BUSANA 7001 - Predictive and Visual Analytics for Business Assignment

Assignment Task

Agenda

Assume that you are a financial analyst working for an investment bank, specializing in initial public oferings (IPOs).

An IPO is the process of ofering shares of a private corporation to the public in a new stock issuance for the frst time. An IPO allows a company to raise equity capital from public investors. Before the IPO, the stocks of a firm are not traded on any stock exchange. After an IPO, the stocks are traded on at least one stock exchange, and public investors could buy its shares.

Companies hire investment banks to underwrite the stock issue. Specifcally, investment banks help an issuer to sell shares to public investors, primarily to large institutional investors such as mutual funds. The tasks of an investment bank include assessing the demand for shares, how much investors are willing to pay for each share, and providing stock price support after its trading commences on the stock exchange (i.e., which means that the investment bank would trade the stock in order to keep its price within a certain range).

Investment banks charge underwriting fees for their service, typically expressed as a percentage of the IPO size. For example, if an issue amount is $100 million, underwriting fees could be 7 per cent or $7 million. You have been assigned the task to analyze the historical IPO fees (data file: IPO_data_2024_S1.csv) and determine how much a new client should be charged for its IPO. In the data set, IPO fees are in % of the IPO amount. IPO price is in $. Debt, profit, assets are in $ million. IPO amount is defined as how much money (in $ million) a firm got from investors.

1. Descriptive statistics using SAS Visual Analytics

Using the provided dataset, create a report (using `Text' object which is available under `Content' group) with various Figures and tables (around 6 objects) that summarize the sample. Discuss briefly your sample, including the number of observations, outliers. Provide the descriptive statistics of the sample. How you choose to do this is entirely at your discretion. However, it is recommended that you consider using both summary statistic and graphical methods (this task should include at least one properly formatted table, one pie chart, one histogram, and one scatter plot) while also noting any peculiarities within the data set. You should put more emphasis on variables that are the dependent variables in the regressions estimated in the next task

Then estimate an OLS regression model where the dependent variable is the IPO fee. Motivate your choice of the independent variables and discuss the results (again, using `Text' object which is available under `Content' group).

2. Estimating yield for a hypothetical bond

First, you should prepare your data for the analysis: 3

• remove duplicates (if any)
• remove observations with missing values of any variable
• remove observations where the exchange is neither Nasdaq nor New York (in other words, retain those observations where the exchange is Nasdaq or New York).

Then create the following variables:

• three time period dummy variables ( (which can be used instead of year fixed effects)
  • if ipo_year ⩽ 2000
  • if 2001 ⩽ ipo_year ⩽ 2009
  • if ipo_year ⩾ 2010
• a natural logarithm of Firm's assets
• a natural logarithm of IPO size
• leverage (debt-to-assets ratio)
• ROA (prot-to-assets ratio)
• a dummy if profit is positive.
• a dummy is a firm is from California.

Then provide a summary statistics table of main variables and briefly discuss it. Afterwards, perform a regression analysis where the dependent variable is IPO fee. To ensure that the results are robust, estimate at least 3 regression models (e.g., in the first regression model, one includes size in $, in the second model, one uses the natural logarithm of size in $, and the third model features something else). To ensure that regression residuals behave well, if you may need to scale or transform one or more variables. For example, to use a natural logarithm value of the variable instead of its raw value. Do not forget to include industry and time fixed effects in the regression models as the independent variables (i.e., at least, one regression should be with xed effects).

Briefly discuss the determinants of IPO fees (i.e., which firm characteristics significantly increase and decrease IPO fees?) and answer the following questions:

• Which industries are associated with highest and lowest IPO fees?
• Do firms in California pay lower IPO fees?
• Do IPO proceeds depend on the time period (1, 2, or 3)?
• Do profitable Fims listed on New York stock exchange have lower IPO fees?
• the IPO amount is $100, roa is 0.1, other issue characteristics are the same as above.

This BUSANA 7001 - Business Analytics has been solved by our PhD Experts at My Uni Paper.