MjgotlvOTNa4KLZbzpzW2Q BF C3 W4 Biases and Forecasting

Download as pdf or txt
Download as pdf or txt
You are on page 1of 15

Business Forecasting

Biases and Forecasting


Problems in Judgmental
Forecasting
Although judgmental methods have relative merit in
certain circumstances there are also problems

These problems can lead to biases and hence systematic


inaccuracies in forecasting

Some biases are due to individual judgment and psychology


(eg. Sales Force forecasts)

Others are related to group biases with forecasts derived from


group input/interaction (Jury of Executive Opinion)

In addition political and organisational issues may lead to


systematic biases
Judgmental Biases- Individual
Research indicates that individual’s decision making
processes and judgments (including forecasts) can be
influenced by psychology, personality, physiology, and
circumstance

These factors can influence the accuracy of judgments made by


influencing the selection of relevant information from
available information, the weighting applied to that information
and subsequent forecasts

Two individuals presented with the same available


information may produce widely differing judgmental
forecasts
How good is your Judgment?

Which is the larger inner Circle?


Which line is Longest?
Centred?
Further Judgment Exercise
Please count the number of times the letter F appears in the
following sentence:

FINISHED FILES ARE THE RESULT OF YEARS OF


SCIENTIFIC STUDY
COMBINED WITH THE EXPERIENCE OF YEARS.

FINISHED FILES ARE THE RESULT OF YEARS OF


SCIENTIFIC STUDY
COMBINED WITH THE EXPERIENCE OF YEARS.
Judgmental Biases-
Individual
Further issues arise because of inconsistency in decision making
for a given individual over many almost identical decision
situations

People are often unable or unwilling to apply the same


criteria or procedures when making similar decisions

Inconsistency may be due to forgetfulness, mood, boredom,


novelty-seeking, or belief conditions have changed when
they haven’t

Research indicates a given individual can make widely varying


decisions using almost identical information depending on
circumstances
Other Problems and Biases
Recency – remembering recent events more vividly, which
consequently influences our judgement more greatly than less
recent events

Beliefs about Information:

1. Belief that the more information we have, the more


accurate our decision will be. Empirical evidence does not
support such a belief. More information increases our confidence
that we are right without necessarily improving accuracy

2. Belief that we can discriminate between useful and


irrelevant information. Empirical evidence indicates that is
rarely the case.
Interpretation of Information
Given the inability to discriminate between useful and irrelevant
information, often irrelevant information is used in
making decisions. This decreases decision-making
accuracy

Most people seem to weight ‘verbal’ information more


heavily than numbers or statistical information and tend to
include qualitative information (that is often irrelevant) in
preference to quantitative information (that is often relevant)

Our system of learning is biased towards analysis of verbal,


oral and aural cues and against mathematical and other
objective information
Consider this Exercise
Linda is 31 years old, single, outspoken and very bright. She
majored in philosophy. As a student, she was deeply
concerned with issues of discrimination and social justice,
and also participated in antinuclear demonstrations.

Which of these two alternatives is more probable?

(a)Linda is a bank teller

(b) Linda is a bank teller and active in the feminist


movement
Which alternative would you choose?
Conjunction Fallacy

Assume you chose (b), just as most subjects - 80% to 90% - in


previous experiments did

Tversky and Kahneman (1983) argue: (b) is the conjunction of


two facts, namely that Linda is a bank teller and is active in the
feminist movement, whereas (a) is one of the conjuncts

Since the probability of a conjunction cannot be greater


than that of one of its conjuncts, the correct answer is (a), not
(b).

Therefore, your judgment is recorded as an instance of a


celebrated reasoning error, known as the conjunction fallacy
Judgmental Biases - Group
Evidence suggests that group decision making amplifies biases
because of organisational issues, politics, personality,
psychology and circumstances

Typically, responsibility for the decisions taken cannot be


attributed to any single individual possibly influencing
accountability and decision making input and process

Herding behaviour and group-think are particular problems


that may bias decisions

Issues of power and conflict are possibly relevant


Group-think
Group-think is a concept which suggests that individuals will
behave and react differently to stimulii if in a group
situation

Decision processes within groups may bias judgments leading


to inaccuracy of decisions and forecasts

Group-think may be a political phenomenon or a reflection of


personality of team members

Group-think is exacerbated when there is high group


cohesiveness and insulation

Also exacerbated if there is dominant leadership and


power/conflict issues within the group.
Accuracy Of Judgmental
Forecasts – Financial Markets
Financial Markets - Graham and Harvey (1995)
Only 22.8% of investment newsletters have average returns
higher than a passive portfolio of equity and cash with the
same volatility

Poor performance more persistent than good performance

Found no evidence investment letters have any knowledge


over and above common levels of predictability. Very few
investment letters can ‘beat’ S&P 500.

Few can beat the market forecast derived from a statistical


representation of publicly available information

There is no evidence that the letters can time the market


(forecast direction of the market) Investment letter
‘winners’ rarely win again and ‘losers’ often again
Forecast “Gurus”
Some investment gurus have outperformed the market but
they represent a tiny exception to the rule;

Past above-average performance does not indicate such


performance will continue in the future

All evidence points to the one conclusion;

All markets where information is widely disseminated and that


cannot be influenced by a few players makes it impossible to
predict them accurately other than by using today’s price
as the best possible forecast (naïve)

You might also like