Thursday, September 15, 2016

Liver cirrhosis mortality, alcohol consumption and tobacco consumption over a 62-year period in a high alcohol consumption country: a trend analysis


Background:

The purpose of this study is to examine the trends within liver cirrhosis mortality and its relationship to alcohol and tobacco consumption. Pulling data from several countries aids this study in an effort to improve forecasting accuracy for alcohol consumption and future mortality rates for liver cirrhosis.

Methods and Discussion:

For this paper, trends were calculated using Joinpoint regression analysis. This type of regression analysis provides the beginning and end results for a single trend. The data provided throughout the study was run through this regression analysis for the purposes of discovering increasing or decreasing trends in liver cirrhosis. Within this study, trend analysis revealed a couple key results. First, the decrease starting in 1969 among females and in 1977 among males concerning liver cirrhosis mortality, is related to decreases in alcohol consumption starting in those same years. Lastly, the same results were related to decreased in tobacco consumption starting in 1972. Figure 1 below illustrates that since the 1970’s there has been a decrease in liver cirrhosis mortality while at the same time alcohol and tobacco sales and alcohol treatment has also been on the decline.


Criticism:

Authors John Ulrich and Monika Hanke state that this approach offers less bias compared to studies using national survey data. However, this study also displayed many assumptions about what may and may not be the cause for decreased trends in liver cirrhosis. The authors did not go into detail about what actually accounted for the decreasing trend, rather it appeared that they gave their best educated guess as a result of the analysis.

Source:

Ulrich, J., & Hanke, M. (2015). Liver cirrhosis mortality, alcohol consumption and tobacco consumption over a 62-year period in a high alcohol consumption country: a trend analysis. BioMed Central Research Notes, 8, 1-7.

Stock Trend Analysis and Trading Strategy

Summary:

He et. al. (2006) developed a highly empirical trend analysis methodology to assess and anticipate future stock trends and trading strategies.  To do this, they formulated a three step approach which combines data partitioning, linear regression, and prediction.  Once combined they recommend using the newly minted trend prediction methodology; Trading based on Trend Prediction (TTP).  The authors additionally devised this methodology as they observed previously that, “patterns in long time series data repeat themselves due to seasonality or other unknown underlying reasons… [and] this information will be able to help decision-making on the trading strategy in stock market trading practice.”

Process:


At the outset the scholars developed sophisticated calculus for data preparation as they needed an ability to train the data for the analysis. The empirical analysis of this step can viewed as a “window” in the training series to observe test data. See Figure 1 below for visual representation:


S1 : p1, p2, …, pwtr
S2 : p2, p3, …, pwtr +1
Sn : pN, pn+1, …, pwtr+N-1



During the “data mining” phase it takes place over three distinct steps; Initialisation, Data Mining, and Test models on test data.  During the Initialisation phase, a training time period is selected to observe the stock data (i.e. – 1999-2000) whereby the data is sampled from the first day of the year to the last day of the year. During the data mining phase, the now trained data is “partitioned” into clusters (k-clusters) to be repurposed later for linear regression modeling. Finally, in the last step, the data can be modeled and calculations can be made for the returns and trading strategies can be identified.

The authors additionally delineate two distinct trading strategies: Naïve Trading (NT) and Trading based on Trend Prediction (TTP). NT is the basic buy low, sell high proposition, while TTP is the same as NT, but incorporates forward looking trend analysis on future stock seasonality for better decision-making.  To that end, they only “sell the share if the trend prediction is downward.”

In testing the method, the scholars ran the data for the 1999-2000 test period against the corresponding training period 1989-1998. What they found was, “TTP’s performance exceed[ed] NT’s performance in most countries… [and] clearly indicates that the trend prediction is able to find the correct trend in some cases.” However, they also found that TTP was not generalizable in predicting trends in all cases.

