Astrology as latent variable model

Many people love to bash astrology, but I see some value in it. I view many kinds of astrology around the world as being like qualitative latent variable models, which are statistical models where usually many observed variables are related to a few latent/hidden variables, often as a way of summarizing/reducing the complexity of the many variables. Ancient societies apparently were not as quantifying and standardizing of every little thing as we are today, but they nevertheless made observations about people’s mental, physical, and behavioral characteristics, and how such things sometimes correlate with natural phenomena, like seasons and moon phases. The results usually are not as rigorous as today’s scientists would want (e.g., we now know about microscopic genetic disorders and infections, regional environmental adaptations, and social pressures that can have physical effects on groups of people), but they do often represent the observations of millions of people over thousands of years, and they often take the form of many observed variables being related to a few typified, latent variables. It might be interesting to apply modern quantitative rigor to the patterns that astrology systems have observed — for example, measure people to see if those born in the summer really do have pointier/straighter physical features (noses, ears, jawlines, etc.) and more extroverted personalities on average than people born in the winter, as some Chinese/Japanese astrology systems suspect — to see if they know about any natural patterns that science has yet to notice.


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s