Decision Tree - Revision history

Tkokotas at 13:07, 23 November 2018

2018-11-23T13:07:14Z

← Older revision		Revision as of 13:07, 23 November 2018
Line 184:		Line 184:
	:'''3.Faber, Michael Havbro (2010) Statistics and Probability Theory - In Pursuit of Engineering Decision Support, Publisher: Springer International Publishing AG		:'''3.Faber, Michael Havbro (2010) Statistics and Probability Theory - In Pursuit of Engineering Decision Support, Publisher: Springer International Publishing AG
	::<u>Summary:</u> This book aims in presenting statistics and probability theory in the context of supporting engineering decision making. The book focuses on the use of the theory for the purpose of engineering model construction, decision making and risk analysis.		::<u>Summary:</u> This book aims in presenting statistics and probability theory in the context of supporting engineering decision making. The book focuses on the use of the theory for the purpose of engineering model construction, decision making and risk analysis.

			[[Category:Project Management]][[Category:Uncertaity]][[Category:Risk]][[Category:Decision Making]]

Tkokotas at 18:45, 17 November 2018

2018-11-17T18:45:15Z

← Older revision		Revision as of 18:45, 17 November 2018
Line 1:		Line 1:
			''Developed by Apostolos Bougas''


	[[File:Complex_decision_tree_1.PNG\|thumb\|right\|300px\|Figure 1: Complex decision Tree]]		[[File:Complex_decision_tree_1.PNG\|thumb\|right\|300px\|Figure 1: Complex decision Tree]]
	<span class="plainlinks">[https://en.wikipedia.org/wiki/Decision_tree '''Decision Tree''']</span> is one of most used and widely recognized decision-making tools in project, program and portfolio management. Its simple structure, along with its clarity and simplicity in application offers to decision makers a powerful tool. Through decisions tree analysis, decisions under uncertainty can be evaluated and, therefore, further actions, in organizations, can be planned. Except its use in project management and risk analysis, decisions trees are also used in data mining and statistical analysis. In this article decision tree as a project management tool is presented. This article analyzes, at first, some important introductory definitions, that someone must be aware to fully understand its concept. Then, the purpose, structure and construction of decision trees is analyzed, with simple examples of decision tree analysis and decision-making. Finally, decision tree has some challenges, that the decision makers and project managers should be aware of and try to overcome for accurate planning and action, so that organizations can head into prosperity. These challenges, which the project managers have to consider, are discussed in the last section of this wiki article. The decision tree is a powerful technique for describing, understaning and analyzing uncertainty, as the project managers can distinguish between different scenarios and decisions, controlling events that may or may not happen.		<span class="plainlinks">[https://en.wikipedia.org/wiki/Decision_tree '''Decision Tree''']</span> is one of most used and widely recognized decision-making tools in project, program and portfolio management. Its simple structure, along with its clarity and simplicity in application offers to decision makers a powerful tool. Through decisions tree analysis, decisions under uncertainty can be evaluated and, therefore, further actions, in organizations, can be planned. Except its use in project management and risk analysis, decisions trees are also used in data mining and statistical analysis. In this article decision tree as a project management tool is presented. This article analyzes, at first, some important introductory definitions, that someone must be aware to fully understand its concept. Then, the purpose, structure and construction of decision trees is analyzed, with simple examples of decision tree analysis and decision-making. Finally, decision tree has some challenges, that the decision makers and project managers should be aware of and try to overcome for accurate planning and action, so that organizations can head into prosperity. These challenges, which the project managers have to consider, are discussed in the last section of this wiki article. The decision tree is a powerful technique for describing, understaning and analyzing uncertainty, as the project managers can distinguish between different scenarios and decisions, controlling events that may or may not happen.

S162469: /* Annotated bibliography */

2017-10-02T21:00:10Z

Annotated bibliography

← Older revision		Revision as of 21:00, 2 October 2017
Line 174:		Line 174:
	=Annotated bibliography=		=Annotated bibliography=
	:'''1. Kerzner, H., Ph.D., (2006), "Project Management: A systems approach to planning, scheduling and controlling". Ninth edition'''		:'''1. Kerzner, H., Ph.D., (2006), "Project Management: A systems approach to planning, scheduling and controlling". Ninth edition'''
	::<u>Summary:</u> The book illustrates the basic principles of project management. The book is targeting for enhancing the project skills of not only students, but also executives, pointing out that project management can be related to every profession apart from ~~engineeering~~, including information systems and business.		::<u>Summary:</u> The book illustrates the basic principles of project management. The book is targeting for enhancing the project skills of not only students, but also executives, pointing out that project management can be related to every profession apart from engineering, including information systems and business.