Finally, they conclude that the results show the proposed methodology improves the trading performance over some existing strategies in some cases. Further, they found that the methodology can correctly predict future trends in stock price, but not predict them well in other situations. They also leave this study open for further research and suggest future ways to further improve the method.

Critique:

Despite this studies overall findings in support of correctly predicting, in some instances, future stock prices -- this study lacks much needed qualitative explanations and support (i.e. – 4 pages in length). The study, although heavily empirical, could make clear changes to further improve the usability of the study by appealing to a wider audience who wishes to utilize sophisticated trend analysis as mentioned herein, but do not have the mathematics background to do so.

Source:


Wednesday, September 14, 2016

Summary of Findings: Devil’s Advocacy (3.5 out of 5 Stars)

Note: This post represents the synthesis of the thoughts, procedures and experiences of others as represented in the articles read in advance (see previous posts) and the discussion among the students and instructor during the Advanced Analytic Techniques class at Mercyhurst University in September 2016 regarding Devil’s Advocacy as an Analytic Technique specifically. This technique was evaluated based on its overall validity, simplicity, flexibility and its ability to effectively use unstructured data.

Description:

Devil’s Advocacy is an analytic modifier that tests assumptions and critiques existing analysis. This is done through the use of a specific individual or team that actively looks for potential inaccuracies or problems within an analysis. This can also be done by the advocate(s) supporting a minority point of view and championing it versus the prevailing analysis.

Strengths:

  • Works with unstructured data
  • Provides alternative viewpoints if the Devil’s Advocate is an expert and at the same level as the rest of the team.
  • It can be simple to set up and create, and is flexible enough to use in any environment.
  • Can help to uncover biases and assumptions in reasoning

Weaknesses:

  • May not be successful if the Devil’s Advocate role is not formalized and  respected within the team
  • Has the potential to create tensions in analytical teams
  • If done incorrectly, it has the potential to unnecessarily reduce confidence (by intelligence consumers) in an adequately supported estimate
  • May not work if team members are unable to accept or perceive the ideas of the Devil’s Advocate
  • If pressed for time, it is difficult to adequately implement

How-To:

  1. Designate a person/team to look at a previously established assumption or analysis.
  2. That person/team then proceeds to use available data and experiences to challenge the assumption or analysis by providing alternative explanations, outcomes, or reasonings that are just as likely to occur given the information available.  
  3. Present these finding to an individual or group willing to actively listen to the Devil’s Advocate’s findings.

Application of Technique:

A group of Graduate Students at Mercyhurst University developed a Devil’s Advocate exercise about North Korean nuclear development strategies.  Various types of role-played national security  intelligence assessments were developed: OSINT, HUMINT, SIGINT, GEOINT, IMINT.  See “National Security oriented Devil’s Advocate Exercise used in class [North Korea]” below.

In class the participatory team challenged “All-Source Team Black’s” overall estimate on North Korean nuclear weapons and developed reasons to accept or reject the overall analysis for it’s legitimacy of sources and built in key assumptions.  Instructions on how to use the process were issued from the “CIA’s Analytic Tradecraft Primer: Structured Analytic Techniques for Improving Intelligence Analysis” Also, students were able to provide personal input on their personal understandings of the situation.  The team had 15-minutes to work through this problem.

For Further Information:

National Security oriented Devil’s Advocate Exercise used in class [North Korea]: https://drive.google.com/file/d/0BxOGezwoHVUCTEl5VTllRmRNbmc/view?usp=sharing

CIA Analytic Tradecraft Primer: Structured Analytic Techniques for Improving Intelligence Analysis, pg. 17: https://www.cia.gov/library/center-for-the-study-of-intelligence/csi-publications/books-and-monographs/Tradecraft%20Primer-apr09.pdf

Devil’s Advocate Wikipedia:

Red Team: How to Succeed By Thinking Like the Enemy, pg. 216-219:
https://www.amazon.com/Red-Team-Succeed-Thinking-Enemy/dp/0465048943

