Session Long Project

ASYMMETRIC INFORMATION AND MARKET OUTCOMES

Links to Estimation Techniques

Tim Shaughnessy, Chapter 7 — Demand Estimation and Forecasting, available from https://www.youtube.com/watch?v=daiTjsnznjM

Matt Kermode, Explanation of Regression Results, Available at https://www.youtube.com/watch?v=c5blVUkkjTM

Jason Delaney, Introduction to Multiple Regression, Available at https://www.youtube.com/watch?v=eLpfEml4Vak

Session Long Project

PART 1

In 2006 the CEO of Bear Sterns, James Caynes, received a compensation package of $34 million. The following year Bear Sterns cost $2.7 billion to the taxpayers. In 2006, the CEO of Lehman Brothers received a compensation package of $27 million. On September 15, 2008, Lehman Brothers filed for bankruptcy. The collapse of Lehman Brothers is seen by many as the key event that sparked the Global Financial Crisis. In 2006, the CEO of Citigroup, Charles Prince, received a compensation package of $25 million. Since then the stock price has fallen from $50 a share to $3.5 a share. The CEO of Countrywide Financial, Angelo Mozilo, did even better. His compensation package was $43 million. Angelo Mozilo and two other top executives were charged by the Security and Exchange Commission (SEC) with fraud. According to the SEC, from 2005 through 2007, Countrywide Financial engaged in an unprecedented expansion of its underwriting guidelines and was writing riskier and riskier loans, which these senior executives were warned might ultimately curtail the company’s ability to sell them. Countrywide Financial was the third biggest originator of subprime mortgages and the nation’s leader in subprime mortgage- backed securities. The tragedy is that these individuals did not make decisions that were in their companies’ best interest. Why? What went wrong? What caused the relation between the CEO and the stockholders to go so badly awry? Discuss.

PART 2

An important component of this course is experience with analyzing economic data at the managerial level. The computer is a perfect tool for manipulating data and performing statistical analyses. While the focus of BUS 530 is not on learning statistics, this course will utilize and improve your computer skills with a computer assignment designed to illustrate the interconnections between data, information and managerial decisions.

The primary software will be Microsoft Excel and the Excel statistical add-in: Data Analysis. Microsoft Excel 2010 (and previous versions) provides a set of data analysis tools called Analysis ToolPak which you can use to save steps when you develop complex statistical analyses. You provide the data and parameters for each analysis; the tool uses the appropriate statistical macro functions and then displays the results in an output table. The Analysis ToolPak is a Microsoft Office Excel add-in program that is available when you install Microsoft Office or Excel. To use the Analysis ToolPak in Excel, however, you need to load it first. Click the Microsoft Office Button, and then click Excel Options. Click Add-Ins, and then in the Manage box, select Excel Add-ins. Click Go. In the Add-Ins available box, select the Analysis ToolPak check box, and then click OK. (If Analysis ToolPak is not listed in the Add-Ins available box, click Browse to locate it.) If you get prompted that the Analysis ToolPak is not currently installed on your computer, click Yes to install it. After you load the Analysis ToolPak, the Data Analysis command is available in the Analysis group on the Data tab.

In the Module 4 SLP assignment you are also asked to estimate a market demand or a cost function (your choice) using the tools of regression analysis and the regression software outlined above.

The estimation of demand follows two approaches:

the classical approach, whereby the quantity demanded of a product is explained by its own price, the prices of related goods (complements and substitutes), income, tastes and preferences, and the size of the population, among others;

the hedonic approach, whereby the price of an asset (car, house) is explained by the characteristics of the asset itself (i.e., the price of housing depends on the number of bedrooms, the number of bathroom, the view from the house (using a dummy variable: 1 = view, 0 = no view), the square footage of the house, the square footage of the lot, etc).

PART 2: Assignment

You are given the data on housing. The data are collected from the real estate pages of the Boston Globe during 1990. These are homes that sold in the Boston, MA area. The source of the data is Wooldridge (2009) Introductory Econometrics: A Modern Approach, 4^th Edition, Cengage

VARIABLES

1. price price, in dollars

2. assess assessed value, in dollars

3. bdrms number of bedrooms

4. lotsize size of lot, square feet

5. sqrft size of house, square feet

Cut and paste in Excel the data set. Then, in Excel, obtain the logarithmic transformation of the following variables using the Excel function =LOG( . )