	:'''2. Maylor, H. (2010), "Project Management". Fourth Edition'''		:'''2. Maylor, H. (2010), "Project Management". Fourth Edition'''

S162469: /* Construction of decision tree Kerzner, H., Ph.D., (2006), ""Project Management: A systems approach to planning, scheduling and controlling"". Ninth edition Hulett, D. T. & Hillson, D. (2006). Branching out. PM Network, 20(5), 36–40 [URL:http...

2017-10-02T20:51:40Z

/* Construction of decision tree Kerzner, H., Ph.D., (2006), ""Project Management: A systems approach to planning, scheduling and controlling"". Ninth edition Hulett, D. T. & Hillson, D. (2006). Branching out. PM Network, 20(5), 36–40 [URL:http...

← Older revision		Revision as of 20:51, 2 October 2017
Line 74:		Line 74:
	*Cost and benefit estimation of each alternative decision. This is a very important step, as the final decision will depend greatly on the accuracy of this project manager's estimation.		*Cost and benefit estimation of each alternative decision. This is a very important step, as the final decision will depend greatly on the accuracy of this project manager's estimation.
	*Addition of the probabilities of the different states on the branches of the tree. The logic tree is, therefore, transformed into a probability tree. Expertise and experience are required in these steps, with knowledge of probabilistic analysis, as in many cases there is not useful databases for precisely calculation. Calculation of the probabilities in the endpoints. The sum in the probabilities in the endpoints must be equal to one.		*Addition of the probabilities of the different states on the branches of the tree. The logic tree is, therefore, transformed into a probability tree. Expertise and experience are required in these steps, with knowledge of probabilistic analysis, as in many cases there is not useful databases for precisely calculation. Calculation of the probabilities in the endpoints. The sum in the probabilities in the endpoints must be equal to one.
	*Calculation of the expected values on each path. The project manager should take into account all the cash flows in each particular decision and sub-decision over time. Maybe the project manager, in some industries, as the construction industry, should also ~~take into account~~ decisions based on industry uncertainties, such as delays, bad weather conditions e.t.c.		*Calculation of the expected values on each path. The project manager should take into account all the cash flows in each particular decision and sub-decision over time. Maybe the project manager, in some industries, as the construction industry, should also consider decisions based on this particular industry uncertainties, such as delays, bad weather conditions e.t.c.
	*Solution of the decision tree. The project manager computes the expected values or costs, by simply multiplication of the values of the different uncertainties and their probabilities. The expected value of a decision node is the highest value or lowest cost leading from that node.		*Solution of the decision tree. The project manager computes the expected values or costs, by simply multiplication of the values of the different uncertainties and their probabilities. The expected value of a decision node is the highest value or lowest cost leading from that node.

S162469: /* Construction of decision tree Kerzner, H., Ph.D., (2006), ""Project Management: A systems approach to planning, scheduling and controlling"". Ninth edition Hulett, D. T. & Hillson, D. (2006). Branching out. PM Network, 20(5), 36–40 [URL:http...

