Analysis and visualization of suicide rate in the United States

Wendy Yu
Posted on Mar 3, 2016

Contributed by Wendy Yu. She is currently in the NYC Data Science Academy 12 week full time Data Science Bootcamp program taking place between January 11th to April 1st, 2016. This post is based on her first project - R Visualization.(due on 2th week)


Every year, there are more then 800,000 people who take their own life, not including attempts. In other words, there is one suicide every 40 seconds. Suicides happen globally across all ages and genders with different rates. In the United States, it is the second leading cause of death for people aged 15-29, and the tenth leading cause of death across all ages. Suicide is a serious problem worldwide, but it is the most preventable when comparing to other leading causes of death. The first-ever Mental Health Action Plan of the World Health Organization was conducted in May 2013. The goal is to reduce the suicide rate by 10% by 2020.

Here, I analyzed suicide rates in the United States and across the world. The goal is to provide insights into this topic and hope this data can be used to prevent suicides in the future.leading_causes_of_death_by_age_group_2013

The Geography of Suicide

fig 1

Screen Shot 2016-03-03 at 4.57.22 PM

fig 2

fig 3

Who is at risk?

  • People age 15-29 have the highest risk of committing suicide.
  • More men commit suicide then women of all ages.

fig 4

What factors influence suicide behavior?

People choose to end their lives for complex reasons. It is difficult to pin down the cause of suicide. Commonly cited reasons include:
* Life history: traumatic experience during childhood, and sexual/physical abuse.
* Life style: alcohol or drug abuse.
* Life event: loss of loved ones or loss of income.
* Mental heath: depression or schizophrenia
Here I explored a few factors that I think would impact suicide rate.


My analysis focuses on how unemployment rate impacts suicide rate. The trend of unemployment and suicide rates are illustrated in the left figure below. Suicide rate showed here is the number of people committing suicide in every 100,000 people. The unemployment rate is the percentage of the labor force aged 16 and older. In the figure we can see the two variables show similar trends, especially between 1995 and 2005. There is a significant decrease in both suicide rate and unemployment percentage from 1995 to 2000, following by an increase in both variables. We also observe the two near parallel regression lines, suggesting a strong correlation between the two variables. To further examine the correlation, we plot the figure on the right, demonstrating a strong positive linear relationship between unemployment rate and suicide rate.

fig 5

The figures above demonstrate the relationship between unemployment and suicide rates over time. Another way to analyze this relationship is to examine it state by state. The figure below shows the correlation between unemployment rate and suicide rates by states in 2013. Interestingly, the result suggests the opposite from the above figure. We see a negative linear relationship. One of the explanations is that 2013 could be the outlier of the trend established from the above figure. Other possibility is that the trend changes after 2005. Since the figure below uses data from 2013, it wouldn’t fit in the trend established from 1995 to 2005.

From our analysis, we can conclude that there is a positive relationship between unemployment rate and suicide rate between 1995 and 2005. The trends of the two variables after 2005 remain unclear from this analysis.

fig 6

School Enrollment

The theory is that students who drop out of school are likely to be experiencing negative life events, which could make them more vulnerable to commit suicide. This analysis explores the relationship between school enrollment rate and suicide rate. School enrollment rate showed here is the percentage of total population aged 3 years old and above who are enrolled in school. From the left figure we see a negative trend between the two variables. The suicide rate decreases as school enrollment rate increase between year 1999 and 2013. We further analyze the correlation between the two variables (right figure) and indeed there is a strong negative linear relationship.

fig 7

Alcohol Consumption

Alcohol consumption and suicide rate seem to have a close relationship. Even though alcohol consumption might not be causal, it tends to give user the mindset to commit suicide. This analysis examines the relationship between alcohol consumption and suicide rate across states. Alcohol consumption used in this dataset is any alcohol use, meaning one or more drinks during the last 30 days of the survey. The result surprisingly shows the opposite as our assumption. The graph demonstrates a negative linear relationship between alcohol consumption and suicide rate. However, the data points are sparse and the variance explained is also very small. The correlation is weak therefore the relationship between the two remains inconclusive.

