Decision Anchoring

A nice summary of how results can be anchored just appeared on the web. This human behavior has great implications in business and technical decisions.

Anchoring sets a biased context for estimation. It is a cognitive limitation that affects the quality of our decisions. Anchoring occurs, for example, when a manager asks for an estimate with something like: "I don’t see how we could commit more than $10,000 to this." $10,000 now becomes the anchor point. This stated amount biases all the following estimates that are generated.

Anchoring can happen in subtle ways. Let’s say you are bidding on a project and you have been led to believe that the customer has a ceiling of, say, $10,000. You are now anchored to this value and will make decisions to try to force your project to fit it. This only seems logical, but it has interesting effects. First, the amount of work you propose will be descoped to fit the budget. But people always are optimistic, so, if you get the job, you will still have more work than money. Then begins the dance of working more for less money (overtime), further descoping or asking for more money. This dance is further discussed on pages 82-85 in Making Robust Decisions.

To demonstrate anchoring, I gave a group of people a simple estimation problem - asking them how long it would take them to wash a list of dishes. I described the dishes in detail, how dirty they were, and what "wash" meant. The mean estimate was 32 min with a standard deviation of 10 min. I then asked another group of subjects to estimate how long it would take to clean the dishes exactly as before, but this time I added "Your partner has told you that the kitchen needs to be clean in 15 minutes." This anchoring resulted in a new distribution with a mean of 18 minutes and a standard deviation of 6 min.

Think of the implications on decision making. All decisions are based on best estimates of past performance, assessments of the current situation, and visions of the future. Every one of these can be clouded by anchoring. You cant totally avoid it. However, you can be aware of how you word your need for information and consciously try not to anchor estimates on which decisions will be based.

Cognitive problems in making decisions

I have been reading "How Doctors Think" by Jerome Groopman. It is one of two books with the same title. Basically, reading this will make you scared to go to the doctor as doctors are human and make lousy decisions, just like all the rest of us. He has a good chapter titled "The Uncertainty of the Expert" which focuses on my favorite topic, decision making with uncertain information. All of Groopman's comments come from cognitive psychology and apply to business and technical decisions as well.

The key point in the chapter is captured in one sentence about half way in: "Physicians, like everyone else, display certain psychological characteristics when they act in the face of uncertainty". Uncertainty arises from 1) incomplete mastery of the available knowledge, 2) limitations of the knowledge, 3) difficulty distinguishing between the 1 and 2, and 4) (he leaves this one out) the variability of the nature of things.

In the face of uncertainty we all tend to:

1. Focus on the positive rather than the negative (except engineers who are pessimists by nature).
2. Ignore uncertainty. This is very evident in how we all talk about technical issue in terms of single values. Luckily we have terms like "about", "near to"
3. Go with what's been done before even if it is based on an unknown and unproven orthodoxy. Of course risk aversion is good and in medicine often leads to the correct diagnosis, whenever the problem is by-the-books. However, in business, technology this aversion can lead to being swamped by the competition.
4. Have a confirmation bias. This means that we look for support for our favorite alternative or hypothesis, at the expense of work on other possible options and discounting the negative (see item 1).

In the medical profession these characteristics are supported by the lack of time, risk aversion and an old-boys-club attitude. It is interesting watching the decision making on the TV program House. Here an arrogant, troubled doctor who hates the establishment diagnoses rare conditions and displays items 1, 2, and 3. He is really good at #3. But, most of us are.

Bayesian Brain and Bayesian Teams

An interesting article "Is This a Unified Theory of the Brain?" appeared in the New Scientist (full text) on May 28th. This is basically a discussion of the work and theories of neuroscientist Karl Friston of the University College in London. His work is based on an earlier theories that the brain makes decisions by trying to make sense out of the uncertainties in the outside world. Basically, you make hypotheses about reality and compare sensory inputs to them, updating the hypotheses and the belief in them as you gather more information. In essence you are constantly updating the probabilities that the hypotheses are true. In fact the wiring in the brain is continuously changing to is suppress prediction errors.

What makes this really fascinating is that 1) this is Bayesian updating and 2) this applies to team decision making also. The first observation has spawned the Bayesian Brain camp of neuroscientists. They believe we are all Bayesian thinkers, updating the probabilities that your hypotheses are correct as you solve small problems (e.g. if I turn the knob, the door will open) and large ones (e.g. If I choose to study the Bayesian brain, I will better understand team decision-making).

This brings us to applying what the neuroscientists are doing on the individual, to what happens in a team making business or technical decisions. These decisions are generally about what courses of action to take to address a current situation (obscured by its immediacy) or the future (clouded by uncertainty). A team that is functioning well will develop alternative courses of action or hypotheses and then gather an communicate information to increase its belief that one is better than the other, or to update the options based on the new information. No different than a single brain, just much more complicated.

