Missing Data and the Statistical Modeling of Adolescent Pregnancy Academic Article

abstract

• 2014 JMASM, Inc. Missing data is a pervasive problem in social science research. Many techniques have been developed to handle the problem. Different ways of handling missing data were shown to lead to different results in statistical models. A demonstration was given based on statistical modeling of the likelihood of a woman reporting having had an adolescent pregnancy by handling missing data with several different approaches. Results indicate that many of the independent variables in the model vary in whether they are, or are not, statistically significant in predicting the log odds of a woman having a teen pregnancy, and in the ranking of the magnitude of their relative effects on the outcome.

authors

• Poston, Dudley

published proceedings

• JOURNAL OF MODERN APPLIED STATISTICAL METHODS

author list (cited authors)

• Poston, D. L., & Conde, E.

citation count

• 1

complete list of authors

• Poston, Dudley L||Conde, Eugenia

publication date

• January 2014

publisher

• The Netherlands Press  Publisher

keywords

• Adolescent Pregnancy
• Demography
• Listwise Deletion
• Logistic Regression
• Logit Coefficients
• Mean Substitution
• Missing Data
• Multiple Imputation
• Proxy Variables
• Race/ethnicity
• Semi-standardized Logit Coefficients

Digital Object Identifier (DOI)

• 10.22237/jmasm/1414815960

start page

• 464

end page

• 478

volume

• 13

issue

• 2

URL

• http://dx.doi.org/10.22237/jmasm/1414815960