Working Paper: CEPR ID: DP17326
Authors: Christopher Rauh; Laetitia Renee
Abstract: In this paper, we measure parenting styles through unsupervised machine learning in a panel following children from age 5 to 29 months. The topic model classifies parents into two parenting styles: "warm" and "cold". Parents of the warm type tend to respond to children's expressions in a supportive manner, while parents of the cold type are less likely to engage with their children in an encouraging manner. Warm parenting is more likely amongst educated and older mothers. Although styles reveal some persistence, the share of parents with a warm style decreases with the age of the child, in particular for boys. Children of warm parents achieve higher cognitive and non-cognitive scores at later ages. We find that the topic model estimated on different sample splits, such as by education or child age, reveal additional information while maintaining robust overall patterns.
Keywords: parenting style; human capital; inequality; early childhood; machine learning
JEL Codes: No JEL codes provided
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| warm parenting (J13) | higher cognitive and noncognitive scores in children (I21) |
| cold parenting (J13) | lower cognitive and noncognitive scores in children (I24) |
| parenting style at 5 months (J13) | later outcomes (I12) |
| warm parenting (J13) | better cognitive and noncognitive scores (D29) |
| parenting styles (J13) | children's developmental outcomes (I25) |