There are now two sets of higher level units that influence the response and in general we can have more than two such sets. In spatial models one of these sets is commonly taken to be the area where an individual (level 1) unit occurs and so does not have a multiple membership structure (since each individual belongs to just one area, that is we replace Eh W¡hM1h by w1ji). The other set consists of those neighbouring units that are assumed to have an effect. The weights will need to be carefully chosen; in spatial models W2 is typically chosen to be equal to 1 (see Langford et al.  for an example). Another application for a model such as (14) is for household data where households share facilities, for example an address. In this case the household that an individual resides in will belong to one set and the other households at the address will belong to the other set. Goldstein et al.  give an application of this model to complex household data.
Was this article helpful?