J. (2009). Data Warehouse Implementations: Critical Implementation Factors
Study. Saarbrücken: VDM Verlag.
Lewis-Beck, M. S. (1995). Data Analysis: an Introduction. New York: Sage Publications Inc.


Running head: MANAGEMENT SCIENCE QUANTITATIVE

Management Science Quantitative

Name

Institution Affiliation

MANAGEMENT SCIENCE QUANTITATIVE

2

Introduction

The construction of new houses leads to a significant impact to economy of the United
States. The economic benefits include job creation, increased earnings, and contribution towards
national Gross Domestic Product (GDP). This paper provides and explains the factors to be used
when forecasting new house sales in the US.

Typically, For every new house built, 2.97 jobs are created and $110,957 are paid in
taxes (Emrath, 2014). This estimate for 2014 has not drastically changed since 2008 (Liu &
Emrath, 2008). The jobs created are not only required to build the house, but also to manufacture
and deliver all the products and designs for the large range of materials used in the constructing.
New house development and population movement and growth causes new public and private
infrastructure. New hospitals, roads, schools, shopping malls and national retail chains etc. all
use estimates of population growth and housing development to manage capital expenditure.
According to Builder Magazine, the top 100 new house construction companies had a total
revenue of $90bn in 2015 (Builder_Magazine, 2016).

Residential Fixed Investment (RFI) is a measure of new single and multi-family homes
and house remodeling. RFI has averaged 4.5% of GDP over the last 35 years (Logan, 2016) and
was 3.6% in 2016. Accurately forecasting the quantity of new houses enables businesses to be
more efficient. They will be able to better plan and manage their capital expenditure and human
resources. The quantity of localized new housing also effects sale prices of existing housing.
This influences the decision making process of buyers and sellers. If it is known that new
housing in a specific area will begin to be constructed, sellers may try and move their properties
earlier, and bu...


Anonymous
I was struggling with this subject, and this helped me a ton!

Studypool
4.7
Trustpilot
4.5
Sitejabber
4.4

Similar Content

Related Tags