Posts Tagged ‘Prediction’

On the shelf in front of you are two jars of strawberry jam; the label on one of them carries the name of a well-known and popular brand of food, on the other jar appears an unfamiliar name. At the same price, which one do you choose to buy? The majority of consumers are likely to go for the well-known brand. It is a fast and easy-to-use heuristic — choose the product of the familiar brand name as it predicts the product is more likely to be of high quality. This fast-and-frugal decision rule is most useful when a consumer is not familiar with any of the jams from personal experience.

However, well-known brand names can affect preferences even when consumers do have experience with both products, and the products are in fact identical. This is a key theme surrounding blind tests of taste. For example, subjects in an experiment were given peanut butter to taste from three jars. The same peanut butter was put in all jars, yet one jar carried a familiar brand name whereas the other two were displayed with “no-name” labels. After tasting, 75% chose the branded jar for tasting better than the peanut butter in the two other jars (chosen by 17% and 8% of subjects). The power of recognized brand names is even more striking when mixing the labels between higher quality and lower quality peanut butter products: 73% chose the jar carrying a name-brand even though it contained the lower quality product (experiments conducted by Hoyer and Brown, 1990, cited by Gigerenzer, 2007). Familiar brand names may create a bias in their favour (“brand names taste better” as put by Gigerenzer). Researchers aim to remove the bias when testing how the taste of food products is perceived, but this potential bias should not be ignored when predicting consumer choice. Nonetheless, at time of choice, relying on the recognized name can aid consumers make correct choices more often under uncertainty at relatively little effort.

Take another example of the practicality of heuristics from a different field (criminology): the problem at hand is to find where a serial criminal might be located based on information on sites of his or her suspected crimes, a problem known as “geographic profiling”. The common approach is to apply sophisticated statistical models that calculate the probabilities of locations that are spatially distributed. In comparison, researchers Snook, Taylor and Bennell (2004, cited by Gigerenzer and Gaissmaier, 2011) tested a more economic “circle heuristic”: the criminal would be located at the centre of a circle drawn through the two most distant sites of crime; this heuristic performed better than ten alternative statistical profiling strategies in predicting the locations of criminals. Gigerenzer and Gaissmaier give this heuristic as an example for one-reason decision-making: the strategy employs a single and rather simple informative cue as its guide yet can perform better than more complex information-rich strategies.

Gerd Gigerenzer, a professor of psychology and Director of the Centre for Adaptive Behaviour and Cognition at the Max Planck Institute for Human Development in Berlin, commends a more positive approach towards heuristics and their role in decision-making than the critical view that has been accepted in psychology since the 1970s. A seminal paper published by Gigerenzer together with Wolfgang Gaissmaier (2011) is illuminating and instructive. In their article the authors work towards establishing a comprehensive theory of heuristics, and especially describe methods that need to be applied to properly define their strategies, specify the information they utilise, and assess their performance.

  • A heuristic is defined concisely by Gigerenzer and Gaismmaier as “a strategy that ignores part of the information, with the goal of making decisions more quickly, frugally, and/or accurately than more complex methods” (p. 454).  The function of a heuristic can fundamentally be specified by three building blocks: search rules, stop rules, and decision rules.

Gigerenzer disagrees with the paradigm in psychology on decision-making, led by Kahneman and Tversky and their colleagues. that associates heuristics with human error and biases. The paradigm is concerned with mistakes people make in processing information and drawing inferences (e.g., because of memory and cognitive limitations). Heuristics are used as a way of simplifying complex decision problems but are marred by inaccuracies and biases that result in sub-optimized  decisions or irrational decision-making. Gigerenzer and Gaissmaier assert that heuristics are not “irrational” and show that they do not necessarily “cost” the decision-maker in incorrect or less accurate outcomes.

Gigerenzer has had further reservations about the interpretation of “bounded rationality”, conceived by Herbert Simon, as the source of such biases or fallacies in human decision-making; Gigerenzer and Selten (2001) argue that bounded rationality is not identified with the class of error and fallacies in judgement and decision-making often demonstrated empirically in experiments in psychology and behavioural economics. In their view, bounded rationality is not about the discrepancy between human reasoning and laws of probability and optimization, looking instead for alternative norms to direct human decisions and studying the actual behaviour of “minds and institutions”.

