BB

Decision Analysis

Multi-criteria decision making (MCDA) is used to logically evaluate and compare multiple criteria that are often conflicting to make the best possible decision

Multi-Criteria Decision Analysis steps

  1. State the problem/objective

  2. Establish criteria (factors and constraints)

    1. State the problem/objective

    2. Establish criteria: factors and considerations

    3. Factor = criterion that enhances or lowers the suitability of a specific alternative for the activity under consideration

    4. Constraint = criterion that limits the alternatives under considerations

    5. Standardize factors - put factors all on the same scale to facilitate comparison

    6. Reclass Boolean – either 1 or 0

    7. Reclass multiple classes – range of values (Useful when integrating multiple considerations and factors)

    8. Reclass fuzzy approach – continuous scale of values

    9. Establish factor weights by using one of the following methods:

    10. Ranking: rank factors with 1, 2, & 3

    11. Rating: rate factors using percentile

    12. Pairwise comparison: Analytical Hierarchy Process (AHP)

    13. Matrix is constructed where each criterion is compared with the other, relative to its importance

    14. A weighted estimate is calculated and used to derive a consistency ratio (CR) of the pairwise comparisons

    15. These are usually converted to numerical weights on a scale of 0 to 1 with an overall summation of 1 (normalization)

    16. Aggregate the criteria

    17. Boolean overlay (BOOLEAN AND)

    18. Weighted Linear Combination (formula)

    19. Weighted linear overlay, fuzzy overlay

    20. Validate/verify the results to assess the reliability of the output, asking do the results reflect reality?

    21. Ground truth verification

  3. Sensitivity analysis – how do the following affect the result

1.   Altering the set of criteria
2. Alerting the respective weights of the factors
3. Is the result reasonable?

Flow Chart of Research

Similar to a flow chart in programming, where it should all the logical steps you take in order to achieve the final map/results. It shows the whole map of what we are doing, without the map, by showing the data and the processes.

Steps to creating a Flow Chart of Research:

  1. Identify what kind of data we need for the project

    1. Both shapefiles and tables

  2. Input the constraints/conditions to classify the map as wither suitable or unsuitable

    1. Using either the values of the variables or a buffer area
    2. Constraints are delineated in red lines, conditions are delineated in green lines

  3. Merging unsuitable and suitable map creates the final potential site maps