Cross impact analysis

Last updated

Cross-impact analysis is a methodology developed by Theodore Gordon and Olaf Helmer in 1966 to help determine how relationships between events would impact resulting events and reduce uncertainty in the future. [1] The Central Intelligence Agency (CIA) became interested in the methodology in the late 1960s and early 1970s as an analytic technique for predicting how different factors and variables would impact future decisions. [2] In the mid-1970s, futurists began to use the methodology in larger numbers as a means to predict the probability of specific events and determine how related events impacted one another. [3] By 2006, cross-impact analysis matured into a number of related methodologies with uses for businesses and communities as well as futurists and intelligence analysts. [4]

Contents

Development

The basic principles of cross-impact analysis date back to the late 1960s, but the original processes were relatively simple and were based on a game design. [1] Eventually, advanced techniques, methodologies, and programs were developed to apply the principles of cross-impact analysis, and the basic method is now applied in futures think tanks, business settings, and the intelligence community.

Origins

Theodore J. Gordon writes that cross-impact analysis was the result of a question: "can forecasting be based on perceptions about how future events may interact?" [1]

The first format of the method was a card game titled Future, where events were determined by probabilities, a special die, and impacts from previously played events. [1] This initial game format of cross-impact analysis was programmed for computers at UCLA in 1968. [3] From this point on, the methodology underwent increasing development and sophistication to meet certain needs and conditions of users.

Early development

As cross-impact analysis expanded in the early 1970s, researchers and futurists modified the basic principles to improve on the methodology. In 1972, researchers at the Institute for the Future added time-series instead of "Slice of Time", Norman Dalkey used conditional probabilities, and Julius Kane developed "KSIM", a simulation technique that used interactions between time series variables rather than events. [5] In 1974, Duperrin and Godet developed Cross Impact Systems and Matrices (or SMIC) in France for prospective forecasting studies. [4]

Advancements in simulation models continued into the 1980s. In 1980, Selwyn Enzer at the University of California incorporated cross-impact analysis into a simulation method known as Interax, The Delphi technique was combined with Cross Impact Analysis in 1984, and researchers at Texas A&M University used Cross Impact in a process called "EZ-IMPACT" that was based on Kane's algorithm from KSIM. [5]

Recent development

After simulation models and methods were developed for cross-impact analysis, analysts began to develop the range of topics that it could address. Cross-impact analysis was being used to solve real world issues as John Stover applied the methodology to simulate the economy of Uruguay. [5] However, real world application of the methodology advanced rapidly in the 1990s. By 1993, SMIC was used for subjects as diverse as the nuclear industry, world geopolitical evolution, and corporate activities and jobs to 2000. [6] In 1999, Robert Blanning and Bruce Reinig from the Owen Graduate School of Management at Vanderbilt University utilized a modified form of cross-impact analysis to determine futures for Hong Kong and the Hong Kong economy as the United Kingdom relinquished control to the People's Republic of China. [7]

Methodology

Cross-impact analysis has two schools of thought and ways of approach. The first is the futures forecasting style that originally developed the methodology. The second is a sub-school of intelligence analysts which modified the original methodology to better address their needs. Nevertheless, cross-impact analysis is based upon the premise that events and activities do not happen in a vacuum and other events and the surrounding environment can significantly influence the probability of certain events to occur. [8]

Cross-impact analysis attempts to connect relationships between events and variables. These relationships are then categorized as positive or negative relative to each other, and are used to determine which events or scenarios are most probable or likely to occur within a given time frame. [4]

Futures forecasting style

The futures forecasting style is based in the systems and methods developed during the 1970s and 1980s and follows several strict steps.