Friday, September 9, 2016

Improving Executive Decisions by Formalizing Dissent: The Corporate Devil's Advocate


Summary:

This article proposes and outlines the method of Corporate Devil's Advocate to ensure valid decision-making inputs. Herbert and Estes (1977) state that the level of sophistication required to cope with the environment and its impact creates the need for "full-time professionals with advanced skills" to investigate problems and recommend solutions to the overloaded line executive. However, the analyses of these professionals might possess more influence than is warranted due to the executive's time and technical skill limitations. Things such as analytical breakdowns and insufficiencies, improper assumptions, or uncertainty absorption can often be covered up by the intricacies of the techniques applied to the problem. All of these things "can operate to increase the executive's blind acceptance of, and implicit reliance on, the analytical process."

The authors review historical examples of formalized dissent, noting that while the techniques vary widely in specifics, they have in common the careful structuring of independent reviews, to balance and test the adequacy of an analytical endeavor. These formal dissenting roles are played by persons investigating the position or proposal of another, and attempt to expose biases and inadequacies while generating counter-proposals. One of the oldest examples of this formalized dissent role, called the "Devil's Advocate," occurs within the Roman Catholic Church. It has been in use since the early 1500s to investigate proposals for canonization and beatification. Separation of the functions of promoter and dissenter ensure that both sides of the question will be thoroughly analyzed, since the roles are not subject to intrapersonal conflict by residing in the same person.

The Process:

The authors assert that the essence of these techniques can be formalized for use in corporate decision processes. First, the Devil's Advocate starts with the analyst's final copy of the proposal, becoming immersed in the report only after having conducted an independent audit of the problem situation to verify that the problem identified or assumed is the real problem. Reconstruction of the analyst's logic and data gives the Devil's Advocate an in-depth trace, and all fallacies or inaccuracies uncovered must be listed with their impacts on the recommendation. When the report of the Devil's Advocate is completed, a special confrontation session is held where the proposing analyst and Devil's Advocate each present their own efforts to the decision-maker. After a formal critique of the proposal, the analyst and Devil's Advocate rationally rebut each others' reports. In the best-case scenario, this process will result in a new proposal that eliminates the fallacious parts of both recommendations and is comprised of the soundest elements of each. Failing this, however, the decision-maker must decide which - if either - recommendation to accept. The advantage is that now the shortcomings are known.

Conclusion:

Since major decisions today are crucial to long-term success in a competitive and volatile market place, the quality of these decisions must be optimized. Creating an official "Nay-sayer", charged with the responsibility of dissenting with recommendations, aids in pointing out logical flaws and other fallacies or inaccuracies in major one-sided proposals. An official dissenter can heighten the probability that decisions will be thoroughly researched and proposed solutions based in reality. The Corporate Devil's Advocate can also help ensure that marginal or unwise decisions are not made at all. 

Critique:

The authors point out that the role of Devil's Advocate can be internal or external. If it is internal, then the concept must be enthusiastically understood and accepted to be workable. Acceptance by the chief executive and other executives will permit the Devil's Advocate to undertake the role freely, without fear of reprisal or recrimination. It would be important to ensure that the Devil's Advocate always be at the same hierarchical level as the analyst who initially wrote the proposal to avoid pressure or other repercussions. Additionally, it would be wise for the Devil's Advocate to report directly to the President of the firm. If the method is outsourced to an external entity, like a consulting firm, then there could be difficulty in recreating the processes through which the conclusions of the initial analyst were derived. However, an independent analysis of the problem might yield alternatives and new insights to assist the executive in their decision-making process.    

