Draft your decision tree. This task presupposes a data set, a viable decision analysis research question, and the necessary data prep. Make sure to reflect on your instructor's feedback from the Milestone One assignment.

You may have to experiment with different modeling styles. The main objective is to draft your model and explain what you did and why it is the best model for your research question.

Your submission should include the following critical elements:

• A clear description of the structure and purpose of the decision tree model that you choose.
• Documentation that refers to potential complications in the analysis process, in an outline or bulleted format. This should be clear, concise, and thorough.
• An evaluation of the results of the model, which includes a discussion of whether or not the results are reasonable and the model is accurate, whether or not there are elements that are not present or are needlessly present, and any errors that may be present.
• Data Link

http://www.seanlahman.com/baseball-archive/statistics/

• Research Question

Are winning teams built based on pitching or hitting?

• . First, you need to have a viable decision analysis research question. In other words, you need a research question that analyzes a discrete set of choices.
• Second, you need to have at least one viable data set. It needs to contain the variables and covariates of interest, or if you have multiple data sets, they need to be combined. a. You have been learning skills in R that will assist you in this data prep phase. If R is still uncomfortable, you can always use Microsoft Excel. The data set you end up with needs to be cleaned of errors and ready to go for use in Rattle or in R to create probabilities.
• Third, and this is the most critical, you need to decide whether you are going to engage in a bottom-up or top-down modeling style. a. If you are going to use a top-down model, you need to be able to create proportions from your data set that represent the decision nodes and chance nodes that fall on the path between outcomes and choices. Get the variables ready as proportions for top-down modeling. b. If you are going to use a bottom-up model, you need to decide how many groups should be represented in the outcome of interest. Is that outcome represented as a continuous value in the data set? If it is, then it will need to be converted into a categorical variable.