On similar grounds, Gigerenzer and Gaissmaier (2011) take a critical stand towards the trade-off between accuracy of different decision rules or strategies and the effort in employing them, formally defined and extensively studied by Payne, Bettman, and Johnson. In the important framework of adaptive behaviour of decision makers, the researchers share concepts on rules and strategies as decision tools that people select from their “toolbox” (mostly subconsciously)  to fit the characteristics of each decision problem. Gigerenzer and Gaissmaier question, however, the implication that people use heuristics as imperfect tools to save time and effort but inherently sacrifice in less accurate or sub-optimal outcomes. The critique seems to target the type and variety of rules considered in analysing the accuracy-effort trade-off. They are more favourably oriented towards the alternative view of ecological rationality which converges more closely with bounded rationality, that is, how well a behaviour (e.g., using a heuristic) is adapted to fit the structure of the environment.

Gigerenzer champions the principle that “less-can-be-more”. It challenges the common rational and logical belief that methods and models using more information (as predictors) inherently lead to more accurate predictions. In environments with much uncertainty, when using more information, and applying it in complex calculations, it does not necessarily lead the decision maker to better results. Research on formalised  heuristics and alternative statistical models has often revealled “less-is-more” effects: “There is an inverse-U-shaped relation between level of accuracy and amount of information, computation, or time” (Gigerenzer and Gaissmaier, 2011, p. 453). It means that at some point adding more of those resources stops improving our performance and furthermore harms it. Hence, there are cases where a decision based on one reason (such as the “circle heuristic”) can be a sufficient and even a more advantageous method to achieving our goals.

Let us return briefly to the example on top of consumer choice of familiar brands. In the case that one of two alternatives (e.g., strawberry jams) is recognized and the other is not, a Recognition heuristic can be applied. The formal heuristic states: infer that the recognized alternative has the higher value with respect to the criterion (cf. Gigerenzer and Gaissmaier, 2011). The criterion, as suggested earlier, may be overall quality or taste. The efficacy of the heuristic has been demonstrated in quiz-like experiments. In one of such experiments, for example, participants were given pairs of cities in Switzerland and were asked for each pair which city had the larger population — the recognition heuristic succeeded in inferring the larger city in 89% of pairs (the rule is less accurate in inferring distance from the country’s centre, just 54%). However, one can benefit from the recognition heuristic only when he or she is ignorant in part, that is, one is familiar with just some of the objects and not others (i.e., when asking non-Swiss residents about Swiss cities).

  • Apparently, a study on tennis plays in Wimbledon 2004 has shown that amateur players, for whom the recognition heuristic is more applicable than for tennis professionals, were more successful in choosing the winner of plays in the tournament (72%) than the professionals or tennis experts (66%-69%).

When one is able to recognize both alternative objects in a pair, he or she can apply a Fluency heuristic which instructs to infer that the alternative recognized faster has the higher value with respect to the criterion. When we need to trust our own recall ability in generating alternatives, a third heuristic is specified by Gigerenzer and Gaissmaier, Take-the-First heuristic: choose the first alternative that comes to mind.

In his book on intuition and gut feelings published a few years back, Gigerenzer (2007) explains and demonstrates in an eloquent manner and a friendly style why and how heuristics work to our benefit. It is less formal and scientific-laden than academic articles yet is thus accessible to a wider audience of readers. The theory on intuition, unconscious cognition and heuristics is delivered in a way that is comprehensible and interesting, supported by many examples such as illustrations of the rules and in related research findings.

The heuristics identified by Gigerenzer and his colleagues are not meant to be newly invented — they may actually seem familiar to many people in one form or another. The significance of the contribution is in collating those heuristics from different fields of life, classifying and formally describing them according to systemic criteria, putting them into context of a theory of heuristics. This step is also important for analysing and evaluating their performance against more complex “rational” models.

Ron Ventura, Ph.D. (Marketing)


Gerd Gigerenzer, 2007, Gut Feelings: The Intelligence of the Unconscious, London: Penguin Books

Gerd Gigerenzer and Wolfgang Gaissmaier, 2011, Heuristic Decision Making, Annual Review of Psychology, Vol. 62, pp. 451-482.

