CONTACT US: Contact info
|
Citation |
Flaherty J. Transp. Res. Rec. 1993; 1410: 93-99. |
|
Copyright |
(Copyright © 1993, Transportation Research Board, National Research Council, National Academy of Sciences USA, Publisher SAGE Publishing) |
|
DOI |
unavailable |
PMID |
unavailable |
|
Abstract |
Monthly factor data were used as input data for cluster analysis of 28 permanent traffic volume counters installed in Arizona. Monthly factors are the ratio of monthly average daily traffic to annual average daily traffic (AADT). Cluster analysis is a statistical procedure that reveals natural groupings in data. There are two types of clustering methods: hierarchical and nonhierarchical. Hierarchical methods use a successive series of either mergers or division. Nonhierarchical methods group objects into a collection of clusters "K". Monthly factor data for each location collected over 5 years were used in the cluster analysis. The group mean monthly factors of the groups that were determined and the monthly factors of each location were applied to the appropriate randomly selected daily traffic count. These counts were proxy variables for short-term 24-hr counts. Statistical analysis was used to determine the "best" method for deriving monthly factors and also provided the best estimates of AADT. From the results of this analysis, it was determined that the two primary groups derived from using four clusters were the best and the most stable of all the variations used in the analysis. The statistical analysis revealed that the results obtained from using the grouped mean monthly factors of this variation were marginally better than those from the other variations. The two distinct groups that were determined as a result of the analysis are quite stable with respect to time and provide an estimated level of precision that was greater than acceptable. Language: en |
|
Keywords |
Recording; Algorithms; Estimation; Computer simulation; Highway systems; Statistical methods; Traffic surveys; Random processes; Data reduction; Hierarchical systems; Multivariable systems; Recording instruments; Statistical tests |