2017-10-02T20:50:03Z

← Older revision		Revision as of 20:50, 2 October 2017
Line 74:		Line 74:
	*Cost and benefit estimation of each alternative decision. This is a very important step, as the final decision will depend greatly on the accuracy of this project manager's estimation.		*Cost and benefit estimation of each alternative decision. This is a very important step, as the final decision will depend greatly on the accuracy of this project manager's estimation.
	*Addition of the probabilities of the different states on the branches of the tree. The logic tree is, therefore, transformed into a probability tree. Expertise and experience are required in these steps, with knowledge of probabilistic analysis, as in many cases there is not useful databases for precisely calculation. Calculation of the probabilities in the endpoints. The sum in the probabilities in the endpoints must be equal to one.		*Addition of the probabilities of the different states on the branches of the tree. The logic tree is, therefore, transformed into a probability tree. Expertise and experience are required in these steps, with knowledge of probabilistic analysis, as in many cases there is not useful databases for precisely calculation. Calculation of the probabilities in the endpoints. The sum in the probabilities in the endpoints must be equal to one.
	*Calculation of the expected values on each path. The project manager should take into account all the cash flows in each particular decision and sub-decision over time. Maybe the project manager, in some industries, as the ~~constuction~~ industry, should also take into account decisions based on industry uncertainties, such as delays, bad weather conditions e.t.c.		*Calculation of the expected values on each path. The project manager should take into account all the cash flows in each particular decision and sub-decision over time. Maybe the project manager, in some industries, as the construction industry, should also take into account decisions based on industry uncertainties, such as delays, bad weather conditions e.t.c.
	*Solution of the decision tree. The project manager computes the expected values or costs, by simply multiplication of the values of the different uncertainties and their probabilities. The expected value of a decision node is the highest value or lowest cost leading from that node.		*Solution of the decision tree. The project manager computes the expected values or costs, by simply multiplication of the values of the different uncertainties and their probabilities. The expected value of a decision node is the highest value or lowest cost leading from that node.

S162469: /* Risk/Expected Value Faber, Michael Havbro (2010) Statistics and Probability Theory - In Pursuit of Engineering Decision Support, Publisher: Springer International Publishing AG. */

2017-10-02T20:49:39Z

Risk/Expected Value Faber, Michael Havbro (2010) Statistics and Probability Theory - In Pursuit of Engineering Decision Support, Publisher: Springer International Publishing AG.

← Older revision		Revision as of 20:49, 2 October 2017
Line 31:		Line 31:
	<math> EV = \sum_{i=1}^{n} P_i\ C_i </math>		<math> EV = \sum_{i=1}^{n} P_i\ C_i </math>

	It is of utmost ~~importantance~~ to note that the expected cost, expected value or risk does not mean that the organization will earn or lose an amount. Actually, it ~~states that~~ if this decision is repeated many times, then the average cost or gain will probably be this value per time.		It is of utmost importance to note that the expected cost, expected value or risk does not mean that the organization will earn or lose an amount. Actually, it meansthat if this decision is repeated many times, then the average cost or gain will probably be this value per time.

	==Decision Tree==		==Decision Tree==

S162469 at 20:49, 2 October 2017

2017-10-02T20:49:15Z

← Older revision		Revision as of 20:49, 2 October 2017
Line 1:		Line 1:
	[[File:Complex_decision_tree_1.PNG\|thumb\|right\|300px\|Figure 1: Complex decision Tree]]		[[File:Complex_decision_tree_1.PNG\|thumb\|right\|300px\|Figure 1: Complex decision Tree]]
	<span class="plainlinks">[https://en.wikipedia.org/wiki/Decision_tree '''Decision Tree''']</span> is one of most used and widely recognized decision-making tools in project, program and portfolio management. Its simple structure, along with its clarity and simplicity in application offers to decision makers a powerful tool. Through decisions tree analysis, decisions under uncertainty can be evaluated and, therefore, further actions, in organizations, can be planned. Except its use in project management and risk analysis, decisions trees are also used in data mining and statistical analysis. In this article decision tree as a project management tool is presented. This article analyzes, at first, some important introductory definitions, that someone must be aware to fully understand its concept. Then, the purpose, structure and construction of decision trees is analyzed, with simple examples of decision tree analysis and ~~decicion~~-making. Finally, decision tree has some challenges, that the decision makers and project managers should be aware of and try to overcome for accurate planning and action, so that organizations can head into prosperity. These challenges, which the project managers have to consider, are discussed in the last section of this wiki article. The decision tree is a powerful technique for describing, understaning and analyzing uncertainty, as the project managers can distinguish between different scenarios and decisions, controlling events that may or may not happen.		<span class="plainlinks">[https://en.wikipedia.org/wiki/Decision_tree '''Decision Tree''']</span> is one of most used and widely recognized decision-making tools in project, program and portfolio management. Its simple structure, along with its clarity and simplicity in application offers to decision makers a powerful tool. Through decisions tree analysis, decisions under uncertainty can be evaluated and, therefore, further actions, in organizations, can be planned. Except its use in project management and risk analysis, decisions trees are also used in data mining and statistical analysis. In this article decision tree as a project management tool is presented. This article analyzes, at first, some important introductory definitions, that someone must be aware to fully understand its concept. Then, the purpose, structure and construction of decision trees is analyzed, with simple examples of decision tree analysis and decision-making. Finally, decision tree has some challenges, that the decision makers and project managers should be aware of and try to overcome for accurate planning and action, so that organizations can head into prosperity. These challenges, which the project managers have to consider, are discussed in the last section of this wiki article. The decision tree is a powerful technique for describing, understaning and analyzing uncertainty, as the project managers can distinguish between different scenarios and decisions, controlling events that may or may not happen.

