# Quantitative Finance

How do I test for time effects in cross section data?

I have cross-sectional data (1999 - 2014) and I want to regress some financials on 2 dummies. A dummy for foreign versus domestic companies and another dummy serves as reputation measure (1 in case of listed in top reputation rankings, 0 otherwise).

However, now I want to control for year. Can I easily create dummy variables for each seperate year (so, DUM99, DUM00 ... DUM14) and include them all? And should I include both intercept and slope dummies? Or only interecept dummies?

Stuart Locke · The University of Waikato

When you have a good set of panel data there is so much you can do with it.  Careful diagnostics are important and ensure you allow the data to speak effectively; the art of positivism.

You can check whether there is a time variation in the variables; its it a fixed effect or random effect model.  Use the Haussmann test.  This is available in STATA which is the package we use for nearly all our staff and PhD students.

Enjoy your analysis and hopefully it will go really well.

How to apply PCA on futures commodity (oil) ?

The data is from the futures market via Bloomberg, with the tickers CL1 to CL9 of the last price and volume. This is similar to Skiadopoulos (2008) .when you extract the data from Bloomberg; you get a column vector of price and volume for each group like CL1 etc. How do I perform PCA on the column vector (price with dim 2567 x 1)? The paper is attached below. Any advice is aprreciated.

Amit Mittal · Indian Institute of Management, Lucknow

I am unsure whether you need guidance in using software as above or other quesions on the use of PCA methdology.

PCA methodology would find factors (unnamed) that would separate the Price data into separate contributions attributable to the various effects of the volatility underlying the prices. As such  commercial models of Futures pricing are already available using PCA successfully

$\ln(F_{t,T}) = \ln(S_t) + (r_{t,T}+x_{t,T}-q_{t,T})(T-t)$

Where

= future prices at time ( ) for delivery at .
= WTI spot prices for delivery at Cushing, OK
= time now
= future delivery time
= nominal (per annum) interest rate at time ( ) for maturity
= nominal (per annum) marginal storage cost at time ( ) for delivery .
= nominal (per annum) theoretical convenience yield at time ( ) for delivery

How can I connect technical rules and efficient market hypothesis with the theory of behavioral finance?

How can I connect technical rules eg moving averages (existed abnormal returns) and Efficient Market Hypothesis (weak form) with the theory of Behavioral Finance (any kind of behavioral issues which are relevant to the research of Technical Analysis)?

Max Isernhagen · University of St Andrews

Have a look at the Adaptive Markets Hypothesis (Lo 2004) and how it is tested in different markets. Its an alternative to the EMH, where modern financial economics can coexist alongside behavioral models in an intellectually consistent manner.

For example Todea (2009) investigates in his paper "Adaptive Markets Hypothesis: evidence from Asia-Pacific financial markets" the profitability of the moving average strategy on 6 Asian capital markets considering the episodic character of linear and/or nonlinear dependencies. The methodology applied there should be of help to you.

I hope this is of help to you!

Which is the best model for Event Study Methodology?
There are different models that are being used to estimate the stock returns under event study methodology such as; arbitrage pricing theory (APT), capital asset pricing model (CAPM), modified market model (MMM) and market model (MM).

My question is which one is better between the market model and CAPM to estimate the return while studying dividend announcements? How will alpha and Beta be estimated under the market model and CAPM in the equation for event study methodology’ i.e Rit = αi + β (market return) + εit?
Paul-Francois Muzindutsi · North West University South Africa

In most studies, market model and the CAPM model seem to generate similar normal returns but the market model is mostly preferred because it does not impose any restrictions.  In your case, you may consider starting with your own preliminary analysis to test whether the normal returns from these two models differ before deciding on which model to use.

See this paper by  MacKinlay (1997)

Is there any case study in resource allocation with game theory ?

there many empirical study on resource allocation with game theory .Is there any paper make a case study on resource allocation with game theory.

