search

thekingofkings / dissertation

My PhD dissertation on spatial-temporal data mining.
0 stars 0 forks source link

Adaptive spatial model (motivation) #3

Open thekingofkings opened 8 years ago

thekingofkings commented 8 years ago

How to motivate this model?

What kind of problems we want to answer? What are the properties that are required in the model?

Compare with GWR #2, what is the difference?

In which aspects, can we promote our adaptive model superior than the GWR.

thekingofkings commented 8 years ago

Areal mode

from slides

Inference for new areal units? Is prediction meaningful here? If we modify the areal units to new units (e.g. from zip codes to county values), what can we say about the new counts we expect for the latter given those for the former? This is the Modifiable Areal Unit Problem (MAUP) or Misalignment.

thekingofkings commented 8 years ago

Modifiable Areal Unit Problem (MAUP)

The modifiable areal unit problem (MAUP) is a source of statistical bias that can radically affect the results of statistical hypothesis tests. It affects results when point-based measures of spatial phenomena (e.g., population density) are aggregated into districts. The resulting summary values (e.g., totals, rates, proportions) are influenced by the choice of district boundaries. For example, census data may be aggregated into census enumeration districts, or postcode areas, or police precincts, or any other spatial partition (thus, the "areal units" are "modifiable").

source: MAUP

notes:

this could be a good motivation on the adaptive partition of space according to the point-based measure.