SLIDE 1
Towards statistically solid thinking about validation
Rick.Donnelly@wsp.com | WSP | 6 May 2020
Traditional practice
2
Towards statistically solid thinking about validation - - PowerPoint PPT Presentation
Towards statistically solid thinking about validation - - PowerPoint PPT Presentation
Towards statistically solid thinking about validation Rick.Donnelly@wsp.com | WSP | 6 May 2020 Traditional practice 2 Top five criteria (n=9) 3 Three revelations Rethinking validation: 1. Differentiate by count type 2. Trimming outliers
SLIDE 2
SLIDE 3
Top five criteria (n=9)
3
SLIDE 4
Three revelations
Rethinking validation: 1. Differentiate by count type 2. Trimming outliers 3. Using meta-networks
4
SLIDE 5
Not all counts are created equal
5
SLIDE 6
Recent outcome
6
SLIDE 7
Potential error in counts
7
Assumptions:
- Data are normally distribution
- Distribution has mean μ and standard deviation σ
- Observations are independent of one another
Implications for counts:
SLIDE 8
Alternative view
8
SLIDE 9
Some traditional stats
9
Root mean squared error: Percent root mean squared error:
SLIDE 10
Outlier effects on RMSE and percent RMSE
10
SLIDE 11
Optimal counts?
11
SLIDE 12
Meta-networks
1. Include only freeways, expressways, major arterials 2. Collapse freeway interchanges to single point 3. Meta-nodes: where these arcs intersect 4. Meta-links: single bidirectional arc between meta-nodes 5. One count per meta-link → independent observations by definition 6. Validate and visualize at the meta-network level
12
SLIDE 13
Forecasting errors
13
SLIDE 14
In perspective...
14
SLIDE 15
Telecommuting trends over time
15
SLIDE 16
Questions?
16