Björn Stefánsson · The Reykjavik Academy

I refer to a case on energy resources among my contributions in the ResearchGate (linked) and to Chapter III.D.4 in Democracy with sequential choice and fund voting.

What is the effect of the securitization transactions on credit risk in an emerging economy?

There is no clear evidence regarding the effect of securitization transactions on the risk in the financial system. The literature about this subject is incipient for emerging economies and, in particular, for Latin American countries. A possible justification for this fact can be a lack of a developed financial system in these countries.

Patrick Navatte · Université de Rennes 1

Hi!

if credit risk is transferred by selling (securitizing) a loan, the bank's incentive to credit-screen and monitor declines. Keys and al (2010) QJE find that securitized pools of subprime loans had default rates hat were 10% to 25% higher than similar mortgages  that were not securitized. Elul (2011) present additional evidence consistent with reduced screening of securitized mortgages.

If investors in mortgage and asset-backed Securities recognize the loan-selling bank's suboptimal-screening, they should discount the value of securitizred loans, forcing the bank to internalize this inefficiency.

In others words, a bank de cision to sell or retain a loan would weight the economic benefits of risk transfer against the economic costs of inefficient screening. (see Han and al (2015) Journal of finance.

*

What do you think of the "health" of the Capital Asset Pricing Model?

The CAPM is based on a robust theoretical framework, but empirically demonstrated weakness. The beta does not seem to be the only factor that can explain the risk-return relationship. Do you really think that the CAPM is dead?

Dávid Zibriczky · ImpressTV Limited

We have studied CAPM whether it's linearity holds in extreme conditions or not. We found that in come cases the nullhypothesis of CAPM linearity should be rejected. You can find more details here: https://www.researchgate.net/publication/227358232_Non-parametric_and_semi-parametric_asset_pricing

We also studied the capability of capturing risk in one meausre and predicting future returns for securities. We compared one factor models, like standard deviation, CAPM beta, and additional two entropy based methods. Based on the results we found both advantages and disadvantages. CAPM beta is good for explaining returns in short term, but it less effective predict them for the next period because the value of CAPM beta for each securities is changing with a high variance over the time. More details here: https://www.researchgate.net/publication/270221149_Entropy-based_financial_asset_pricing

Overally I think the theory is usable, however it has weaknesses. It can be a good basis for a more efficient multi-factored models, like Fama-French model (SMB-HML), Carhart model (SMB-HML-Moment) or additional factors like liquidity or entropy.

How are the benefits of asset management measured and tracked in your organisation?

The ISO 55000 mentions several benefits of implementing asset management. How valid and practical are these benefits? In the IAM Academic Research Network Working Group on "Measuring the Benefits of Asset Management" we want to develop a framework/methodology to identify the critical success factors that ensure that the benefits to an organisation by implementing good asset management practices are achieved. To begin with we are interested in how various organisations have identified, quantified, and tracked “benefits” of asset management activities over time.

Peter Prischl · University of Applied Sciences Kufstein

Dear Rob,

I find the "Platform" approach interesting: If you view best-practice asset management as a platform, as an enabler in your organization, what can you DO that you cannot do today?

When should we use SUR instead of fixed or random effect model?

We are doing research on capital structure. To the best of my knowledge, researchers usually applied panel with fixed of random effect. Few studies use SUR when they focused on macro variables. When should we use SUR in stead of panel with fixed or random effect? As the results I got quite different when running SUR. Many thanks

Fabrizio Rossi · University of Cassino and Southern Lazio - Italy

I agree with Enrico Onali. If your work involves issues of CG, a good study is to BB.

How do I do Logit regression with time-series data?

Hi! I want to use logit regression whit lags of the independent variables. Now, I was told I need to use time fixed effects for this (even though I don´t get why). Is this true, and if so, how do I do it? I can't both set the data to time-series and panel (tsset and xtset), but have to choose. Also, can I go around this problem by constructing the lagged independent variables ouside of Stata, in Excel, and then xtset the dataset? I'm a novice at both econometrics and at Stata, so please explain to me as if I was a child?

