A Multilevel Model of Sudden Infant Death Syndrome in England and Wales

Abstract

It has previously been shown that there is a significant association between mortality from sudden infant death syndrome (SIDS) and rates of long-term migration between local authority districts in England and Wales. This evidence supports the theory that exposure to infections, mediated by population mixing, may be an important factor in many cases of SIDS. In this paper, multilevel modelling is used to examine the variability in SIDS deaths at different geographical scales, namely district, county, and regional levels. Given the population-mixing hypothesis, it is possible that high levels of population mixing in one district will have an effect on the spread of infections in an adjacent district, and the rates for individual districts will not be spatially independent of each other. Factors such as climate varying at regional scale may also be important. A log—linear multilevel model is developed to examine these issues, and the discussion focuses on the methodological issues raised by the analysis such as appropriate multilevel structure, methods of estimation, dispersion of residuals, and significance of parameter estimates.

Get full access to this article

View all access options for this article.

References

Beal

S M

Finch

C F

, 1991, “An overview of retrospective case-control studies investigating the relationship between prone sleeping position and SIDS” Journal of Paediatric Child Health 27 334–339

Beckwith

J B

, 1970, “Observations on the pathological anatomy of the sudden infant death syndrome”, in Proceedings of the Second International Conference on the Causes of Sudden Death in Infants Eds Bergman

A E

Beckwith

J B

Roy

C G

(Washington Press, Seattle, WA) pp 83–110

Bentham

, 1994, “Population mixing and sudden infant death syndrome in England and Wales” International Journal of Epidemiology 23 540–544

Bernardinelli

Montomoli

, 1992, “Empirical Bayes versus fully Bayesian analysis of geographical variation in disease risk” Statistics in Medicine 11 983–1007

Breslow

N E

, 1984, “Extra-Poisson variation in log—linear models” Applied Statistics 33 38–44

Breslow

N E

Clayton

D G

, 1993, “Approximate inference in generalized linear mixed models” Journal of the American Statistical Association 88 9–25

Bryk

A S

Raudenbush

S W

, 1992 Hierarchical Linear Models: Applications and Data Analysis Methods (Sage, London)

Clayton

Kaldor

, 1987, “Empirical Bayes estimates of age-standardized relative risks for use in disease mapping” Biometrics 43 671–681

Department of Health, 1993 Report of the Chief Medical Officer's Expert Group in the Sleeping Position of Infants and Cot Death (HMSO, London)

10.

Dwyer

Ponsonby

A L

, 1992, “Sudden infant death syndrome—insights from epidemiological research” Journal of Epidemiology and Community Health 46 98–102

11.

Fleming

P J

Gilbert

Azaz

Berry

Rudd

Stewart

, and Others, 1990, “Interaction between bedding and sleeping position in the sudden infant death syndrome: a population based case-control study” British Medical Journal 301 85–89

12.

Fox

J P

Elveback

Scott

Gatewood

Ackerman

, 1971, “Herd immunity: basic concept and relevance to public health immunization practices” American Journal of Epidemiology 94 179–189

13.

Gilbert

R E

Fleming

P J

Azaz

Rudd

P T

, 1990, “Signs of illness preceding sudden unexpected deaths in infants” British Medical Journal 300 1237–1239

14.

Golding

Limerick

Macfarlane

, 1985 Sudden Infant Death: Patterns, Puzzles and Problems (Open Books, Wells, Somerset)

15.

Goldstein

, 1995 Multilevel Statistical Models 2nd edition (Edward Arnold, London)

16.

Howat

W J

Moore

I E

Judd

Roche

W R

, 1994, “Pulmonary immunopathology of sudden infant death syndrome” Lancet 343 1390–1392

17.

Kinlen

L J

, 1988, “Evidence for an infective cause of childhood leukaemia: comparison of a Scottish new town with nuclear reprocessing sites in Britain” Lancet ii 1323–1327

18.

Jones

M E

Ponsonby

A L

Dwyer

Gilbert

, 1994, “The relationship between climatic temperature and sudden infant death syndrome differs among communities: results from an ecological analysis” Epidemiology 5 332–336

19.

Langford

I H

, 1994a, “A cross-classified multilevel model of district mortality rates” Multilevel Modelling Newsletter 6(2) 9–11

20.

Langford

I H

, 1994b, “Using empirical Bayes estimates in the geographical analysis of disease risk” Area 26 142–149

21.

Langford

I H

Bentham

McDonald

A-L

, 1995, “Malignant melanoma mortality and UV exposure in the European Community”, CSERGE GEC WP 95-13 (University of East Anglia, Norwich)

22.

Lindley

D V

Smith

F M

, 1972, “Bayes estimates for the linear model (with discussion)” Journal of the Royal Statistical Society Series B 34 1–41

23.

OPCS, 1990 Mortality and Geography: A Review in the Mid-1980s: The Registrar General's Decennial Supplement for England and Wales Series DS, number 9, Office of Population Censuses and Surveys (HMSO, London)

24.

Ponsonby

A L

Dwyer

Jones

M E

, 1992, “Sudden infant death syndrome: seasonality and a biphasic model” Journal of Epidemiology and Community Health 46 33–37

25.

Rasbash

Woodhouse

, 1995 MLn Command Reference: version 1.0 Multilevel Models Project (Institute of Education, University of London, London)