Diogo Mesquita's Data Analytics Portfolio

Diogo Mesquita's Data Analytics Portfolio

Diogo Mesquita

Throughout the Data Analytics Program, students are asked to imagine themselves as analysts for various imaginary companies. Below is Diogo’s descriptive analysis of staffing during a US flu pandemic.

Hi Diogo! What inspired you to make a career change into data analytics? 

Data analysis is a great skill to complement my career as an economist and a social scientist. Great strides are being made due to our expanding capacity to analyse data. I didn’t want to miss the train! 

What did you enjoy most about the program?

The motivation that comes from advancing from achievement to achievement. I also liked the convenience of managing your time and going at your own pace. It was so cool to start thinking about all the amazing things I could do with data!

Talk us through this portfolio project. 

I really enjoyed deepening my understanding of a natural phenomena like the flu by analyzing the underlying data. It was a great way to hone my new skills. 

 

Contents:

  1. Project goals 
  2. Defining the research questions and hypothesis 
  3. Sourcing and preparing the data 
  4. Statistical and visual analysis 
  5. Results

 

1. Project goals 

Project motivation

The United States has an influenza season where more people than usual suffer from the flu. Some people, particularly in vulnerable population, develop serious health complications and end up in hospital. Hospitals and clinics need additional staff to adequately treat these extra patients. The medical staffing agency provides this temporary staff. 

Objective

Determine when to send staff, and how many, to each state. 

Scope

The agency covers all hospitals in each of the 50 states of the United States, and the project will plan for the upcoming influenza season.

 

 2. Defining the research questions and hypothesis

Clarifying questions:
  1. Which states are most affected by influenza?
  2. When is flu season?
  3. Which states have the most residents in vulnerable populations?
Funneling questions:
  1. (relative to B) Is flu season the same in every state?
  2. (relative to B) Is flu season the same length every year?
  3. (relative to B) Is flu season only once a year?”
Defining hypothesis: 

If a state has a larger proportion of vulnerable population, then more deaths from flu will occur. 

 

3. Sourcing and preparing the data

Influenza deaths by geography, time, age, and gender Source: CDC

Population data by geography Source: US Census Bureau

In Excel, the data was

  • Cleaned
  • Transformed
  • Integrated
  • Summarized

 

4. Statistical and visual analysis

Tools:
  • Excel
  • Tableau
Summary: 
  • Correlation analysis and statistical test did not support initial hypothesis 
  • Correlation and visual analysis of various variables took us to new conclusions

 

 5. Results

Initial questions:
Clarifying questions:
  1. Which states are most affected by influenza?
  2. When is flu season?
  3. Which states have the most residents in vulnerable populations?
Funneling questions:
  1. (relative to B) Is flu season the same in every state?
  2. (relative to B) Is flu season the same length every year?
  3. (relative to B) Is flu season only once a year?”
Conclusion

The data shows that states with more population, and therefore more vulnerable population, have more deaths due to the flu. Vulnerable populations suffer the most severe impacts from the flu and are the most likely to end up in the hospital, determining the need for increased medical personnel. 

The flu season in the USA is from November to May. The precise timing and severity varies between states. 

Recommendations 

Send staff to the different states, taking into consideration the size of the population, the size of the vulnerable populations, as well as the forecast of the timing and severity of the flu season for each state. 

Click here to view the full Tableau presentation for Diogo’s project. 

Other Portfolios