Descriptive statistics about the data

Over the past four weeks you’ve covered a lot of material! You’re well on your way to becoming a data scientist. To recap the content so far, you have:  

· Received a quick introduction to the data science workflow, including exploration, visualization, statistics, and machine learning

 Gotten hands-on experience with analyzing data in Excel

 

· Learned about dashboards and reports in Power BI

 

· Discovered how to use key storytelling principles to generate high impact with data  

 

This is the first project that you will complete through the boot-camp. These projects both provide you with hands-on experience and can serve as the start of your data science portfolio!  

 

For the first project, you are going to be developing an exploratory data analysis report. You can choose to use either Excel or Power BI. The overall goal is to produce a report that  

 

1. Highlights at least one interesting aspect of the data, and

 

2. Allows a reader to interactively explore other aspects of the data  

 

Concepts covered:  

 

· Exploratory data analysis

 

· Analytics storytelling

 

· Basic data analysis and visualization in Excel and/or Power BI  

 

The Dataset

 

 

 

The dataset we’ll be using is about workplace fatalities. It can be found  here . Within this dataset you’ll find data points on fatalities, injuries, inspections, and penalties for each state in the US for the year 2012.

 

Requirements

 

Your report will be evaluated on how well it meets the following criteria:  

 

1. Summarizes descriptive statistics about the data, including at least one descriptive visualization, such as a box-and-whisker plot or histogram displaying the distribution of a variable

 

2. Contains an interactive element that lets a user cut into the data, e.g., an Excel pivot table with slicers

 

3. Generates interesting questions about the data and explores those questions with two or more visualizations that highlight an insight about the data, possibly applying transformations to the data. For example, a scatter or line plot showing the relationship between two variables.

 

4. Effectively uses of analytical storytelling to convey insight(s), including good practices for visualizations  

 

As part of these criteria, your report should answer  at least the following questions:  

 

· Which program, state or federal, has the highest rate of fatalities?

 

· Which state with a state program has the highest number of injuries/illnesses?

 

· What is the relationship, if any, between “Average of Years to Inspect Each Workplace Once” and “Rate of Fatalities”?

 

Submission

 

When you have completed the project, upload following deliverables under project subsmission section.  

 

1. A Power BI report. You must send an actual file, not publish a Power BI report to the web and send a link.

 

2. A document (Word file, PDF, or plain text) containing:  

 

· Details on the questions explored, insights highlighted, and functionality provided by your project

 

· Information about which Excel/Power BI features were used

 

· What information from the Analytics Storytelling course you applied

 

· Ideas for future improvement of your project (minimum of 3)