First, analysts must consider the number and type of events to be considered in the analysis and create an event set. Because each event will have an interaction with every other event, Gordon recommends that 10–40 events be used. [8]

Second, analysts must take the initial probability of each event into account. The probabilities of events must be taken in isolation from one another. [8]

Third, analysts need to generate conditional probabilities that events have on each other. Basically, this asks the question, "If event 'A' occurs, what is the new probability of event 'B' occurring?" This must be done for every possible interaction between events. [9]

Fourth, analysts must test their initial conditional probabilities to ensure that there are no mathematical errors. This is usually done by running simulations in a computer several times. [9]

Fifth, analysts can run the analysis to determine future scenarios, [4] or determine how significant other events are to specific events. [10]

Mathematical technique

The futurist forecasting style of cross-impact analysis relies heavily on probabilities and mathematics in its processes. Initial probabilities and conditional probabilities are calculated using either percentages [9] or factor numbers equivalent to percentages. [4] Researchers must calculate the numerical values or percentages very precisely to ensure accurate results and that impacts of events on each other are realistic and not contradictory. In addition, researchers must be careful when calculating negative impacts as the negative influence can create mathematical impossibilities. [9]

This mathematical strictness makes the futurist forecasting style of cross-impact analysis uniform and differences in actual analytic methods, simulations and programs have only minor differences to fit the needs of the specific researcher or analyst.

Relationship to Delphi technique

The accuracy of the math and specific events requires special expertise in the events or topic of discussion. In order to get the insight needed to get events and calculations, analysts typically contact a large number of experts and ask their opinions on events or probabilities in person as groups [9] or through surveys. [4]

These groupings often resemble the Delphi Technique, which is an analytic technique that gathers a group of experts on a subject together and asks their opinion on a scenario or prediction. Usually, analysts consider the average prediction or scenario as the most likely to occur. [11] The two are so closely related, that analysts often use the two techniques in combination or as part of a larger methodology. [5]

Strengths

The futurist forecasting style of cross-impact analysis carries a few key strengths. Its use of groups of experts ensures a number of opinions worth considering when calculating probabilities of events. The level of mathematics in calculating probabilities ensures that the results are as accurate as a researcher can make them. In addition, when used on consort with other analytic techniques, this type of cross-impact analysis can give greater quantitative results to an otherwise qualitative analysis. [9] The relative conformity of methods ensures that analysts using different methods or simulations can come to similar results, making the results testable in a broader setting.

Weaknesses

Many of the strengths of the futurist forecasting style of cross-impact analysis give rise to many of its weaknesses. The conformity of the style generates a certain level of inflexibility when dealing with variables other than events, like environmental conditions or political issues. In addition, the severe level of mathematics involved in this style leads to long delays as scenarios must be run to ensure mathematical accuracy of probabilities, [12] or particular issues with Bayes' theorem appear. [13] The level of math also require researchers to either be knowledgeable in math or additional computer programs to deal with the scenarios and probabilities of the method.

Intelligence analysis style

Shortly after Theodore Gordon and Olaf Helmer developed the original cross-impact method, the United States intelligence community picked up the technique and has been using it for over thirty years. [2]

While the basic premise of relationships and impacts between multiple variables remains the same, the intelligence community modified cross-impact analysis to meet its various needs.

The intelligence community has created a more flexible and variable system than the original methodology. Event relationships and impacts are still similar to the method incorporated by futurists. [14] However, intelligence analysts have expanded the parameters of cross-impact analysis beyond comparing events to include variables like environment, political circumstances, and popular opinion to influence probabilities of certain events. [15] In addition, intelligence analysts can choose to use more flexible measurements like "enhancing", "inhibiting", or "unrelated" instead of the rigid mathematics of the tradition methodology to include non-event variables. [16]

Cross-impact matrix

A major part of the intelligence analysis style of cross-impact analysis is the cross-impact matrix. The matrix is a visualization of the cross-impact analysis and allows for modification. It also allows an analyst to find both the most influential variables and those variables that are impacted by the most other variables, not just direct, one-to-one relationships. [17] While several traditional cross-impact analysis methods suggest the creation of a matrix, the priority still relies in probabilities, one-to-one relationships, and the order of events. [12]

