You will work to complete this business analytics project. The project can be fo

You will work to complete this business analytics project. The project can be focused on OCD data
If on a specific organization: Select a dataset about this specific organization and apply the techniques used in this course to run an analytic project to help assist the executives in organizational decision-making. The project report will includethe dataset link,
an overview of the organization and the industry in which it operates,
the opportunity or challenge you are attempting to address through business analytics,
the results and recommendations, and
references (if any).
If on a general research question: Identify a research question you would like to address through use of the techniques and applications covered in this course. The project will includethe research question
an argument stating the importance of your research question,
your hypotheses,
the methodology used,
the source of the data,
a write-up of your results and implications, and
references (if any).
As part of the project, you should apply multiple techniques, compare and contrast their results using the evaluation techniques covered in the course. The deliverables for the project will be
This project will be held to the standards of publishable research, so proper citation and formatting are required.
use R or R Studio to get the data as well
use these comments for a feedback to revise the paper
introduction and the research/business question(s) (10 points/100 points)
Okay.
* an argument stating the importance of your research question (10 points/100 points)
Okay
* your hypotheses (5 points/100 points)
Okay
* the data and EDA (20 points/100 points; data source, # of obs; list of variables with description and variable type; univariate, bivariate, numerical and graphical, with outputs and comments on the outputs)
– No clear data source stated; -1
– # of obs; Okay
– list of variables with description & variable type; Okay
– univariate numerical and/or graphical summary and comments. Not much! -1.5
– bivariate analysis and comments:
1) contingency table: -1
2) scatterplots and correlation: Okay
3) boxplot by group: -1
* the methodology used (apply multiple techniques, compare and contrast their results using the evaluation techniques covered in the course) (30 points/100 points)
– Linear regression & ANOVA
– Logistic Regression
– LDA
– outputs and comments; Okay
– variable selection; involved but not thorough and accurate -1.5
– no validation or cross-validation; -3
– model performance; commented on R^2 but all quite small (< 1%) - summary of comparisons on model results; the choice of the optimal model; -2 * a write-up of your findings and implications, and provide references (if any) (25 points/100 points) Okay.