fig 8

Correlation does not imply causation

From the analysis above, we see strong correlations between suicide rate and some factors, which may contribute to suicide rate. However, one thing that is very important to keep in mind is that correlation doesn't imply causation. For example, we concluded that people who are unemployed are at higher risk for committing suicide, but we cannot say unemployment is what caused suicide. As data scientists, we should be careful not to use correlation as the basis of a hypothesis for a causal relationship. As an example, we examine the relationship between cheese consumption and suicide rate. The results suggest that increased American cheese consumption will lead to higher suicide rate, and increased cottage cheese consumption will lower suicide rate. We observe the relationship between cheese consumption and suicide rate; however, we are missing the factor or factors linking the two variables and cannot say American cheese consumption causes suicide. No matter how strong the correlation is, it doesn't imply causation.

fig 9


Suicide is an escalating problem, and it is preventable. Analysis from this report provides an insight to suicide behavior. We found that

  1. Men have a higher risk of committing suicide then women.
  2. Young people between 15-29 are at the highest risk among all age groups.
  3. People who are unemployed are at high risk of committing suicide.
  4. People who drop out of school are at high risk of committing suicide.

I hope that the above finding can be useful for developing suicide prevention strategy.


  1. Mortality due to self-inflicted injury, per 100 000 standard population, age adjusted. WHO Global Burden of Disease.
  2. Mortality and global health estimate cause of heath. WHO Global Health Observatory data repository.
  3. Unemployment Rates for States Annual Average Rankings Year: 2013. Bureau of labor statistics, United States Department of Labor.
  4. CPS Historical Time Series Tables on School Enrollment. United States Census Bureau.
  5. State-Specific Alcohol Consumption Rates for 2013. Center of Disease Control and Prevention.
  6. Dairy products: Per capita consumption, United States (Annual). United States Agriculture Economic Research Service.

[contact-form to='[email protected]'][contact-field label='Name' type='name' required='1'/][contact-field label='Email' type='email' required='1'/][contact-field label='Website' type='url'/][contact-field label='Comment' type='textarea' required='1'/][/contact-form]

About Author

Wendy Yu

Wendy Yu

As a biologist, Wendy believes in evidence-base analysis, and is passionate about data. Wendy graduated from the University of Pennsylvania in 2013 with a Masters in Biotechnology. While pursuing a career as a biologist Wendy quickly realized that...
View all posts by Wendy Yu >

Related Articles

Leave a Comment

No comments found.

View Posts by Categories

Our Recent Popular Posts

View Posts by Tags

#python #trainwithnycdsa 2019 airbnb Alex Baransky alumni Alumni Interview Alumni Reviews Alumni Spotlight alumni story Alumnus API Application artist aws beautiful soup Best Bootcamp Best Data Science 2019 Best Data Science Bootcamp Best Data Science Bootcamp 2020 Best Ranked Big Data Book Launch Book-Signing bootcamp Bootcamp Alumni Bootcamp Prep Bundles California Cancer Research capstone Career Career Day citibike clustering Coding Course Demo Course Report D3.js data Data Analyst data science Data Science Academy Data Science Bootcamp Data science jobs Data Science Reviews Data Scientist Data Scientist Jobs data visualization Deep Learning Demo Day Discount dplyr employer networking feature engineering Finance Financial Data Science Flask gbm Get Hired ggplot2 googleVis Hadoop higgs boson Hiring hiring partner events Hiring Partners Industry Experts Instructor Blog Instructor Interview Job Job Placement Jobs Jon Krohn JP Morgan Chase Kaggle Kickstarter lasso regression Lead Data Scienctist Lead Data Scientist leaflet linear regression Logistic Regression machine learning Maps matplotlib Medical Research Meet the team meetup Networking neural network Neural networks New Courses nlp NYC NYC Data Science nyc data science academy NYC Open Data NYCDSA NYCDSA Alumni Online Online Bootcamp Online Training Open Data painter pandas Part-time Portfolio Development prediction Prework Programming PwC python Python Data Analysis python machine learning python scrapy python web scraping python webscraping Python Workshop R R language R Programming R Shiny r studio R Visualization R Workshop R-bloggers random forest Ranking recommendation recommendation system regression Remote remote data science bootcamp Scrapy scrapy visualization seaborn Selenium sentiment analysis Shiny Shiny Dashboard Spark Special Special Summer Sports statistics streaming Student Interview Student Showcase SVM Switchup Tableau team TensorFlow Testimonial tf-idf Top Data Science Bootcamp twitter visualization web scraping Weekend Course What to expect word cloud word2vec XGBoost yelp