In the intelligence analysis style cross-impact matrix, analysts use pluses and minuses instead of numerical values allowing for non-event variables and allowing the analyst to compare variables directly to all other variables without calculations. [18]

Strengths

Intelligence analysis style cross-impact analysis has several key advantages. The flexibility of the model allows for analysts to measure different types of variables against each other, not just probable events. [19] In addition, the ability to discard stringent mathematical criteria means that researchers do not need extensive mathematics training or specialized software to use cross-impact analysis. This also enables experts in a topic to use the methodology relatively quickly without having to cross-check the numerous calculations faced by the Futurist Forecasting Style. [20]

Weaknesses

The lack of stringent procedures of the intelligence analysis style also bring considerable drawbacks. The flexibility of the style relies heavily on the opinions and knowledge of the analysts involved, and is difficult to reproduce results with a different group. In addition, the option to remove mathematics can harm analysts by creating results that do not have numerical values to back them. This lack of mathematics may make the process easier at first, but the amount of specialized software is limited when compared to the Futurist Forecasting Style, making work more tedious as the number of variables increases.

Applications

Researchers can use cross-impact analysis for a wide variety of applications. Futurists have already used the methodology for forecasting events in specific industries, politics, markets, and even entire communities. [6] [7]

In intelligence analysis, analysts can use the method to predict events, conditions, or decisions based on a wide variety of variables and conditions at local, national, and international levels. [19]

See also

Related Research Articles

Analysis Process of understanding a complex topic or substance

Analysis is the process of breaking a complex topic or substance into smaller parts in order to gain a better understanding of it. The technique has been applied in the study of mathematics and logic since before Aristotle, though analysis as a formal concept is a relatively recent development.

Statistics Study of the collection, analysis, interpretation, and presentation of data

Statistics is the discipline that concerns the collection, organization, analysis, interpretation, and presentation of data. In applying statistics to a scientific, industrial, or social problem, it is conventional to begin with a statistical population or a statistical model to be studied. Populations can be diverse groups of people or objects such as "all people living in a country" or "every atom composing a crystal". Statistics deals with every aspect of data, including the planning of data collection in terms of the design of surveys and experiments.

Monte Carlo methods, or Monte Carlo experiments, are a broad class of computational algorithms that rely on repeated random sampling to obtain numerical results. The underlying concept is to use randomness to solve problems that might be deterministic in principle. They are often used in physical and mathematical problems and are most useful when it is difficult or impossible to use other approaches. Monte Carlo methods are mainly used in three problem classes: optimization, numerical integration, and generating draws from a probability distribution.

Prediction Statement about a future event

A prediction, or forecast, is a statement about a future event or data. They are often, but not always, based upon experience or knowledge. There is no universal agreement about the exact difference from "estimation"; different authors and disciplines ascribe different connotations.

The Delphi method or Delphi technique is a structured communication technique or method, originally developed as a systematic, interactive forecasting method which relies on a panel of experts. The technique can also be adapted for use in face-to-face meetings, and is then called mini-Delphi or Estimate-Talk-Estimate (ETE). Delphi has been widely used for business forecasting and has certain advantages over another structured forecasting approach, prediction markets.

Futurists are people whose specialty or interest is futurology or the attempt to systematically explore predictions and possibilities about the future and how they can emerge from the present, whether that of human society in particular or of life on Earth in general.

Monte Carlo methods are used in corporate finance and mathematical finance to value and analyze (complex) instruments, portfolios and investments by simulating the various sources of uncertainty affecting their value, and then determining the distribution of their value over the range of resultant outcomes. This is usually done by help of stochastic asset models. The advantage of Monte Carlo methods over other techniques increases as the dimensions of the problem increase.

