NotesFAQContact Us
Collection
Advanced
Search Tips
Peer reviewed Peer reviewed
Direct linkDirect link
ERIC Number: EJ839794
Record Type: Journal
Publication Date: 2009-Mar
Pages: 10
Abstractor: ERIC
Reference Count: 7
ISBN: N/A
ISSN: ISSN-0037-7732
Race Differences in Cohort Effects on Non-Marital Fertility in the United States: Reply to Martin
Stockard, Jean; Gray, Jo Anna; O'Brien, Robert; Stone, Joe
Social Forces, v87 n3 p1489-1498 Mar 2009
In this article, the authors clarify and provide additional tests of the key elements of their age-period-cohort analysis of non-marital birth rates in this March 2009 issue of "Social Forces." Where Steve Martin, in his commentary, has suggested specific alternative specifications or interpretations of their findings, the authors have re-estimated and performed explicit tests of the alternatives. Martin suggests two explanations for the cohort patterns found in the authors' data: (1) different trends in the relationships of age-groups to NFRs; and (2) differences in the proportion unmarried for age-groups in different periods. The authors enter variables representing both of these postulated relationships into their models and find that they do not significantly alter the coefficients associated with the cohort characteristics that they reported in their original paper. Thus, at least taking these possible explanations into consideration, the authors find that the cohort effects remain strong in their data. Martin claims that the coefficients for the cohort characteristics that the authors report are improbably large--the authors find no evidence of that in their reading of the results. Martin finds the pattern of residuals within cohorts to be "weird" given the authors' model. In fact, the pattern of the residuals is supportive of cohort effects. Finally, the authors find cohort effects for age-period-specific NFRs when they analyze only cohorts with complete data, examining cohorts born in the years 1933-1937 and 1958-1962. According to Martin, such an analysis should not be subject to the biases that form the core of his critique. The authors have demonstrated the robustness of their results and strengthened the case for their interpretations. The points Martin raises and the authors' responses should help to clarify the nature of cohort effects and the authors' interpretation of them. (Contains 1 table, 1 figure and 4 notes.)
University of North Carolina Press. 116 South Boundary Street, P.O. Box 2288, Chapel Hill, NC 27515-2288. Tel: 800-848-6224; Tel: 919-966-7449; Fax: 919-962-2704; e-mail: uncpress@unc.edu; Web site: http://uncpress.unc.edu/
Publication Type: Journal Articles; Opinion Papers
Education Level: N/A
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: N/A
Identifiers - Location: United States