chuckf333 / DataScienceProject

0 stars 0 forks source link

p02 peer review summary #8

Open ballen2024 opened 4 years ago

ballen2024 commented 4 years ago

- Data Preparation: Good job with cleaning the data and especially with the web scraping. The final product was good.

- Modeling: Something that catches my eye is that in your model, each year is used as a predictor for average salary, which I think would be obvious from your plot in Phase 1, so I would not include that in your model. I realized that you mentioned that too, but even still. I might just mention that instead of printing out the whole model summary. Looking at the plot, I am not sure if you can definitively say that the better a player bats the more they are paid. I say this because there appears to be an equal amount of points below and above your line which means that no matter what people are paid, they seem to be hitting the same.

- R Proficiency: Hiding warnings would be a good practice, since they don't serve any purpose in a writeup. A suggestion that I would have too is to use the index.html file that Kevin provided. It looks clean in my opinion.

- Communication: You did a good job of communicating what your predictions where and how your model fit in to it.

- Critical Thinking: Like I said before, I am not sure if the conclusions drawn from your plot are definitive, so maybe explain that. I could just be totally missing it though. My reasoning behind it is if it looks like there are the same amount of points on both sides of the line, then it wouldn't point to the higher the salary, the better the players.

- Feedback: I would not include the output of the phase 1 loading. Good job with stat_smooth().