What makes it harder is not only the communication of information amongst the team members (a clear focus of Information Management, Business Intelligence and the Webex's of the world), but developing a shared vision of the information. This is not to imply that everyone needs to understand all the information, but that there is some common understanding of the important bits. This is a topic I beat on in Chapter 4 of Making Robust Decisions "Team Don't Make Decisions, But...."

When we were first developing Accord software, an effort to support the team decision making process, we assumed that we could help teams by making what occurs inside one person's head transparent for the entire team. Maybe we should become neuro-scioscientists and study "Bayesian Team Dynamics".

Decision Making for KM and BI

A June 10th article "Knowledge Management and Business Intelligence" tries to tease apart KM and BI. In the piece the author, Richard Herschel, refers to Gartner's definitions of the two terms:

• BI= a set of all technologies that gather and analyze data to improve decision making
• KM = a systematic process of finding, selecting, organizing, distilling and presenting information in a way that improves an employee's comprehension in a specific area of interest Specific knowledge management activities help focus the organization on acquiring, storing and utilizing knowledge for such things as problem solving, dynamic learning, strategic planning and decision making.

What has always amazed me about these and other fields such as Analysis of Alternatives (AOA), Data Mining and even most Decision Support Systems (DSS) is that they are all about developing and managing information to support and improve decision making, yet none of them actually support the decision making process.

The decision making process requires 1) framing the problem, 2) evaluating the alternatives, 3)fusing the evaluation and 4) deciding what to do next. All of the methods listed above help gather and organize information that is vital to good decisions, but all stop short. Decision making requires more than the availability of database information. In fact, as mentioned in the article "up to 80% of business information is not quantitative or structured in a way that can be captured in a relational database". This non-quantitative information is the basis on which many business and technical decisions are made.

Two cases support this. First, a manufacturer of rocket engines uses our Accord software because many of their key early decisions are qualitative and Accord can manage fusing the qualitative and quantitative evaluations. Second, a Fortune 100 company received 20 proposals in response to an RFP for a piece of electronic equipment. In the RFP were over 60 quantitative specifications for size, functionality, reliability, etc. When they reviewed the proposals, they sorted them into two piles, those that met the specs and those that didn't. Then they began to use the unstated, usually qualitative measures to differentiate the acceptable proposals so they could decide how to award the contract.

The point is, most best practices focus on generating and managing information so decisions can be made. They don't spend enough effort on framing, fusing and managing what to do next. Framing and evaluation fusion are the social interactions occur that develop buy-in, accountability and robust decisions. It is these areas that are the hard part, that are not covered in school and are not well supported.

Stuck in 'Analysis Paralysis'?

Unresolved decisions can be very damaging to an organization. You know something needs to be done but can't decide what to do. Deliberation continues among your staff without an actionable conclusion. You have 'analysis paralysis'. Your operation is not moving forward, but you're using resources and your competition is not standing still.

Symptoms of 'Stuck' decision making include the following:

• Holding more than 3 meetings on a single issue
• Continually gathering more information
• Endlessly discussing and deliberating but not coming to a conclusion

'Stuck' deliberation is often resolved at the twelfth hour and by a manager who may be forced to act arbitrarily, if not irrationally. For any organization this is a highly risky way of operating. Here are some pointers for avoiding analysis paralysis:

1. Build a Shared Understanding: Information about the alternatives and criteria in a decision are understood only from each team member's own perspective. Team members may not have a complete picture of the situation, nor the knowledge or time to develop a full, long-term view. The key here is to set up environments that support the sharing of pertinent information needed for the decision.


2. Work to separate Goals from Importance: Separate what is to be achieved (i.e. goals, targets) from how important it is to achieve it. It is easier to agree on goals than what is important.Evaluation uncertainty may swamp out the differences in importance, but only if this goal/importance separation is made explicit.


3. Acknowledge and Manage Uncertainty: The future is always uncertain. The extent of this uncertainty needs to be identified as objectively as possible during decision-making. Engineers and financial analysts in particular are prone to giving single, deterministic values for information that is really a distribution. Push back on them to find the distribution, even if it is in terms like "very sure", "about" or "sort-of". Early in the development of a system all estimates are uncertain and need to be managed as such.Information that is highly uncertain needs to be discounted or its uncertainty reduced if-and-only-if it is important (see item 2)


4. Develop Multiple Alternatives: Always consider multiple courses of action that can be itemized. If the choice is to do A or "do nothing", then make an effort to develop alternatives B and C. Develop methods within your organization that encourage creative options.Find ways to help the champions of each idea compare and contrast their alternatives with others.


5. Define a Decision-making Strategy: Make sure there is an agreed to decision-making strategy. Decision-making by stirring and restirring existing information is not beneficial.


6. Build collaboration: Collaboration means that all stakeholders' opinions are heard during deliberation. Then, even those whose first choice is not chosen will more likely buy in to the outcome. This also gives the whole team a sense of accountability for the final decision.


