Over the four days I spent at JSM back in August, I met with four different college professors. I think I gained a lot of knowledge even in such a short time about different topics in data science.
In my meeting with Professor Annie Qu, I got information about a summer program held by UCI which focuses on data science. With Professor Rebecca Hubbard, I learned about Frequentist statistics which makes a lot more sense to me, be thought of as the inverse of Bayesian statistics. I learned machine learning is actually a loosely defined blanket term for predictive models, and that measurement error actually just accounts for error instead of trying to correct for interpolation or other means. When meeting Professor Maria Cuellar, I learned causal inference is the measure of the difference between if an action is taken or not, and that the reason causal inference exists is because we cannot preform studies such as clinical trials on an individual person and say job well done. I also learned machine learning can be treated as the next step after causal inference. In addition, machine learning works in a similar field to statistics but statistics is slower and spends more time in proving its approach and work. In my meeting with Professor Razieh Nabi, I learned causal inference is also important in order to distinguish correlation and causation. I also learned that there are three ways to teach machine learning supervised, where it is fed complete examples; unsupervised, where the ML will cluster, knowing things are alike but not what they are; and reinforcement, where the ML will experiment and a human will give it either positive or negative feedback.
Throughout JSM, I felt these meetings were very informative, and that now I have a much better understanding of data science concepts but there is still a long way for me to go.