Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Towards real-time spatio-temporal prediction of district-level meningitis incidence in sub-Saharan Africa
AU - Stanton, Michelle
AU - Agier, Agier
AU - Taylor, Benjamin
AU - Diggle, Peter
PY - 2014/6
Y1 - 2014/6
N2 - Within an area of sub-Saharan Africa termed ‘the meningitis belt’, meningococcal meningitis epidemics are a major public health concern. The epidemic control strategy currently utilised is reactive, such that a vaccination programme is initiated in a district once a pre-defined weekly incidence threshold is exceeded. In this paper we report progress towards the development of an early warning system based on statistical modelling of district-level weekly incidence data. Four modelling approaches are considered and their forecasting performances are compared usingweekly epidemiological data from Niger for the period 1986-2007. We conclude that the models under consideration are advantageous in different situations. The described three-state Markov model in which observed incidence is categorised according to policy-defined thresholds gives the most reliable short term forecasts, whereas the proposed dynamic linear model, using log-transformed weekly incidence as the response variable, gives more reliable predictions of annual epidemics.
AB - Within an area of sub-Saharan Africa termed ‘the meningitis belt’, meningococcal meningitis epidemics are a major public health concern. The epidemic control strategy currently utilised is reactive, such that a vaccination programme is initiated in a district once a pre-defined weekly incidence threshold is exceeded. In this paper we report progress towards the development of an early warning system based on statistical modelling of district-level weekly incidence data. Four modelling approaches are considered and their forecasting performances are compared usingweekly epidemiological data from Niger for the period 1986-2007. We conclude that the models under consideration are advantageous in different situations. The described three-state Markov model in which observed incidence is categorised according to policy-defined thresholds gives the most reliable short term forecasts, whereas the proposed dynamic linear model, using log-transformed weekly incidence as the response variable, gives more reliable predictions of annual epidemics.
KW - Dynamic generalized linear models
KW - Epidemic control
KW - Markov chain
KW - Meningitis belt
KW - Meningococcal meningitis
U2 - 10.1111/rssa.12033
DO - 10.1111/rssa.12033
M3 - Journal article
VL - 177
SP - 661
EP - 678
JO - Journal of the Royal Statistical Society: Series C (Applied Statistics)
JF - Journal of the Royal Statistical Society: Series C (Applied Statistics)
SN - 0035-9254
IS - 3
ER -