Milestone I Exam With Correct Complete Solutions Graded A+

What is the four-stage pipeline and how does it apply to your project? -Answer Problem Formulation Data Collection and Cleaning Analysis and Modeling Presentation and Integration into Action Explain how the law of small numbers applies to the work you did for your project. -Answer Not enough data can lead to over generalization What sources of bias did you identify in your project? -Answer Observer bias Researcher subconsciously projects their expectations onto the research To what degree did you follow the "10 Rules for Creating Reproducible Results in Data Science" in your project work? -Answer Followed: Version control Kept intermediated data sets Stored raw data for charts Public access How did you apply data cleaning principles in your project? -Answer Imputed a small number of results with medians/means Are there places where overfitting may have played a role in your analyses? -Answer Did not do any machine learning modeling in the analysis. Overfitting is creating a model that performs extremely well on the training data but poorly on the test data. What is cross-validation? -Answer Set aside a sample of data to test your model on later. There are numerous ways to do this, train/testing sets, kfolds, etc.