	=Introduction=		=Introduction=

S162469: /* Construction of decision tree Kerzner, H., Ph.D., (2006), ""Project Management: A systems approach to planning, scheduling and controlling"". Ninth edition Kerzner, H., Ph.D., (2006), ""Project Management: A systems approach to planning, schedu...

2017-10-02T20:43:32Z

/* Construction of decision tree Kerzner, H., Ph.D., (2006), ""Project Management: A systems approach to planning, scheduling and controlling"". Ninth edition Kerzner, H., Ph.D., (2006), ""Project Management: A systems approach to planning, schedu...

← Older revision		Revision as of 20:43, 2 October 2017
Line 67:		Line 67:
	This ability of the decision tree to follow the natural flow of events, as in many cases, the paths of the decision trees follow the project schedule allows the connection and incorporations with other applications as influence diagrams. Decision trees can be combined with other decision-making techniques such as PERT charts and linear distributions		This ability of the decision tree to follow the natural flow of events, as in many cases, the paths of the decision trees follow the project schedule allows the connection and incorporations with other applications as influence diagrams. Decision trees can be combined with other decision-making techniques such as PERT charts and linear distributions

	===Construction of decision tree <ref name="Kerzner">Kerzner, H., Ph.D., (2006), ""Project Management: A systems approach to planning, scheduling and controlling"". Ninth edition</ref> <ref name="~~Kerzner~~">~~Kerzner~~, H., Ph.D., (~~2006~~), ~~""Project Management~~: ~~A systems approach to planning, scheduling and controlling""~~. ~~Ninth edition~~</ref>===		===Construction of decision tree <ref name="Kerzner">Kerzner, H., Ph.D., (2006), ""Project Management: A systems approach to planning, scheduling and controlling"". Ninth edition</ref> <ref name="PMI "> Hulett, D. T. & Hillson, D. (2006). Branching out. PM Network, 20(5), 36–40 [URL:https://www.pmi.org/learning/library/decision-tree-analysis-implementation-dta-2729]Retrieved on 2 October 2017</ref>===

	For an accurate construction of a decision tree, a project manager needs to conduct the following steps		For an accurate construction of a decision tree, a project manager needs to conduct the following steps
	*Identification of the major possible decisions		*Identification of the major possible decisions and uncertainties
	*Construction of a logic tree, usually from left to right, including the decision and chance nodes		*Construction of a logic tree, usually from left to right, including the decision and chance nodes, stating also its main consequences. By that the project manager considers more carefully the elements that go into a decision.
	*Addition of the probabilities of the different states on the branches of the tree. The logic tree is, therefore, transformed into a probability tree. Calculation of the probabilities in the endpoints. The sum in the probabilities in the endpoints must be equal to one.		*Cost and benefit estimation of each alternative decision. This is a very important step, as the final decision will depend greatly on the accuracy of this project manager's estimation.
	*~~Addition~~ of the ~~conditional outcomes~~. The ~~construction~~ of decision tree is ~~completed~~.		*Addition of the probabilities of the different states on the branches of the tree. The logic tree is, therefore, transformed into a probability tree. Expertise and experience are required in these steps, with knowledge of probabilistic analysis, as in many cases there is not useful databases for precisely calculation. Calculation of the probabilities in the endpoints. The sum in the probabilities in the endpoints must be equal to one.
			*Calculation of the expected values on each path. The project manager should take into account all the cash flows in each particular decision and sub-decision over time. Maybe the project manager, in some industries, as the constuction industry, should also take into account decisions based on industry uncertainties, such as delays, bad weather conditions e.t.c.
			*Solution of the decision tree. The project manager computes the expected values or costs, by simply multiplication of the values of the different uncertainties and their probabilities. The expected value of a decision node is the highest value or lowest cost leading from that node.

