Mission accomplished

The mission was to determine what machine learning could discover from a dataset of 40,000 quiz entries. The psychology researchers wanted to know if they could trust using this data to provide a path forward for their research. They also wanted to know if machine learning interpretation would show them which features and feature values impact the outcome the most.

Using PDPs, we discovered that there were some discrepancies with the distribution of age and birth order, since the proportion of middle children must increase with age. If any modeling exercise is to work in real-world scenarios, the training data must match real-world distributions. All is not all lost, though. You can take corrective measures by balancing these distributions. Significant changes likely have to be made to the data to make it more reliable for research purposes. That being said, since it's an online quiz made anonymously, you can expect lying to be commonplace, so the margin...