An alternative procedure for fitting relational model life tables

Area of Science:

• Demography
• Mortality Analysis
• Statistical Modeling

Background:

• Challenges in constructing life tables arise when infant and child mortality data are unreliable or absent.
• Such data deficiencies are common in populations with indirect adult mortality estimation (e.g., orphanhood methods) or incomplete vital registration.
• Traditional methods often overemphasize data from younger age groups, potentially skewing results.

Purpose of the Study:

• To develop and present a novel technique for fitting relational model life tables.
• To address the specific problem of incomplete mortality data, particularly the lack of infant and child mortality estimates.
• To offer an alternative fitting method that provides a more equitable weighting of available age-specific mortality data.

Main Methods:

• The study proposes a new fitting technique for relational model life tables.
• This method allows for equal weighting of all available age-specific mortality risk information.
• The technique is applied to mortality data where infant and child mortality estimates are not reliable.

Main Results:

• The proposed fitting technique offers an improvement over traditional methods by not disproportionately weighting younger age data.
• It enables a more balanced utilization of all available age-specific mortality risk information.
• An application using Brazilian demographic data demonstrates the practical utility of the method.

Conclusions:

• The developed fitting technique is effective for constructing life tables with incomplete mortality data.
• This approach enhances the reliability of demographic analyses in situations with data limitations.
• The method provides a valuable tool for demographers and public health researchers working with challenging datasets.