Rebecca Reeve · University of New South Wales

Have a look at Stata's xtlogit command.

How do I calculate asset allocation policy of a mutual fund asset allocation?

Must I take the unquoted shares also?

Bheergoonath Amit · University of Mauritius

thank you guyz :-) (y)

How can I manage Product Portfolio for Engineer-to-Order industries?

Working on a research topic, I am faced with this question " How can we propose a Product Portfolio Management framework for Engineer-to-Order industries?" Although, these industries have certain product families, they offer totally different products to their customers, based on what customers need. Sometimes they accept orders from customers, they design products and services just for them, but at the end they notice that the process was not as profitable as what they expected.
So, how can these industries define their product portfolio in a way in which they still have demands and the whole design, manufacturing and delivery process remains profitable for them?
Are there any related case-studies or articles in the literature? Thank you for your help and kind answers in advance.

Arian Razmi Farooji · University of Oulu

Is anyone doing research on entropy and Stock market?

Is anyone doing research on entropy and Stock market?

It would be great to know if someone here is doing the same kind of research which will help in sharing ideas to each other.

Dávid Zibriczky · ImpressTV Limited

Hi Guys,

I'm currently doing my PhD in Finance. One of my topics is the entropy-based risk estimation methods in stock market. Maybe this research can be interesting for you: https://www.researchgate.net/publication/270221149_Entropy-based_financial_asset_pricing

Another interesting paper, an overview about the application of entropy in finance: http://www.mdpi.com/1099-4300/15/11/4909

What is the primary instrument to measure different fund( pension, hedge and mutual fund) performance?

I want guidance or literature from anybody that can guide me to measurement items (questionnanires items) on measurement of pension/hedge/mutual fund or firm performance. The model I developed requires primary data and not secondary data for firm's of fund's performance. Thanks

Angel Marchev · University of National and World Economy

(Not a full answer - just a reminder)
I am sure you know this, but do not trust Sharpe Ratio (or any of the conceptually similar measures) as it is not a monotonous function for negative returns.

If the time series data is stationary at a level, can we apply VAR?

The data I have is stationary at level for both of the two variables. Can I apply VAR?

Ghazi Al-Assaf · University of Jordan

Yes in this case you can use VAR. However, I suggest to check the stantionarity of your series using other unit root tests such as PP and KPSS. If you have the same results, you need to to estimate VAR then, you can also try the SVAR.

How do you measure money and liquidity in a financial market?

How do you measure money and liquidity in a financial market?

Fábio Henrique Bittes Terra · Universidade Federal de Uberlândia (UFU)

The usual measures of liquidity are the size or volume of the means of payment, which start from the monetary base, going through the more liquid financial assets (money in public power and account deposits - that is to say, money or absolute liquidity), to the more illiquid financial assets (M4 or M5, depending on development level of the economy).

Central Bank controls these variables when doing monetary policy, i. e., the public policy that deals with keeping the liquidity level in the economy.

For example, when Central Bank moves the interest rate, it is trying to change the liquidity between the means of payment and, thereby, between financial and real assets.

Is the Fed interest rate as a measure of the liquidity crisis is not appropriate?

I am using the fed rate as a proxy for Liquidity crises in US, however I had a comment that  the interest rates can be used for general monetary policy purposes. So, I have to provide evidence that the Fed interest rates are not used in us from 1954 to 2011  for general monetary policy purposes, then this quantity cannot be used as a measure of liquidity crisis. Is there any thing in the literature related to this issue. what is the best proxy for liquidity crisis ( credit crunch) ?

David M. Fields · University of Utah

Dear Mohammed, I am attaching my RIPE paper.

In late nineties and early 2000 the vanishing dividends trend was prevailing, what is the trend today and why?

Because trading in the U.S stock market is very active investors seeks speculative profits over dividend income

Can the coefficient of lagged debt variable be negative in capital structure model?