Gerd Gigerenzer and Reinhard Selten, 2001, Rethinking Rationality, in Bounded Rationality: The Adaptive Toolbox, G. Gigerenzer and R. Selten (editors), Cambridge, MA; London, UK: MIT Press


Read Full Post »

Competition in health-related industries (i.e., health care services, pharmaceutical, biotechnology) has been increasing continuously in the past two to three decades. The health business has also become more complex and multilayered with public and private institutions, individual doctors and patients, as players. Consequently, decision processes on medical treatment may become more complicated or variable, being more difficult to predict which treatment or medication will be administered to patients. For example:

  • For many medical conditions there are likely to exist a few alternative brands or versions of the same type of prescribed medication. Depending on the health systems in different countries, and on additional situational factors, it may be decided by a physician, a health care provider and/or insurer, or a pharmacist what particular brand of medication a patient would use. In some cases the patient may be allowed to choose between a more expensive brand and an economic brand (e.g., original and generic brands, subsidised and non-subsidised brands).
  •  There are plenty of over-the-counter (OTC) medications, formulae and devices that patients can buy at their own discretion, possibly with a recommendation of a physician or pharmacist.
  • Public and private medical centers and clinics offer various clinical tests and treatments (e.g., prostate screening, MRI scanning, [virtual] colonoscopy), often going above the heads of general/family physicians of the concerned patients.
  • In more complex or serious conditions, a patient may choose between having a surgery at a public hospital or at a private hospital, depending on the coverage of his or her health insurance.

In the late 1990s, professionals, executives and researchers in health-related areas have developed an interest in methods for measuring preferences that would allow them to better understand how decisions are made by their prospect customers, especially doctors and patients (“end-consumers”). This knowledge serves (a) to address more closely the preferences of patients or requirements of physicians, and (b) to channel planning, product development or marketing efforts more effectively. In particular, they have become interested in methods of conjoint analysis and choice-based conjoint that have already been prevalent in marketing research for measuring and analysing preferences. Conjoint methods are based on two key principles: (a) making trade-offs between decision criteria, and (b) decomposition of stated preferences with respect to whole product concepts (e.g., a medication) by means of statistical techniques into utility values for levels of each attribute or criterion describing the product (e.g., administering 2 vs. 4 times in 24 hours). The methods differ, some argue quite distinctly, in terms of the form in which preferences are expressed (i.e., ranking or rating versus choice) and in the statistical models applied (e.g., choice-based conjoint is often identified by its application of discrete choice modelling). An important benefit for pharmaceutical companies, for example, is gained in learning what characteristics of a medication (e.g., anti-depressant) contribute more to convincing physicians to prescribe it, versus factors like risks or side-effects that lead them to avoid a medication.

The product concepts presented are hypothetical in the sense that they are specified by using controlled experimental techniques and do not necessarily match existing products at the time of study. This property is essential for deriving utility values for the various levels of product attributes studied, and to allow prediction by simulation of shares of preference (“market shares”) for future products. The forecasting power of conjoint models is considered their major appeal from a managerial perspective. In addition, conjoint data can be used for segmenting patients and designing refined targeted marketing strategies.

Interest in application of conjoint methods in a health context has grown in the past decade. According to a review research of conjoint studies reported in 79 articles published between 2005 and 2008, the number of studies nearly doubled from 16 in 2005 to 29 in 2007. The researchers estimated that by the end of 2008 the number of published studies would reach 40. The most frequent areas of application have been cancer (15%) and respiratory disorder (12%)(1). However, applications of conjoint techniques can be found also for guiding policy making and the design of health plans in a broader context of health-care services provided to patients (e.g., by HMOs).

Most conjoint studies in health (71%) apply choice experiments and modelling, becoming the dominant approach (close to 80%) particularly in 2008. A typical study includes 5 or 6 attributes with 2 or 3 levels for each attribute. Most studies in a choice-based approach involve 7 to 8 scenarios (choice sets) but studies with 10-11 or 14-15 scenarios are also frequent (2). A choice scenario normally includes 3 to 5 concepts from which a respondent has to choose a single most prefered concept.