Source:

Herbert, T. T., & Estes, R. W. (1977). Improving executive decisions by formalizing dissent: The corporate devil's advocate. The Academy of Management Review, 2, 662-667. Retrieved from http://www.jstor.org/stable/257518

Devil’s Advocacy in Managerial Decision Making


Summary:

What this report looked to do was to first define what devil’s advocacy (DA) does and how it is supposed to function. Then, it quickly evaluated the merits of DA in laboratory settings and field settings. The evaluation of DA looked at not only DA, but also dialectic inquiry (DI) as well as expert advice (E). DA itself, at its most basic, is a procedure that involves one or several persons who are appointed to raise objections to favored alternatives, challenge underlying assumptions, and potentially present differing ideas. According to the study, the introduction of conflict to challenge previously formed assumptions is the definition of DA that is generally agreed on.

However, while researchers agree on the definition, how the DA goes about their work does not have a wide consensus. First, at what point does the DA intervene in the process? Next, should the DA deride the majority position or should they champion the alternative?  Finally, the whom and how many should play the role are also not agreed on.

According to the results of the field and lab testing, it is agreeded that introduced conflict (as in devil’s advocacy) works. Laboratory studies have found that DA or DI yields better results as opposed to E. How the study functioned is that with three groups, one group received an “expert recommendation” (the E group) another group received the same recommendation but with a critique (the DA group), and a third group received a recommendation, a critique, and another recommendation stemming from the critique (a DA/DI group). Testing of the group’s ability to make strategic decisions showed that the superiority of the DI/DA groups versus the E group was statistically significant. However, the difference between DI/DA was only marginally significant. It did show that conflict introduced into the decision-making  process yielded strong results.

In field tests, tests involving DI as a version that offers a counter-plan against the prevailing expert decision do tend to yield far better results as well. From private sector to public sector, field tests point towards DI, and even just DA alone, having a better chance to produce more options that are novel versus a standard experts opinion. The availability of more options versus the one expert opinion yielded a management group that had a deeper understanding of a problem. Additionally, it reduced the potential for groupthink created by the expert advice. Furthermore, it leads to more alternatives and greater overall satisfaction with the decision brought on by a sense of having considered all the options.

Conclusion:

The study concludes with how to employ a devil’s advocate scenario that looks to address the three problems stated earlier. First and one of the more complicated issues, the role of the DA is dependent on the structure and nature of the group. Constraints such as time, structure, and goal all alter how to use the devil’s advocate. If dialectic inquiry is used, it could take a substantial amount of time to construct a counter strategy. If a group already has a great deal of conflict within itself, the advocate can be used to structure the debates to prevent one strategy from receiving more resources than the others strategies receive.

Second, the advocate should make every attempt to avoid advocating for one particular option. This would prevent them from becoming a “carping critic” and ultimately weakening the role of the advocate. This type of devil’s advocate can harm the decision making process and the management’s views of situation. Instead, the advocate should seek to highlight every other option.

Third, concerning the logistics of the advocate, further research is needed. Rotating the advocate around each of the members of the group allows each member to understand the role of the devil’s advocate. However, if one person is selected, they have the chance to become a more effective advocate. As to which option is stronger, it remains to be discovered.

Finally, and separate from the three problems, underlying all of the study is the ultimate need for management to be open to the devil’s advocate or dialectic inquiry methods. In order for the devil’s advocate’s work to have any impact, their role must be taken seriously and legitimate thought must be given to what the advocate states. This need ultimately falls on management’s ability to deal with and accept that there may be multiple ways of dealing with a situation and that their views and ideas are not always correct. Without management’s ability to accept different views, the role of the devil’s advocate would be domesticated or even harmful. However, once caveat is that even in these rigid situations, the devil’s advocate could be used to forcibly breakdown groupthink situations.

Critique:

The only real piece of criticism that can be made about this report concerns the metrics by which the laboratory experiments were measured against. What constituted a more sound, strategic decision? Granted, information on where to find it was included within the report, but a brief description would have helped to drive home some of the key points of the study a little better.

Source: Schwenk, C. R. (1984). DEVIL'S ADVOCACY IN MANAGERIAL DECISION-MAKING. Journal Of Management Studies, 21(2), 153-168.