The coefficient of lagged debt ratio has economic meaning in capital structure research that makes use of dynamic model specification. From the coefficient of the lagged debt variable, researchers usually calculate the speed of adjustment to the target debt (capital structure) level. But the coefficient of this lagged debt ratio is usually constrained between positive one and zero. Can the coefficient of lagged debt variable be negative in capital structure model? if yes, does it indicates negative adjustment to target debt (capital structure) level.

Shivbhakta Joshi · Tri Nano (Nanotechbiz.org), Qcfinance.in, Freegregmatclass.com and IndoIsraelReserch.com

Yes it can be.

refer to my article on quantcorpfin blog.

Are there any papers or books which examined historical change of the concept "hoarding"?

I am wondering why the concept of hoarding has disappeared after Keynes's General Theory. Are there any economists who tried to extricate the concept of Hoarding after Keynes?

The concept of Hoarding was once one of the most important ones. For example, it was an essential part of D. S. Robertson's framework of his monetary theory. However this concept does not play any conspicuous role in the economics after Keynes. It was practically wiped out from economics. As I have observed in my post of December 13, 2014 to my own question "Is saving necessarily invested or not? How can this contradiction in Keynes be solved?" (linked below), it seems that Keynes's Liquidity Preference concept has replaced and wiped out the concept of Hoarding.

I am thinking to save the concept of Hoarding and coin it anew as an essential part of the monetary theory of productions. In that purpose, I want to know the conceptual history of the this notion.

Fabrício Pitombo Leite · Universidade Federal do Rio Grande do Norte

From a perspective of History of Economic Thought, see Robinson, Joan (1938). The Concept of Hoarding

Does transformation of microfinance institutions into regulated financial institutions increase accessibility of financing to the low income class?

Most microfinance institutions were founded as non-profit organizations with main mission of providing financial services to the low income class or financially excluded people, mostly women. Although, it appears that transformation of microfinance institutions into regulated financial institutions comes with many benefits such as influx of new capital, deposit mobilization, increase outreach and improved management and governance among others. There is fear that transformed microfinance institutions may deviate from their original mission to serve the low income class and alleviate poverty. More specifically, some observers believe that the transformation of microfinance institutions into regulated financial institutions may encourage profit motive over social impact of alleviating poverty.

Sigit Pramono · Ritsumeikan Asia Pacific University

Indeed, regulatory framework and adequate supervisory mechanism are needed to strengthening microfinance institutions. However, transformation of microfinance institutions into regulated financial institutions itself should be attached with affirmative action programs by the whole stakeholders to bring financial inclusion attained with enhancement financial access for the poor. In this sense, it is time to provide a comprehensive financial education, encourage community development  and empowerment, and government public policy alignment for the poor.

If you had to solve a Hamilton-Jacobi-Bellman equation and you only have to give a quick and dirty (sub optimal) solution, how would you proceed ?

Say, to optimize buy/sell controls from a portfolio with transaction costs over 180 periods

Theoretically, you use spectral decomposition, search for viscosity solutions ,
discretize, etc then solve backwards ... but run into curse of dimension or it yields too difficult to interpret and unstable solutions anyhow. Some adaptive online sampling methods seem to work sufficiently well (Q-learning, TD learning, NDP, SMC etc.) . Has anyone used them ? Thanks

Duc Pham-Hi · ECE Paris Graduate School of Engineering

Thanks Sergei, in fact I was thinking about that : a robot that learns to trade based on charts should work best if it had a way to decide when, to switch between forward (new learning) and backward (consolidation of old maps) optimization. Maybe a simple measure like, the new data, how far is it ( > X times standard deviations) ? if it's new go forward, if not, go backwards.

Does capital structure affect firm growth or growth affect it?
Is there a model of growth as a dependent variable and leverage as independent?
Krishna Swamy · Western Michigan University

According to Myers, high levels of debt reduces future growth rates. I have empirically tested this proposition and found it to be true.