	=Decision Tree Analysis=		=Decision Tree Analysis=

S162469: /* Construction of decision tree Kerzner, H., Ph.D., (2006), ""Project Management: A systems approach to planning, scheduling and controlling"". Ninth edition */

2017-10-02T20:25:03Z

Construction of decision tree Kerzner, H., Ph.D., (2006), ""Project Management: A systems approach to planning, scheduling and controlling"". Ninth edition

← Older revision		Revision as of 20:25, 2 October 2017
Line 67:		Line 67:
	This ability of the decision tree to follow the natural flow of events, as in many cases, the paths of the decision trees follow the project schedule allows the connection and incorporations with other applications as influence diagrams. Decision trees can be combined with other decision-making techniques such as PERT charts and linear distributions		This ability of the decision tree to follow the natural flow of events, as in many cases, the paths of the decision trees follow the project schedule allows the connection and incorporations with other applications as influence diagrams. Decision trees can be combined with other decision-making techniques such as PERT charts and linear distributions

	===Construction of decision tree <ref name="Kerzner">Kerzner, H., Ph.D., (2006), ""Project Management: A systems approach to planning, scheduling and controlling"". Ninth edition</ref>===		===Construction of decision tree <ref name="Kerzner">Kerzner, H., Ph.D., (2006), ""Project Management: A systems approach to planning, scheduling and controlling"". Ninth edition</ref> <ref name="Kerzner">Kerzner, H., Ph.D., (2006), ""Project Management: A systems approach to planning, scheduling and controlling"". Ninth edition</ref>===

	For an accurate construction of a decision tree, a project manager needs to conduct the following steps		For an accurate construction of a decision tree, a project manager needs to conduct the following steps
			*Identification of the major possible decisions
	*Construction of a logic tree, usually from left to right, including the decision and chance nodes		*Construction of a logic tree, usually from left to right, including the decision and chance nodes
	*Addition of the probabilities of the different states on the branches of the tree. The logic tree is, therefore, transformed into a probability tree. Calculation of the probabilities in the endpoints. The sum in the probabilities in the endpoints must be equal to one.		*Addition of the probabilities of the different states on the branches of the tree. The logic tree is, therefore, transformed into a probability tree. Calculation of the probabilities in the endpoints. The sum in the probabilities in the endpoints must be equal to one.

S162469: /* Posterior Analysis */

2017-10-02T20:13:45Z

Posterior Analysis

← Older revision		Revision as of 20:13, 2 October 2017
Line 134:		Line 134:
	A posterior analysis is used to evaluate the effect of activities, which factually they have performed. More specifically, in posterior analysis, additional information is available. Consequently, the probabilities that are used for the prior decision analysis can be updated, leading eventually to more accurate estimations and, therefore, more accurate decision-making.		A posterior analysis is used to evaluate the effect of activities, which factually they have performed. More specifically, in posterior analysis, additional information is available. Consequently, the probabilities that are used for the prior decision analysis can be updated, leading eventually to more accurate estimations and, therefore, more accurate decision-making.

	~~====Example====~~

	[[File:Decision_tree_3.PNG\|thumb\|right\|250px\|Figure 6: Decision Tree for pre-posterior Analysis]]		[[File:Decision_tree_3.PNG\|thumb\|right\|250px\|Figure 6: Decision Tree for pre-posterior Analysis]]
Line 143:		Line 142:

	<math> P'[\theta_i] = \frac{P[z_k\|\theta_i] P[\theta_i]} { \sum_{j=1}^{n} P[z_k\|\theta_j] P'[\theta_j]} </math>		<math> P'[\theta_i] = \frac{P[z_k\|\theta_i] P[\theta_i]} { \sum_{j=1}^{n} P[z_k\|\theta_j] P'[\theta_j]} </math>

			For the estimation of the expected costs or expected values of the different decisions, after the calculatio of the posterior probability, the same procedure as in prior analysis is applied. Moreover, the project manager should consider additional costs from obtaining the additional information.

	===Pre-posterior Analysis===		===Pre-posterior Analysis===