<span class="mw-page-title-main">Futures studies</span> Study of postulating possible, probable, and preferable futures

Futures studies, futures research, futurism or futurology is the systematic, interdisciplinary and holistic study of social and technological advancement, and other environmental trends, often for the purpose of exploring how people will live and work in the future. Predictive techniques, such as forecasting, can be applied, but contemporary futures studies scholars emphasize the importance of systematically exploring alternatives. In general, it can be considered as a branch of the social sciences and an extension to the field of history. Futures studies seeks to understand what is likely to continue and what could plausibly change. Part of the discipline thus seeks a systematic and pattern-based understanding of past and present, and to explore the possibility of future events and trends.

Network traffic simulation is a process used in telecommunications engineering to measure the efficiency of a communications network.

Predictive modelling uses scientifically proved mathematical statistics to predict events outcomes. Most often one event that a mathematician wants to predict or apply predictive analysis on it is in the future, but predictive modelling can be applied to any type of mathematically stated as "unknown" event, (almost) regardless of when it occurred.

Data analysis Machine Learning Data analysis process inspection. cleansing, generic data-sets and modelling

Data analysis is a process of inspecting, cleansing, transforming, and modelling data with the goal of discovering useful information, informing conclusions, and supporting decision-making. Data analysis has multiple facets and approaches, encompassing diverse techniques under a variety of names, and is used in different business, science, and social science domains. In today's business world, data analysis plays a role in making decisions more scientific and helping businesses operate more effectively.

Futures techniques used in the multi-disciplinary field of futurology by futurists in Americas and Australasia, and futurology by futurologists in EU, include a diverse range of forecasting methods, including anticipatory thinking, backcasting, simulation, and visioning. Some of the anticipatory methods include, the delphi method, causal layered analysis, environmental scanning, morphological analysis, and scenario planning.

Intelligence analysis is the application of individual and collective cognitive methods to weigh data and test hypotheses within a secret socio-cultural context. The descriptions are drawn from what may only be available in the form of deliberately deceptive information; the analyst must correlate the similarities among deceptions and extract a common truth. Although its practice is found in its purest form inside national intelligence agencies, its methods are also applicable in fields such as business intelligence or competitive intelligence.

Analysis of competing hypotheses Process to evaluate alternative hypotheses

The analysis of competing hypotheses (ACH) is a methodology for evaluating multiple competing hypotheses for observed data. It was developed by Richards (Dick) J. Heuer, Jr., a 45-year veteran of the Central Intelligence Agency, in the 1970s for use by the Agency. ACH is used by analysts in various fields who make judgments that entail a high risk of error in reasoning. ACH aims to help an analyst overcome, or at least minimize, some of the cognitive limitations that make prescient intelligence analysis so difficult to achieve.

Event chain methodology Network analysis technique

Event chain methodology is a network analysis technique that is focused on identifying and managing events and relationship between them that affect project schedules. It is an uncertainty modeling schedule technique. Event chain methodology is an extension of quantitative project risk analysis with Monte Carlo simulations. It is the next advance beyond critical path method and critical chain project management. Event chain methodology tries to mitigate the effect of motivational and cognitive biases in estimating and scheduling. It improves accuracy of risk assessment and helps to generate more realistic risk adjusted project schedules.

Words of estimative probability are terms used by intelligence analysts in the production of analytic reports to convey the likelihood of a future event occurring. A well-chosen WEP gives a decision maker a clear and unambiguous estimate upon which to base a decision. Ineffective WEPs are vague or misleading about the likelihood of an event. An ineffective WEP places the decision maker in the role of the analyst, increasing the likelihood of poor or snap decision making. Some intelligence and policy failures appear to be related to the imprecise use of estimative words.

Richards "Dick" J. Heuer, Jr. was a CIA veteran of 45 years and most known for his work on analysis of competing hypotheses and his book, Psychology of Intelligence Analysis.The former provides a methodology for overcoming intelligence biases while the latter outlines how mental models and natural biases impede clear thinking and analysis. Throughout his career, he worked in collection operations, counterintelligence, intelligence analysis and personnel security. In 2010 he co-authored a book with Randolph (Randy) H. Pherson titled Structured Analytic Techniques for Intelligence Analysis.