How to figure out Qn reg Jarrow-Rudd formula with skewness and kurtosis adjustments in actual conditions?
I am trying to implement the Jarrow-Rudd formula for valuing options with adjustment terms for skewness and kurtosis. The Jarrow-Rudd formula in its simplest variation, gives the value of the option C (F) as:

C (F) = C (A) +λ1Q3 +λ2Q4
where C(A) is the Black-Scholes Option price, Q3 and Q4 involve some term of derivative of St at strike price K.

I don't understand how to work out this derivative in actual conditions. Their paper on approximate valuation of option pricing does not give any indication of this and I do not have access to their other paper on the testing of the formula with market prices (this paper is part of the book on option pricing edited by M Brenner.) Does anyone have an idea as to how to decode this type of derivative?

Paul Louangrath · Bangkok University

If you wish to pursue this subject further, you are most welcome to contact me via email. With words file, the equation may be more legible. This is my email: Lecturepedia@gmail.com

Cheers.

Does Anyone Use The Network Theory Principles in the Financial Application, Especially in Stock Market Issues? IF Yes, What is Your Focus?

how we can use these models in stock market?

Hossein Dastkhan · AmirKabir University of Technology, Imam Javad University (IJU).

Dear Prof Golo & Andrikopoulos and the other respondents

Thank you for your answers. I really want to know the objectives of these kinds of researches. Are all of these researches done to analyze the systemic risk and casecade effects? are the network models usable for analyzing systemic risk in stock market?I do appreciate your answers?

Is unit root testing good enough for testing random walk behavior or test for efficiency in market?
There are a good number of empirical papers that conclude through unit root testing whether a given market is efficient or not and maximum times the series contains unit root which confirms that markets are efficient. I also tested for many time series related to stock market and exchange rates and found unit root at levels and stationary at first difference. But common sense says it can't be possible that every market is efficient as people makes money in market through trading rules also by following fundamentals of stocks. I find that confusing.
Vince Daly · Kingston University London

The ADF test employs lagged differences. If their coefficients are non-zero then there is an element of predictability in prices - even if a unit root is not rejected.

What are the assumptions of CAPM? Are the assumptions relevant or irrelevant in today's context?
The development of portfolio theory by Markowitz.
Bikramaditya Ghosh · International School of Management Excellence- ISME

What I personally think as a researcher in Behavioral Finance is that all investors , especially in country like mine (i.e. India) are completely a set of complex & differentiated in nature, having very less financial literacy & full of ethnic bias, as far as investment is concerned. These make them concentrate very heavily on Land and Gold as an traditional ethnic investment vehicle. They are not in a position to maximize economic utilities. May be in a developed economy with less cross sectional ethnicity and higher level of financial literacy it will be in good effect.

What is your opinion on: "The benefits of Naive and Markowitz diversifications have the same origins. They vary only in degree"?
Not true.
Naive diversification is combining assets into portfolios randomly and ignore correlation. In contrast, Markowitz diversification is combining assets with correlation coefficients.
John King'athia Karuitha · Karatina University College

The problem with MPT is the presupposition that somehow, the correlation between assets" returns is less than unity, and ideally negatively correlated. This is a naive assumption in itself, as the global financial crisis taught us. The actual naive strategy does not make such an assumption....it simply advocates the avoidance of putting all eggs in one basket so that they do not get crushed. This is where you realize the two converge...

Who are the top researchers in Behavioral finance?
Who are they, what are they researching and what are the universities leading the topics?
Theodore C. Moorman · Baylor University

The following two papers are highly cited behavioral finance papers.  In this regard, their authors may be considered top researchers.

Barberis, N., A. Shleifer, and R. W. Vishny, 1998, “A Model of Investor Sentiments,” Journal of Financial Economics 49, 307-343

Daniel, Kent, David Hirshleifer, and Avanidhar Subrahmanyam, 1998, “Investor Psychology and Security Market Under- and Overreactions,” Journal of Finance 53, 1839-1885.