6. lprice log(price) : dependent variable

7. lassess log(assess) : independent variable

8. llotsize log(lotsize) : independent variable

9. lsqrft log(sqrft) : independent variable

DATASET 1

OBSERVATIONS

PRICE	SQRFT	ASSESS	BDRMS	LOTSIZE
300	2438	349.1	4	6126
370	2076	351.5	3	9903
191	1374	217.7	3	5200
195	1448	231.8	3	4600
373	2514	319.1	4	6095
466	2754	414.5	5	8566
332	2067	367.8	3	9000
315	1731	300.2	3	6210
206	1767	236.1	3	6000
240	1890	256.3	3	2892
285	2336	314	4	6000
300	2634	416.5	5	7047
405	3375	434	3	12237
212	1899	279.3	3	6460
265	2312	287.5	3	6519
227	1760	232.9	4	3597
240	2000	303.8	4	5922
285	1774	305.6	3	7123
268	1376	266.7	3	5642
310	1835	326	4	8602
266	2048	294.3	3	5494
270	2124	318.8	3	7800
225	1768	294.2	3	6003
150	1732	208	4	5218
247	1440	239.7	3	9425
275	1932	294.1	3	6114
230	1932	267.4	3	6710
343	2106	359.9	3	8577
477	3529	478.1	7	8400
350	2051	355.3	4	9773
230	1573	217.8	4	4806
335	2829	385	4	15086
251	1630	224.3	3	5763
235	1840	251.9	4	6383
361	2066	354.9	4	9000
190	1702	212.5	4	3500
360	2750	452.4	4	10892
575	3880	518.1	5	15634
209	1854	289.4	4	6400
225	1421	268.1	2	8880
246	1662	278.5	3	6314
713	3331	655.4	5	28231
248	1656	273.3	4	7050
230	1171	212.1	3	5305
375	2293	354	5	6637
265	1764	252.1	3	7834
313	2768	324	3	1000
417	3733	475.5	4	8112
253	1536	256.8	3	5850
315	1638	279.2	4	6660
264	1972	313.9	3	6637
255	1478	279.8	2	15267
210	1408	198.7	3	5146
180	1812	221.5	3	6017
250	1722	268.4	3	8410
250	1780	282.3	4	5625
209	1674	230.7	4	5600
258	1850	287	4	6525
289	1925	298.7	3	6060
316	2343	314.6	4	5539
225	1567	291	3	7566
266	1664	286.4	4	5484
310	1386	253.6	6	5348
471	2617	482	5	15834
335	2321	384.3	4	8022
495	2638	543.6	4	11966
279	1915	336.5	4	8460
380	2589	515.1	4	15105
325	2709	437	4	10859
220	1587	263.4	3	6300
215	1694	300.4	3	11554
240	1536	250.7	3	6000
725	3662	708.6	5	31000
230	1736	276.3	3	4054
306	2205	388.6	2	20700
425	1502	252.5	3	5525
318	1696	295.2	4	92681
330	2186	359.5	3	8178
246	1928	276.2	4	5944
225	1294	249.8	3	18838
111	1535	202.4	4	4315
268	1980	254	3	5167
244	2090	306.8	4	7893
295	1837	318.3	3	6056
236	1715	259.4	3	5828
202	1574	258.1	3	6341
219	1185	232	2	6362
242	1774	252	4	4950

Please keep in mind that when you interpret a regression coefficient, you are assuming that all the other variables remain constant.

A Note on ANOVA

The ANOVA table is used to test the null hypothesis that all regression coefficients (excluding the intercept term) are equal to zero against the alternative hypothesis that at least one is different from zero. This test is known as the F test for regression. The F test is computed as follows, under the assumption that the null hypothesis is true:

The F statistics has two sets of degrees of freedom: numerator (attached to the Regression SS) and denominator degrees of freedom (attached to Residual SS).

Excel computes the F statistic for you in the ANOVA table, and computes in the last column the level of significance (p-value). If the level of significance of the test is less than 5%, you will reject at the 5% level the null hypothesis that all regression parameters are zero. On the other hand, if the level of significance is greater than 5%, you will accept (i.e., fail to reject) the null hypothesis that all regression parameters are zero.

SLP ASSIGNMENT EXPECTATIONS

In this Assignment, you are expected to:

Describe the purpose of the paper and provide a conclusion.

Present information in a professional manner.

Answer the SLP Assignment question clearly and provide necessary details.

Write clearly and correctly—that is, no poor sentence structure, no spelling and grammar mistakes, and no run-on sentences.

Provide citations to support your argument and place references on a separate page. (All the sources that you listed in the references section must be cited in the paper.) Use APA format to provide citations and references with credible sources (3-5 sources) [http://owl.english.purdue.edu/owl/resource/560/01/].

Type and double-space the paper, minimum 3-4 pages.

please use Excel, Chart and graph to show supporting computations, present economic information in tables, and use the data to answer follow-up questions.

Reading Required:

Worstall, T. (2013, March 1). Solving The Principal Agent Problem: Apple Insists That Executives Must Hold Company Stock. Forbes. Retrived from http://www.forbes.com/sites/timworstall/2013/03/01/solving-the-principal-agent-problem-apple-insists-that-executives-must-hold-company-stock/

Philips, J. (2012, Dec. 28). ‪The Principal Agent Problem [Video file]. Retrieved from https://www.youtube.com/watch?v=eByLsoIPMy8

Roy, M. (2013, Sept. 26 ). Agency Theory [Video file]. Retrieved from https://www.youtube.com/watch?v=GJ7y2XaSUCc

Optional Reading

openlectures sg. (2013, Feb. 9). Principal Agent Problem [Video file]. Retrieved from https://www.youtube.com/watch?v=NfigWaPhAqo

Worstall, T. (2014, July 7). Soaring Inequality And CEO Pay Are Not Caused By The Principal/Agent Problem. Forbes. Retrieved from http://www.forbes.com/sites/timworstall/2014/07/20/soaring-inequality-and-ceo-pay-are-not-caused-by-the-principalagent-problem/