Home > Research > Publications & Outputs > Model-based imputation of missing data from the...

Research

Links

Text available via DOI:

Keywords

View graph of relations

Model-based imputation of missing data from the 122 Cities Mortality Reporting System (122 CMRS)

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Model-based imputation of missing data from the 122 Cities Mortality Reporting System (122 CMRS). / Moraga, P.; Ozonoff, A.
In: Stochastic Environmental Research and Risk Assessment, Vol. 29, No. 5, 2013, p. 1499-1507.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Moraga, P & Ozonoff, A 2013, 'Model-based imputation of missing data from the 122 Cities Mortality Reporting System (122 CMRS)', Stochastic Environmental Research and Risk Assessment, vol. 29, no. 5, pp. 1499-1507. https://doi.org/10.1007/s00477-014-0974-4

APA

Moraga, P., & Ozonoff, A. (2013). Model-based imputation of missing data from the 122 Cities Mortality Reporting System (122 CMRS). Stochastic Environmental Research and Risk Assessment, 29(5), 1499-1507. https://doi.org/10.1007/s00477-014-0974-4

Vancouver

Moraga P, Ozonoff A. Model-based imputation of missing data from the 122 Cities Mortality Reporting System (122 CMRS). Stochastic Environmental Research and Risk Assessment. 2013;29(5):1499-1507. doi: 10.1007/s00477-014-0974-4

Author

Moraga, P. ; Ozonoff, A. / Model-based imputation of missing data from the 122 Cities Mortality Reporting System (122 CMRS). In: Stochastic Environmental Research and Risk Assessment. 2013 ; Vol. 29, No. 5. pp. 1499-1507.

Bibtex

@article{381e383f0e244636b6a5b7ec6baadabe,
title = "Model-based imputation of missing data from the 122 Cities Mortality Reporting System (122 CMRS)",
abstract = "National estimates of the all-cause and pneumonia and influenza (P&I) mortality burden derived from U.S. influenza surveillance data treat all missing or unreported values as zero counts. The effect of this methodological decision is to undercount influenza deaths, thus biasing estimates downward and producing underestimates of the true mortality burden. In this paper, a regression-based procedure is proposed to impute missing values and thus produce a more accurate estimate of mortality. Several model specifications are considered and evaluated to predict weekly death counts by city, calendar week, calendar year and age group. Revised all-cause, P&I and excess mortality estimates are calculated by imputing the missing data. The impact of the treatment of unreported mortality data on national estimates is evaluated by comparing the estimates obtained using data with and without imputation. This comparison reflects some differences in mortality burden, excess deaths, and trends over time. The model presented is a useful approach to impute missing counts and improve inference in situations with modest occurrence of missing data.",
keywords = "Influenza surveillance , Excess mortality , Missing data, Serfling method ",
author = "P. Moraga and A. Ozonoff",
year = "2013",
doi = "10.1007/s00477-014-0974-4",
language = "English",
volume = "29",
pages = "1499--1507",
journal = "Stochastic Environmental Research and Risk Assessment",
issn = "1436-3240",
publisher = "Springer New York",
number = "5",

}

RIS

TY - JOUR

T1 - Model-based imputation of missing data from the 122 Cities Mortality Reporting System (122 CMRS)

AU - Moraga, P.

AU - Ozonoff, A.

PY - 2013

Y1 - 2013

N2 - National estimates of the all-cause and pneumonia and influenza (P&I) mortality burden derived from U.S. influenza surveillance data treat all missing or unreported values as zero counts. The effect of this methodological decision is to undercount influenza deaths, thus biasing estimates downward and producing underestimates of the true mortality burden. In this paper, a regression-based procedure is proposed to impute missing values and thus produce a more accurate estimate of mortality. Several model specifications are considered and evaluated to predict weekly death counts by city, calendar week, calendar year and age group. Revised all-cause, P&I and excess mortality estimates are calculated by imputing the missing data. The impact of the treatment of unreported mortality data on national estimates is evaluated by comparing the estimates obtained using data with and without imputation. This comparison reflects some differences in mortality burden, excess deaths, and trends over time. The model presented is a useful approach to impute missing counts and improve inference in situations with modest occurrence of missing data.

AB - National estimates of the all-cause and pneumonia and influenza (P&I) mortality burden derived from U.S. influenza surveillance data treat all missing or unreported values as zero counts. The effect of this methodological decision is to undercount influenza deaths, thus biasing estimates downward and producing underestimates of the true mortality burden. In this paper, a regression-based procedure is proposed to impute missing values and thus produce a more accurate estimate of mortality. Several model specifications are considered and evaluated to predict weekly death counts by city, calendar week, calendar year and age group. Revised all-cause, P&I and excess mortality estimates are calculated by imputing the missing data. The impact of the treatment of unreported mortality data on national estimates is evaluated by comparing the estimates obtained using data with and without imputation. This comparison reflects some differences in mortality burden, excess deaths, and trends over time. The model presented is a useful approach to impute missing counts and improve inference in situations with modest occurrence of missing data.

KW - Influenza surveillance

KW - Excess mortality

KW - Missing data

KW - Serfling method

U2 - 10.1007/s00477-014-0974-4

DO - 10.1007/s00477-014-0974-4

M3 - Journal article

VL - 29

SP - 1499

EP - 1507

JO - Stochastic Environmental Research and Risk Assessment

JF - Stochastic Environmental Research and Risk Assessment

SN - 1436-3240

IS - 5

ER -