Interpretation of conjoint studies among medical doctors needs a special qualification to be distinguished from studies of patients or consumers. That is because the physicians make professional judgements about the most appropriate treatment option for their patients.  Therefore, it is less appropriate to relate to personal preferences in this context. It is more sensible and suitable to talk about decision criteria that physicians apply, their priorities (i.e., represented by importance weights), and requirements of physicians from pharmaceutical or other treatment alternatives available in the market.

Including monetary cost in conjoint studies on products and services in health-care may be subject to several complications and limitations. That may be the reason for the relatively low proportion of articles on conjoint studies in health that were found to include prices (40%)  (3). For instance, doctors do not take money out of their own pockets to pay for the medications they prescribe, so it is generally less relevant to include price in their studies. It may be sensible, however, to include cost in cases where doctors are allowed to purchase and hold a readily available  inventory of medications for their visiting patients in their private clinics (e.g., Switzerland). It may still be useful to examine how sensitive doctors are to the cost of medication that their patients will have to incur when prescribing them. However, this practice may be additionally complicated because the actual price patients pay for a specific medication is likely to change according to the coverage of their health plan or insurance. It is appropriate and recommended to include price in studies on OTC medications or health-related devices (e.g., for measuring blood pressure). Aspects of cost can be included in studies on health plans such as the percentage of discounts provided on medications and other types of clinical tests and treatments in the plan’s coverage.

An Example for a Conjoint Study on Health-Care Plans:

A choice-based conjoint study was conducted to help a health-care coverage provider assess the potential for a new modified heath plan it was considering to launch. Researchers Gates, McDaniel and Braunsberger (4)  designed a study with 11 attributes including provider names (the client and two competitors), network of physicians accessible, payment per doctor visit, prescription coverage, doctor quality, hospital choice, monthly premium, and additional attributes. Each respondent was introduced to 10 choice sets where in each set he or she had to choose one out of four plans. This setting was elected so that in subsequent simulations the researchers could more accurately test scenarios with existing plans of the three providers plus a new plan by the client-provider. The study was conducted among residents in a specific US region by mail. Yet beforehand a qualitative study (focus group discussions) and a telephone survey have been carried out to define, screen and refine the set of attributes to be included in the conjoint study. 506 health-care patients returned the mail questionnaire (71% response rate out of those in the phone survey who agreed to participate in the next phase).

The estimated (aggregate) utility function suggested to the researchers that the attributes could be divided into two classes of importance: primary criteria for choosing a health plan and secondary considerations. The primary criteria focused on access allowed to doctors in the region of residence and cost associated with the plan, representing the more immediate concerns to target consumers in the market in choosing a health-care plan by a HMO. It was mainly confirmed in the study that consumers are less concerned by narrowing the network of doctors they may visit, as long as they can keep their current family physician and are not forced to replace him or her with another on the list. Respondents appeared to rely less on reported quality ratings of doctors and hospitals. Vision tests and dental coverage were among the secondary considerations. Managers could thereby examine candidate modifications to their health plan and estimate their impact on market shares.

The conjoint methods offer professionals and managers in health-related organizations research tools for gaining valuable insights into patient preferences or criteria governing the clinical decisions of doctors on medications and other treatments. These methods can be particularly helpful in guiding the development of pharmaceutical products or instruments for performing clinical tests and treatments when issues of marketing and promoting them to decision makers come into play. As illustrated in the example, findings from conjoint studies can be useful in policy making on health-care services and designing attractive health plans to patients. This kind of research-based knowledge is acknowledged more widely as a key to success in the highly competitive environs of health-care.

Ron Ventura, Ph.D. (Marketing)


(1)  Conjoint Analysis Applications in Health – How Are Studies Being Designed and Reported? An Update of Current Practice in the Published Literature Between 2005 and 2008, D. Marshall, J.F.P. Bridges, B. Hauber, R. Cameron, L. Donnalley, K. Fyie, and F.R. Johnson, 2010, The Patient: Patient-Centered Outcomes Research, 3 (4), 249-256

(2) Ibid. 1.

(3) Ibid. 1.

