Partner violence surrounding divorce: A record-linkage study of wives and their husbands

Abstract

Objective: This study analyzes the victimization trajectories of partner violence against women surrounding divorce, depending on whether the couple has children together.

Background: Prior studies have found that partner violence is associated with an increased risk of divorce. No study has assessed the victimization trajectories surrounding divorce for women with and without children, although women with children may remain at higher risk of violence following divorce.

Method: Using Finnish record-linkage data of 22,468 divorced and 333,542 continuously married women and their husbands, we used repeated-measures logistic regression analyses to assess changes in victimization for partner violence before and after divorce. The outcomes considered were police-reported crimes committed by husbands against their wives and hospital-treated assault injuries recorded for wives.

Results: The risk of crime victimization for partner assault was already elevated from 2 to 3 years before divorce, peaked in the year prior to divorce, and then mainly leveled off 1-2 years after divorce. Hospital data show that the time of the greatest risk was from 6 to 12 months before divorce, when divorce is usually filed for. Women with younger children experienced elevated risks of physical violence shortly before divorce and remained at higher risk of menace than women without children for a year after divorce.

Conclusion: Divorcing women committed assaults against their husbands, but these were mostly accompanied by victimization, suggesting that resistant violence was common for women as perpetrators. Women with a history of victimization need support, especially at the starts of their divorce processes.

Keywords: crime; divorce; domestic violence; intimate partner violence; marital relations; motherhood.

FIGURE 1

Trajectories of hospitalization for assault injuries (6‐month probability) before and after the date of divorce for divorcing women, and before and after a random date for continuously married women. The predicted probabilities shown in the left panel are adjusted for calendar year only and those in the right panel are adjusted for calendar year, age, education, the duration and order of marriage, and the number of children. Error bars are 95% confidence intervals. [Color figure can be viewed at wileyonlinelibrary.com]

FIGURE 2

Trajectories of crime victimization for partner assault (annual probability) before and after the year of divorce for divorcing women, and before and after the year 2015 for continuously married women. The predicted probabilities shown in the left panel are unadjusted and those in the right panel are adjusted for year, age, education, the duration and order of marriage, and the number of children. Error bars are 95% confidence intervals. [Color figure can be viewed at wileyonlinelibrary.com]

FIGURE 3

Trajectories of crime victimization for menace (annual probability) before and after the year of divorce for divorcing women, and before and after the year 2015 for continuously married women. The predicted probabilities shown in the left panel are unadjusted and those in the right panel are adjusted for year, age, education, the duration and order of marriage, and the number of children. Error bars are 95% confidence intervals. [Color figure can be viewed at wileyonlinelibrary.com]

FIGURE 4

Unadjusted trajectories of crime victimization for partner assault (left panel) and menace (right panel) before and after the year of divorce for divorcing women, and before and after the year 2015 for continuously married women, according to whether women have children with their husbands. Error bars are 95% confidence intervals. [Color figure can be viewed at wileyonlinelibrary.com]

FIGURE 5

Trajectories of crime victimization for partner assault (left panel) and menace (right panel) before and after the year of divorce for divorcing women, according to the age of the youngest child. The predicted probabilities are adjusted for year, age, education, and the duration and order of marriage. Error bars are 95% confidence intervals. [Color figure can be viewed at wileyonlinelibrary.com]

FIGURE 6

Unadjusted trajectories of crime victimization for and perpetration of menace (left panel) and of partner assault (middle panel) for divorcing women, and the number of divorcing women who experienced partner assault as a victim only, as a victim and perpetrator, and as a perpetrator only before and after the year of divorce (right panel). Error bars are 95% confidence intervals based on the predicted probabilities from repeated‐measures logistic models. [Color figure can be viewed at wileyonlinelibrary.com]