7. Be Aware of Diminishing Analytical Returns: Analysis is expensive and is likely to postpone resolution. Over-analysis is the risk-averse activity of trying to drive out all uncertainty. When the fidelity of simulation is greater than the uncertainty of the information on which the simulation is based, time and money are being wasted.


8. Reuse History: Work toward learning from past decisions. Evaluating your success requires keeping track of past choices; the actions as well as the results.


9. Find a Platform to manage and fuse uncertain team evaluations: Use proven methods and tools that help your organization reduce risk and avoid deliberative quagmires.

A Justification is Not a Decision

There are two kinds of decision-making: justification and selection. Justification occurs when the result is a foregone conclusion — the choice is made in advance of any argument or consideration. This often happens when the boss already has his favorite option in mind and wants information to "prove" that it is the right choice. I have seen this during my career in product design and the nation saw it in President Bush's decisions about Iraq. In Maureen Dowd's NY times Op-Ed on June 1 2008, "Cult of Deception" she says that "our president is a one-man refutation of Malcolm Gladwell's best seller Blink, about the value of trusting your gut."

In an earlier blog, I discussed Blink and how trusting your gut can be the wrong approach for complex decisions, because you can't include sufficient information or study alternative courses of action. However, managers that get that warm fuzzy feeling when they know the best course of action, before they have sufficient information, can be dangerous. Of course, they may be right. If they usually are, then they clearly have sufficient information and a good decision making style. But if these justifications often end up with later fire-fighting, then justification is not working in lieu of decision-making.

Actually, the CIA has a method that is supposed to short circuit justification-thinking. It is called Analysis of Competing Hypotheses and is in a downloadable book titled "Psychology of Intelligence Analysis." Basically, ACH prescribes the following steps:

1. Identify the possible hypotheses to be considered.
2. List the significant evidence and assumptions for and against each hypothesis.
3. Draw tentative conclusions about the relative likelihood of each hypothesis.
4. Analyze sensitivity of the conclusion to critical items of evidence.
5. Identify future observations that would confirm one of the hypotheses or eliminate others.

This differs some from the process I develop in Making Robust Decisions, but both begin with basic fact that — YOU MUST HAVE ALTERNATIVES TO MAKE A DECISION. I put this in bold because it seems evident that many Washington decision makers don't follow this basic truth. In fact, many business leaders don't follow this either. In the book Why Decisions Fail, Paul Nutt gives three basic blunders. One of these, "Premature Commitments" is the the same as the justifications we are discussing here.

So what do you do to stop this kind of ineffective decision-making. The only thing to do is to set up an environment that forces multiple decisions to be considered. Sometimes this is difficult from below, but if you are a manager, insist on multiple alternatives to consider.

Gut decisions don’t work well in many situations

There has been a recent spate of best-selling books that support the notion that you should go with your gut when making a decision (e.g. Blink: The Power of Thinking Without Thinking by Malcolm Gladwell, Gut Feelings by Gerd Gigerenzer and Gary Klein's The Power of Intuition: How to Use Your Gut Feelings to Make Better Decisions at Work).

The authors of these books state that for many decisions there is no need to formally identify the issue, develop multiple alternatives, and itemize criteria — just go with your intuition. Of course, they are right — for some decisions. We make decisions in two very different ways. Sometimes we reach conclusions unconsciously — our minds quickly and silently sorting through the available information and drawing an immediate judgment. This may be in a blink — so quickly and so far below our level of awareness that we may have no consciousness of where our conclusions came from. If we are trying to decide what to do in an emergency, how to walk through a doorway, or many other simple or no-time-to-think situations then this is the right approach.

One study of decision-making methods (see Payne, Bettman, and Johnson, The Adaptive Decision Maker) found that

1. People use a variety of cognitive strategies, dependent on task and context factors.
2. Given that people have limited cognitive abilities, strategy selection is a compromise between accuracy and the desire to minimize cognitive effort.
3. People are opportunistic; they change their strategies on the fly.

The study indicated that intuition follows a strategy in which we compare the first alternative solution for the situation to the most important criterion. If our evaluation shows that the alternative satisfies that criterion, we accept it and move on. If it doesn’t, we generate another alternative and try again. If there is more than one alternative that satisfies the most important criteria, we move to the next most important criterion to try to zero in on the one to choose. Of course, this strategy may be modified if we are out time, there are too many alternatives, or there are others involved.

Research I did in the early 1990s showed that designers who pursued their first idea generally ended up with concepts that needed much patching to make them work, if they could be fixed at all. Another study of design engineers showed that the quality of design results linearly improved with the time and effort spent on developing alternatives and criteria (this work is in an obscure German dissertation but the results can be read in a paper I wrote "The Ideal Engineering Decision Support System."