(4) Modeling Consumer Health Plan Choice Behavior to Improve Customer Value and Health Plan Market Share, Roger Gates, Carl McDaniel, and Karin Braunsberger, 2000, Journal of Business Research, 48, pp. 247-257 (The research was executed by DSS Research to which Gates is affiliated).

Additional sources:

A special report on conducting conjoint studies in health was prpared in 2011 by a task force of the International Society for Pharmaeconomics and Outcomes Research. The authors provide methodological recommendations for guiding the planning, design, and analysis and reporting conjoint studies in health-related domains.

Conjoint Analysis Applications in Health – A Checklist: A Report of the ISPOR Good Research Practices for Conjoint Analysis Task Force, John F.P. Bridges, and A. Brett Hauber et al., 2011, Value in Health, 14, pp. 403-413


Read Full Post »

On Friday evening of 13th January the cruise ship Costa Concordia smashed against the rocks of Isola Giglio in Italian waters, tilted to its side and capsized. Suspicions were soon raised rather unexpectedly blaming this tragic accident on grave misconduct of the captain of the ship. The recording of conversations between the officer of the Italian Coast Guard and  captain Francesco Schettino, fleeing from the ship, are most disturbing. Allegations running against the captain are highly discomforting, ranging from negligence, poor judgement, and to outright disregard for the lives of his passengers and crew.

The Costa Concordia carried about 3,200 passengers and a thousand (1,000) crew members. Seventeen (17) victims who lost their lives are confirmed at the time of writing this post, and there are still 15 people missing. Fortunately enough, since the massive cruise ship landed in a spot where water is not so deep, the ship did not sink completely and the vast majority of people on board could escape by swimming or be evacuated safely to the shores of Toscana. Giving full tribute to Concordia’s victims, we should be thankful that this disaster did not end worse and that so many of the people on board are survivors.

The cruise ship belonged to the company Costa Cruises, an Italian subsidiary of British-American Carnival Corporation.  It was built together with six ship-sisters in the previous decade in the same shipyard in Italy. Concordia, inaugurated in 2006, was the largest and most glamorous of them all. It was Costa’s flag-ship, literally.  At first the company faced fears that the cause of accident could be a technical or physical failure of some sort. This would mean that all sisters of Concordia would have to be grounded. If the failure could not be repaired, it was speculated, financial losses would be immense. Seniors at the company may be relieved now that this is not the case, but instead they will have to bear the shame and embarrassment from the alleged behaviour of their ship captain and the public anger targeted against them, with all their potential negative consequences.

According to a statement issued by the company on 15th January and posted on their website (1), Schettino joined Costa Cruises in 2002 as a safety officer and was appointed captain in 2006. It is not yet clear what has led captain Schettino to manoeuver the ship so irresponsibly: was it to impress one of his officers, to “show-off” to a female friend, or just being negligent? However, it is already difficult to comprehend the captain’s behaviour after the accident had occurred. Apparently the captain understood he has done wrong and became more concerned about not being caught by the Italian authorities than helping in safeguarding the lives of his passengers and crew. Another account by an officer on bridge suggests Schettino was merely panicking (2). Most bizarre are the excuses ‘il capitano’ has given the Coast Guard’s officer about his whereabouts, suggesting for instance that he “fell off” from the ship’s deck and right into a lifeboat below the ship. According to the transcript of the conversation, it is implied that at some point he was actually already some distance away from the ship nearing the coast and was ordered to return to the site of accident. This conduct of Schettino after the accident may have an even stronger negative impact on travelers’ attitudes than his conduct leading to the accident.

There is an aspect in the chain of events on the night of the accident that passengers were not prepared for; while many passengers were probably not aware of the behaviour of the captain in a situation that was hard already for them, this was revealled soon in the aftermath of the accident. Thereby it created much rage among passengers and the public. Let us look more closely at this aspect.

People tend to underestimate the probability of negative events like fires or fatal car accidents that might occur to them. When going on a cruise, passengers may take into consideration that the ship could be caught in a gusty storm or strike a rock but they try to weigh down these scenarios. But just in case, most travellers take a travel insurance. This human approach generally allows us to take actions like going on vacation without worrying too much about negative contingencies. However, tourists who are over-confident in their skills (e.g., swimming, skiing) or their judgement (i.e., assessing certain events so unlikely that they can be ignored, strongly holding a belief that “it will not happen to me”), they are susceptible of behaving recklessly or foolishly, and they may also choose not to take a travel insurance.

