Analytical Insights in Analysis

OVERVIEW
The purpose of this assignment is to practice gaining analytical insights into a dataset by applying descriptive statistical practices. You will demonstrate your ability to communicate these findings to a non-technical audience.
INSTRUCTIONS

1. Find a data set of interest to you for analysis. There are many free datasets available that can be discovered with an internet search. Some datasets are very large. Choose one that can be easily accommodated in Excel or choose a relevant portion of data to consider. It is recommended that your data include at least three quantitative variables and three categorical variables.
2. Develop an executive summary, detailing the purpose of the data and results of your statistical analysis (Step #3 of the instructions). As you explore the data, you may discover certain findings of interest. Be sure to detail these as well as potential business problems these findings could address. Typically, we would start with the business problem, but for the purpose of this project, you will focus largely on data exploration.
3. Explore the data and provide the following, as appropriate:
   a. Data preparation activities
   i. If a sample was chosen, describe the selection process
   ii. Reformatting of data to allow for analysis
   iii. Identification of outliers and/or missing data

b. Metadata for each field, including, but not limited to:
i. Type of data (categorical, quantitative, etc.)
ii. Use of dummy variables (i.e. 1=male, 2=female)
iii. Notes for fields that may be unclear from field name alone

c. Analysis of chosen variables. It is not necessary to analyze all variables, especially if you have many columns of data, but at least three variables must be explored. Consider the following in your analysis, as appropriate for the chosen data:
i. Basic descriptive statistics (mean, standard deviation, range, variance, etc.)
ii. A frequency distribution
iii. Percentile or Quartile information

d. Charts: include at least 3 charts. You must include:
i. A scatter chart (two numerical variables that may have a relationship)
ii. A histogram showing the distribution of one variable
iii. A third chart of your choosing

e. A hypothesis test of your choosing. To test the hypothesis, you can locate a second source of the same type of data and compare (i.e. is the mean of your sample significantly different from the second source?). If you cannot find a second source, you can split your data into two or create your own randomized data to test against.
Deliverable
Assume that you are speaking to a bright, but non-technical audience who will require an explanation of your analysis. The text of your final project must exceed 750 words (3 pages). Use APA format and include a reference to your data source(s) as available.
You will submit:

1. An informative summary of your dataset and analysis. There is no exact page requirement as you will likely have many figures, tables, graphs, etc. However, it is expected that with narrative and figures combined, the project will easily exceed 5 pages. As organization is a key component, you must make use of sectioning/headers in your project. Include the following sections: Executive Summary, Data Preparation, Metadata, Analysis of Data, Hypothesis Test, and Conclusion. The charts may be placed in their own section or weaved throughout the project as appropriate. An appendix or table of contents may be used. Do not leave figures, tables, and charts unexplained.
2. Excel Data file. Along with your written summary, you must submit the data used for your analysis in an Excel file. It should be clear which part of the file represents the original data and which your modifications/additions are. This can be done by having two copies of the data in the file on separate worksheets – (1) being the original from the data source and (2) being a copy of the data where you have performed any cleaning, manipulation, addition of formulas, etc. Additional worksheets in the file can be used to display any tables, pivot tables, statistical summaries, etc. Label your worksheet tabs clearly and modify the tab colors to clearly identify your efforts.