Structured Geospatial Analytic Method

The Structured Geospatial Analytic Method (SGAM) is both as an analytic method and pedagogy for the Geospatial Intelligence professional. This model was derived from and incorporates aspects of both Pirolli and Card’s sensemaking process and Richards Heuer’s Analysis of Competing Hypotheses model. This is a simplified view of the geospatial analytic process within the larger intelligence cycle.

The following outline is provided as an overview of and topical guide to formal science:

Indicator analysis is a structured analytic technique used in intelligence analysis. It uses historical data to expose trends and identify upcoming major shifts in a subject area, helping the analyst provide evidence-based forecasts with reduced cognitive bias.

References

  1. 1 2 3 4 Gordon, Theodore Jay, Cross Impact Method Archived 2011-07-13 at the Wayback Machine , United Nations University Millennium Project, 1994, p 1
  2. 1 2 Heuer, Richards J., Randolph H. Pherson, Structured Analytic Techniques for Intelligence Analysis, CQ Press, 2011, p 107
  3. 1 2 Gordon, Theodore Jay, Cross Impact Method Archived 2011-07-13 at the Wayback Machine , pp 1-2
  4. 1 2 3 4 5 6 For Learn – Cross Impact Analysis Archived 2011-07-20 at the Wayback Machine , For Learn, Joint Research Centre, European Commission, 2006
  5. 1 2 3 4 Gordon, Theodore Jay, Cross Impact Method Archived 2011-07-13 at the Wayback Machine , p 2
  6. 1 2 Gordon, Theodore Jay, Cross Impact Method Archived 2011-07-13 at the Wayback Machine , pp 2-3
  7. 1 2 Blanning, Robert and Bruce Reinig, Cross-impact analysis using group decision support systems: an application to the future of Hong Kong Archived 2011-07-06 at the Wayback Machine , Elsevier Science Ltd., 1999.
  8. 1 2 3 Gordon, Theodore Jay, Cross Impact Method Archived 2011-07-13 at the Wayback Machine , p 4
  9. 1 2 3 4 5 6 Gordon, Theodore Jay, Cross Impact Method Archived 2011-07-13 at the Wayback Machine , p 5
  10. ↑ Gordon, Theodore Jay, Cross Impact Method Archived 2011-07-13 at the Wayback Machine , p 10
  11. ↑ Heuer, Richards J., Randolph H. Pherson, Structured Analytic Techniques for Intelligence Analysis, p 247
  12. 1 2 Gordon, Theodore Jay, Cross Impact Method Archived 2011-07-13 at the Wayback Machine , p 5-9
  13. ↑ Blanning, Robert, Bruce A. Reinig, Cross-impact analysis using group decision support systems: an application to the future of Hong Kong Archived 2011-07-06 at the Wayback Machine , p 40
  14. ↑ Clark, Robert M., Intelligence Analysis: A Target-Centric Approach, CQ Press, Third Edition, 2010. p 202-203
  15. ↑ Heuer, Richards J., Randolph H. Pherson, Structured Analytic Techniques for Intelligence Analysis, pp 104-105
  16. ↑ Heuer, Richards J., Randolph H. Pherson, Structured Analytic Techniques for Intelligence Analysis, p 105
  17. ↑ Heuer, Richards J., Randolph H. Pherson, Structured Analytic Techniques for Intelligence Analysis, p 106
  18. ↑ Heuer, Richards J., Randolph H. Pherson, Structured Analytic Techniques for Intelligence Analysis, pp 105-106
  19. 1 2 Heuer, Richards J., Randolph H. Pherson, Structured Analytic Techniques for Intelligence Analysis, pp 104-106
  20. ↑ Gordon, Theodore Jay, Cross Impact Method Archived 2011-07-13 at the Wayback Machine , pp 6-9

Further reading

This page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.