Yet, passengers of the Costa Concordia have found out that someting happened on the night of accident that their usual mechanisms of self-protection could not help them in this case — a breach of trust by the captain responsible for their safety in sea. The alleged role of the captain in causing the accident by acting unprofessionally and with disrespect to his usual duties as captain of a cruise ship means that this accident was completely avoidable. It is hardly conceivable by passengers that the captain will be directly involved in causing an accident on a ship of the scale of Concordia. Primarily, the conduct of captain Schettino abandoning the ship, leaving behind his passengers and crew, stands against the norm and commonplace belief that the captain always stays last on board to orchestrate rescue operations even at the risk of his own life, as famously did Edward John Smith, of the Titanic in 1912.

The Greater the Unpleasant Surprise, the Stronger Negative Impact on Travellers Expected

The surprise evoked by the circumstances surrounding the accident, shaking-up of strong beliefs about the responsibility of the captain and his senior officers for the well-being of passengers, and the eventual breach of trust are the kind of factors likely to have a specially strong effect on travelers’ attitudes and behaviour. Tourists are likely to feel more vulnerable. They will start questioning the confidence they have put in this cruising company and its senior officers, which may easily spill to other cruisers. The stressing situation may further evoke emotions of frustration and anger. It is difficult to predict for how long these negative effects will prevail but they can very well hurt the tourist industry, particularly in leisure cruises, for the next couple of years.

Was it actually a freak incident in the behaviour of Schettino? Was his conduct on this occasion in complete contradiction to his previous behaviour as captain that the company’s management could not suspect him to fail so badly in his last cruise? These are heavy-weight questions that investigators of the accident will probably address. It is yet pre-mature to doubt the decision of Costa Cruises to hire him in the first place or appoint him to be captain. It also is too easy to find signs of misconduct in hindsight (e.g., “the captain was partying”), because “early signs” receive greater attention, appearing more obvious after the event. Nevertheless, investigators will have to enquire if there were any signs ignored by Schettino’s superiors which should have increased their scrutiny regarding his performance as captain. Prosecuters in Italy intend to charge captain Schettino with multiple manslaughter, causing a shipwreck, and abandoning the ship before all passengers and crew evacuated (2).

The Costa Cruises company (and the mother-company Carnival Corp.) already has to bear the loss of its ship Costa Concordia, and in the short to mid-term it can expect to face multiple law suits and pay compensation to passengers and their families and cover the cost of removing the ship wreck from water. Last Friday (30th January) the company reached an agreement with a coalition of consumer groups that it will pay €11,000 to each passenger on top of refund for the cruise cost, medical and transportation expenses (3); but nothing is final as some passenger groups already express discontent. Furthermore, concerns have been raised of environmental damages to the sea and coast that the company will have to help and fix or compensate Italy for them. After that, the company is likely to face economic losses in the mid- to long-term because of tourists’ reluctance to travel with them again. Costa Cruises is going to remember captain Schettino for a very long time.

Italians are also going to remember their native Schettino for many years as an infamous captain. It looks like the last thing Italy needed at this time. He has potentially caused a blast to their tourist industry when their economy needs mostly a boost. The Italians have every reason to be angry with him. Most surely, he will not be forgiven for a very long time for embarrassing Italy so badly.

Ron Ventura, Ph.D. (Marketing)


(1) Statements issued by Costa Cruises associated with the Concordia’s accident: http://www.costacruise.com/B2C/USA/Info/concordia_statement.htm

(2) “Costa Concordia Captain ‘Distracted by Guests on Bridge’,” The Guardian Online, 23 January 2012  http://www.guardian.co.uk/world/2012/jan/23/costa-concordia-captain-distracted-guests

(3) “Costa Concordia Company Offers Passengers Compensation,” BBC News Online, 29 January 2012.   http://www.bbc.co.uk/news/world-europe-16754771

Read Full Post »