Predicting Negative Childbearing Motivation using a Neural Network Approach: The Role of Parental Rejection, Early Maladaptive Schemas, and Psychological Distress.

This study explores the psychological underpinnings of negative childbearing motivation. While traditional linear models have offered some insights, they may fail to capture the complex, non-linear interactions between developmental experiences and adult cognitions. This study will utilize a neural network regression model to predict the intensity of negative childbearing motivation based on perceived parental rejection (PARQ), early maladaptive schema domains (YSQ), and current psychological distress (CORE-OM). We hypothesize that a neural network model will demonstrate superior predictive performance compared to a standard multiple linear regression. The analysis will involve splitting the data into training and testing sets, standardizing predictors, and evaluating model performance using R-squared and Root Mean Squared Error. A permutation feature importance analysis will be conducted to identify the most influential predictors. This research aims to provide a more nuanced, non-linear understanding of the psychological factors contributing to childbearing decisions.