Business Forecasting Topic 11 Flashcards

1
Q

forecasts involve judgment in what ways

A
  1. choice of method
  2. how much past data
  3. which variables to include

direct (widely used) - wholly based on judgment or judgmental adjustments to statistical

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

benefits of management judgment to forecasts:

A
  1. account special events (strike, gov initiative)
  2. compensate for deficiencies/absence of historical data
  3. allow managers to have control over variables
  4. acceptable forecasts - managers = sense of ownership
    (complex stats method = lack transparency and credibility)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

problems of judgment related to humans

A
  • limited info processing capacity
  • simple mental strategies = cope with complexities
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Heuristics

A

are simple strategies that humans, animals, organizations, and even machines use to quickly form judgments,

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

3 types of heuristics

A
  1. availability
  2. anchoring and adjustment
  3. representatives
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

availability

A
  • likelihood of future events -> how easily similar past events are recalled
  • over influenced by recent/vivid/events in press

fear e.g. violent crime more than obesity, terrorism more than smoking or food poisoning

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

anchoring and adjustment

A
  • making estimate, start with initial value and adjust from this
  • estimates tend to be close to anchor even if implausible value
  • underestimate upward trends (severe for exponential trends) - stay close to. most recent values
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Representativeness

A

extrapolating time series = expect future pattern to be representative of past pattern

  • try reproduce perceived past pattern in forecasts - much of this past pattern is noise
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

narrative fallacy

A

expert in investing explanations for these random movements

  • many movements in sales = random = people brilliant at inventing explanations
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

5 problems with judgment

A
  1. hindsight bias -> wrongly think could have easily predicted - knew it all along
  2. overconfidence -> better forecasts than really are despite messages from computer
  3. political biases - dishonesty to please boss, Sandbagging - deliberately low
  4. optimism bias - calculated
  5. group biases - conformity
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

6 ways of making the best use of judgment

A
  1. Delphi method
  2. decomposing
  3. feedback
  4. adjusting if appropriate
  5. record reasons
  6. combine judgment with statistical
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Delphi method

A
  • avoid danger of face to face with groups
  1. individual and anonymous forecasts & reasons
  2. results tallied and summarised
  3. re-polling
  4. repeated until consensus emerges - median estimate = used as forecast
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

adv and dis of Delphi

A

adv: large/geographic groups, no dominance, change minds

dis: little chance of persuasion, choosing panel members (experts = over analyse/not open minded)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

decomposition

A

make judgmental tasks easier through breaking down to smaller easier tasks

adjustments -> price reduction, promotion, new customer

only if this is practical

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

feedback on performance

A

MAPE or MPE

on bias - more useful than feedback on accuracy

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

adjusting statistical forecasts

A

only when appropriate -> important extra info on forthcoming events

  • only effective when forecaster has important information (not available to statistical forecast)
  • unnecessary (small) adjustments = reduce forecast accuracy and waste time
17
Q

record reasons for adjustments

A
  • reduces gratuitous adjustments
  • others understand forecast basis
  • reduces possibility of political biases
18
Q

comparing judgmental and statistical

A

statistical = superior in finding patterns and relationships in data

human judgment = subject to number of biases -> best only when no past data or special events known to be forthcoming