Presentation on theme: "Cross-classified and Multiple membership models"— Presentation transcript:
1Cross-classified and Multiple membership models Lecture 21Cross-classified and Multiple membership models
2Lecture Contents Cross classified models AI example Multiple membership modelsDanish chickens exampleMore complex structuresALSPAC educational exampleThanks to Jon Rasbash for slides!
3Cross-classification For example, hospitals by neighbourhoods. Hospitals will draw patients from many different neighbourhoods and the inhabitants of a neighbourhood will go to many hospitals. No pure hierarchy can be found and patients are said to be contained within a cross-classification of hospitals by neighbourhoods :nbhd 1nbhd 2Nbhd 3hospital 1xxxhospital 2hospital 3hospital 4xxxHospital H H H H4Patient P1 P2 P3 P4 P5 P6 P7 P8 P9 P10 P11 P12Nbhd N N N3
4Other examples of cross-classifications pupils within primary schools by secondary schools.patients within GPs by hospitals.interviewees within interviewers by surveys.repeated measures within raters by individual. (e.g. patients by nurses)
5NotationWith hierarchical models we use a subscript notation that has one subscript per level and nesting is implied reading from the left. For example, subscript pattern ijk denotes the i’th level 1 unit within the j’th level 2 unit within the k’th level 3 unit.If models become cross-classified we use the term classification instead of level. With notation that has one subscript per classification, that captures the relationship between classifications, notation can become very cumbersome. We propose an alternative notation introduced in Browne et al. (2001) that only has a single subscript no matter how many classifications are in the model.
6Single subscript notation Hospital H H H H4Patient P1 P2 P3 P4 P5 P6 P7 P8 P9 P10 P11 P12Nbhd N N N3We write the model asinbhd(i)hosp(i)123456789101112Where classification 2 is neighbourhood and classification 3 is hospital. Classification 1 always corresponds to the classification at which the response measurements are made, in this case patients. For patients 1 and 11 equation (1) becomes:
7Classification diagrams In the single subscript notation we lose information about the relationship(crossed or nested) between classifications. A useful way of conveying this information is with the classification diagram. Which has one node per classification and nodes linked by arrows have a nested relationship and unlinked nodes have a crossed relationship.HospitalNeighbourhoodHospitalPatientNeighbourhoodPatientCross-classified structure where patients from a hospital come from many neighbourhoods and people from a neighbourhood attend several hospitals.Nested structure where hospitals are contained within neighbourhoods
8Example : Artificial insemination by donor 1901 women279 donors1328 donations12100 ovulatory cyclesresponse is whether conception occurs in a given cycleIn terms of a unit diagram:Or a classification diagram:DonorWomanCycleDonation
9Model for artificial insemination data We can write the model asResults:ParameterDescriptionEstimate(se)intercept-4.04(2.30)azoospermia *0.22(0.11)semen quality0.19(0.03)womens age>35-0.30(0.14)sperm count0.20(0.07)sperm motility0.02(0.06)insemination to early-0.72(0.19)insemination to late-0.27(0.10)women variance1.02(0.21)donation variance0.644(0.21)donor variance0.338(0.07)
10Multiple membership models When level 1 units are members of more than one higher level unit we describe a model for such data as a multiple membership model.For example, Pupils change schools/classes and each school/class has an effect on pupil outcomes.Patients are seen by more than one nurse during the course of their treatment.
11NotationNote that nurse(i) now indexes the set of nurses that treat patient i and w(2)i,j is a weighting factor relating patient i to nurse j. For example, with four patients and three nurses, we may have the following weights:n1(j=1)n2(j=2)n3(j=3)p1(i=1)0.5p2(i=2)1p3(i=3)p4(i=4)Here patient 1 was seen by nurse 1 and 3 but not nurse 2 and so on. If we substitute the values of w(2)i,j , i and j. from the table into (1) we get the series of equations :
12Classification diagrams for multiple membership relationships Double arrows indicate a multiple membership relationship between classifications.We can mix multiple membership, crossed and hierarchical structures in a single model.patientnursepatientnursehospitalGP practiceHere patients are multiple members of nurses, nurses are nested within hospitals and GP practice is crossed with both nurse and hospital.
13Example involving nesting, crossing and multiple membership – Danish chickens Production hierarchy10,127 child flocks725 houses304 farmsBreeding hierarchy10,127 child flocks200 parent flocksAs a unit diagram:As a classification diagram:Child flockHouseFarmParent flock
15ALSPAC dataAll the children born in the Avon area in 1990 followed up longitudinally.Many measurements made including educational attainment measures.Children span 3 school year cohorts(say 1994,1995,1996).Suppose we wish to model development of numeracy over the schooling period. We may have the following attainment measures on a child :m1 m2 m3 m m5 m6 m7 m8primary school secondary school
16Structure for primary schools P School CohortAreaM. OccasionPupilP. TeacherMeasurement occasions within pupils.At each occasion there may be a different teacher.Pupils are nested within primary school cohorts.All this structure is nested within primary school.Pupils are nested within residential areas.
17A mixture of nested and crossed relationships M. occasionsPupilP. TeacherP School CohortPrimary schoolAreaNodes directly connected by a single arrow are nested, otherwise nodes are cross-classified. For example, measurement occasions are nested within pupils. However, cohort are cross-classified with primary teachers, that is teachers teach more than one cohort and a cohort is taught by more than one teacher.T1T2T3Cohort 1959697Cohort 298Cohort 39900
18Multiple membershipIt is reasonable to suppose the attainment of a child in a particualr year is influenced not only by the current teacher, but also by teachers in previous years. That is measurements occasions are “multiple members” of teachers.m m m m4t t t t4M. occasionsPupilP. TeacherP School CohortPrimary schoolAreaWe represent this in the classification diagram by using a double arrow.
19What happens if pupils move area? M. occasionsPupilP. TeacherP School CohortPrimary schoolAreaClassification diagram without pupils moving residential areas.If pupils move area, then pupils are no longer nested within areas. Pupils and areas are cross-classified. Also it is reasonable to suppose that pupils measured attainments are effected by the areas they have previously lived in. So measurement occasions are multiple members of areas.M. occasionsPupilP. TeacherP School CohortPrimary schoolAreaClassification diagram where pupils move between residential areas.BUT…
20If pupils move area they will also move schools M. occasionsPupilP. TeacherP School CohortPrimary schoolAreaClassification diagram where pupils move between areas but not schools.If pupils move schools they are no longer nested within primary school or primary school cohort. Also we can expect, for the mobile pupils, both their previous and current cohort and school to effect measured attainments.M. occasionsPupilP. TeacherP School CohortPrimary schoolAreaClassification diagram where pupils move between schools and areas.
21If pupils move area they will also move schools cnt’d And secondary schools…M. occasionsPupilP. TeacherP School CohortPrimary schoolAreaWe could also extend the above model to take account of Secondary school, secondary school cohort and secondary school teachers.
22Other predictor variables Remember we are partitioning the variability in attainment over time between primary school, residential area, pupil, p. school cohort, teacher and occasion. We also have predictor variables for these classifications, eg pupil social class, teacher training, school budget and so on. We can introduce these predictor variables to see to what extent they explain the partitioned variability.
23Information for the practicals We have two MLwiN practicals taken from chapters of Browne (2003).We firstly look at a cross-classified model for education data (primary schools and secondary schools.We secondly look at a multiple membership model for a (simulated) earnings dataset.