Explaining uncertainty in women's fertility preferences

Abstract

People's fertility preferences are often considered an important determinant of fertility. What is often neglected in studies of preferred fertility, is the uncertainty that people may have about their preferences. In this study, using data on Dutch women through the Longitudinal Internet studies for the Social Sciences (collected early 2018), we examined women's fertility preferences and asked detailed questions about the certainty of these preferences. We also examined whether women agreed with their partner on preferred family size, and to what extent partner (dis)agreement shaped uncertainty. We show that Dutch women expressed much uncertainty about their fertility preferences, with only one-third feeling strongly about their preferences. Uncertainty strongly increased when women preferred higher numbers of children, whereas already having children reduced it. Women who wanted no children were most certain about their preference. Higher preferred family sizes also led to more disagreement with the partner about these preferences, and greater partner disagreement, in turn, led to more uncertainty. These findings imply that people are more likely to downgrade their fertility preferences than to increase them, as women are more certain about their preferences for lower numbers of children and are more open to family sizes below than above their preferred choice. Partner disagreement is often resolved by not having (more) children, lowering realised fertility. Hence, these findings provide another explanation for why many people have fewer children than desired.

Keywords: Family size; Fertility preferences; Partner agreement; The Netherlands; Uncertainty.

Fig. 1

Percentage of women (N = 681) with varying degrees of certainty about their preferred number of children (A), depending on motherhood status (B), partnership status (C), and the preferred number of children (D).

Fig. 2

Percentage of women (N = 510) with varying degrees of agreement with her partner on the preferred number of children (A), depending on motherhood status (B), and the preferred number of children (C).

Fig. 3

Average difference in adjusted predictions on several outcomes (in grey) for the variables having children (reference: no children), having a partner (reference: no partner), age, and the preferred number of children (difference in probability with a change of respectively 1 SD and 1 unit). The average (grey dot) and the 95% confidence interval (width of bar) is based on 1000 bootstrap samples.

Fig. 4

Average difference in adjusted predictions on several outcomes (in grey) for different categories of partner agreement (reference: partner agreement). The average (grey dot) and the 95% confidence interval (width of bar) is based on 1000 bootstrap samples.