Attached.

Running head: ANALYSIS OF THE US GDP USING MULTIPLE REGRESSION

Analysis of the US GDP Using Multiple Regression
Student’s name
Institution affiliation
Date

1

ANALYSIS OF THE US GDP USING MULTIPLE REGRESSION

2

Analysis of the US GDP using Multiple Regression and Econometric Analysis
Abstract
The Gross Domestic Products (GDP) is an essential indicator of the economic stability of
the United States. The federal government and other regulatory agencies use the GDP to plan for
economic policies and predict future fluctuations in the economy. The ultimate goal of this paper
is to use the multiple regression models to determine the impact of changes in the S&P 500 index
to the US GDP (Gordon and Harris 2018). The model will be able to predict whether the S&P 500
is leading or lagging as compared to the GDP over a certain period. The model will give a clear
understanding of why the variations in the gross domestic products (GDP) are occurring and why
various business entities are much more reliable than the others. The data was collected through
secondary sources, including yahoo finance, St. Luis Fed, and Morningstar.
Introduction
The US economy and total financial outputs from various business entities are pivotal to
all business functions such as production, consumption, business, and wealth management.
Corporate and business activities are analyzed basing on the absolute accuracy of these aspects.
The S&P 500 index has been essential in predicting the economic dynamic and get a clear
understanding of the performance of the various business organizations. This research reveals how
the slight changes in the S&P 5000 affect the US GDP and the secondary impacts on the economy.
As a result, a multiple regression tool was used to model the parameters and predict the changes
which can be used by investors, business people, or policymakers to make significant business
decisions. For instance, one can be able to predict the imminent or forthcoming sources of revenue,
both by purchasing substantive assets through debts or cash and decide whether to invest in the

ANALYSIS OF THE US GDP USING MULTIPLE REGRESSION

3

form of equities or instead in fixed income markets. The modeling will significantly assist in
determining future variations in the economy and the advancements that the measures that need to
be undertaken to balance the economy. The GPD data of the United States has secondarily
collected from the St. Louis Fed webpage, and the historical S&P 500 data was collected from the
yahoo finance webpage for comparison and analysis. The data were statistically analyzed through
regression models in an excel spreadsheet showing a restrained positive relationship between the
GDP and the S&P 500 every quarter. The model tracks the economy of the united states as
compared to the stock market exchange and then determines how farther the predicted data can be
true. The key objective of the model is to focus on the preceding quarters and make assumptions
on the future changes and the primary cause in changes. Therefore, the study is essential because
it establishes measures that can be used by business personnel, policymakers, and various financial
organization can use the regression model to determine the variations in the stock market.
Literature Review
The recent historical trends in forecasting the economic decline or growth entail both the
financial aspects and the economics to assist in lessening some of the apparent uncertainties in the
stock market. So many models have been developed by various researchers to predict the
fluctuations in the economy. Some of the models have successfully predicted, while many other
models have significantly failed to show results. Unfortunately, most of the models used to predict
or analyze the variations in the US economy has never demonstrated consistency. According to
(Dritsaki, 2017), the GDP models proved that the changes in GDP could be used to predict the
equity escalation. The percentage changes in GDP in the models prove that the financial systems
in a given econometric market can be either fixed income or equity. Dritsaki’s 2017 models took

ANALYSIS OF THE US GDP USING MULTIPLE REGRESSION

4

the historical deviations in GDP and made a comparative analysis of what happens in the equity
market and the trends in the financial output of various entities. Dritsaki broke down the models
by overlaying the previous and current market in the form of graphs and project the future
outcomes in the economy. However, the models were not that successful as the assumptions were
basically on what the GDP will be doing rather than making a substantive prediction of what will
be happening in the future basing on the current output. For instance, the models reacted to the
current trends instead of predicting future trends in the market.
According to Dynan & Sheiner (2018), the S&P represents the aggregate increase or
growth in the economy over a certain period. Through the use of a naïve Bayes classifier, Dynan
& Sheiner (2018) were able to predict the advances in the economy over the years. The models
were beneficial because they were able to project the recession and various changes in the economy
for about the past 28 years. Dynan & Sheiner's (2018) studies were essential because one can be
able to create a model which can use parameters such as the financial markets as its primary
indicator in the dynamic economy. The models were able to cover a variety of economic states by
using a simple Bayes classifier in testing the annual projections, the economic downturn, and
growth in the economy. The tests significantly assisted in strengthening the models hence
becoming one of the most used models in predicting the imminent macroeconomics.
Similarly, Andrei & Bugudui (2019) utilized the Keynes theorem to make focus on how
the economic output will be influenced or affected by the demand in the short run. In today's
competitive business environment, we understand the consumer demand is essential for any
business entity to stay competitive in the market. A change in consumer demand has a major impact
on the overall economic output. Consequently, a slight change in the economy can have an elastic

ANALYSIS OF THE US GDP USING MULTIPLE REGRESSION

5

effect on the changes in demand. Andrei & Bugudui (2019) showed how the instability in the
overall financial output could highly affect the financial markets over a certain period of time.
However, their research significantly depended on the foregone macroeconomic theories. Also,
the models highly relied on the policies made by the government towards stabilizing the economy
of the country. For instance, the government can employ various policies to counteract the
recession, thus making it easier to predict the changes that might occur over a certain range of
time.
The models are not viable in projecting the changes in the economy when there is no
government stipulation on regulating the economy. When there are little concerns by the
government or other monetary regulations, the Andrei & Bugudui (2019) models will not be
accurate because the models much depend on the rules to make stipulated projections. The models
are improved models of Wabomba's 2016 research models on the impact of gross domestic product
GDP on the economy. The models also analyze the impacts of banking regulations on the dynamic
economy. According to Wabomba (2016), the stiffer the government and banking regulations, the
higher the S&P 500. Therefore, this helps the GDP to play a significant role in predicting the shifts
in the economy. Also, modeling research by Wabomba can be affected if there will be no
regulations imposed by monetary policies.
Barhoumi et al. (2017) used the models of the Auto-Regressive Integrated Moving Average
(ARIMA) to explain how the financial markets can be the leading indicators of a country’s
economic changes. Indeed, focusing on the projected economic outcome is essential to cognitive
decision making by policymakers, producers, consumers, and any other responsible person in
different business sectors. The ARIMA is more moderate than Keynes's theorem in finding the

ANALYSIS OF THE US GDP USING MULTIPLE REGRESSION

6

ultimate relationship between the economy and the financial market. The models can predict
whether economic output over a certain time lags or leads in the stock market rates.
Methodology
The data for modeling was compiled from secondary sources. Historical data of the S&P
500, XLF (finance) stock prices, XLU (utility stock), and XLI (industrial stock) were extracted
from yahoo finance from 2005 to 2019. The GDP data for the United States was extracted from
the St. Luis Fed search website, which assisted in the creation of the GDP m...