Spurious correlation #3,176 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Associates degrees awarded in Management information systems and the second variable is Burglaries in Rhode Island. The chart goes from 2011 to 2021, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Associates degrees awarded in Management information systems and the second variable is Burglaries in Rhode Island. The chart goes from 2011 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the number of MIS professionals declined, so did the opportunities for cybercrime. It seems the real formula for success was to reduce those tech-savvy individuals and prevent any unauthorized data entry into homes! It's a case of 'breaking in' to a new career or just 'password' on the opportunity for thieves!

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image that seems like a scene from 'Star Wars': In a bustling classroom, a group of students proudly holds up their newly awarded Associates degrees in Management Information Systems. Meanwhile, outside a row of houses in Rhode Island, a burglar, equipped with high-tech gear, scratches their head in confusion as they are unable to break into any homes due to the lack of skilled hackers to help them. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.

This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: Associates degrees awarded in Management information systems and Burglaries in Rhode Island. Given these, which of the following image style descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand. Please respond with only one of the following potential descriptions: Sci-fi fantacy 3D Pixar Style An image that looks like it is a scene from 'Star Wars' Minimalism A scene from Skyrim
ChatGPT: An image that looks like it is a scene from 'Star Wars'

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Associates degrees awarded in Management information systems and Burglaries in Rhode Island, in the following situation: As the number of MIS degrees decreased, so did the expertise in hacking systems. Without skilled hackers, burglaries in Rhode Island saw a decrease as well, leaving the criminals "locked out" of their usual tech-savvy antics.. Keep the description simple.
ChatGPT: In a bustling classroom, a group of students proudly holds up their newly awarded Associates degrees in Management Information Systems. Meanwhile, outside a row of houses in Rhode Island, a burglar, equipped with high-tech gear, scratches their head in confusion as they are unable to break into any homes due to the lack of skilled hackers to help them.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ An image that looks like it is a scene from 'Star Wars' ] and depicting this scene: In a bustling classroom, a group of students proudly holds up their newly awarded Associates degrees in Management Information Systems. Meanwhile, outside a row of houses in Rhode Island, a burglar, equipped with high-tech gear, scratches their head in confusion as they are unable to break into any homes due to the lack of skilled hackers to help them. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image that seems like a scene from 'Star Wars': In a bustling classroom, a group of students proudly holds up their newly awarded Associates degrees in Management Information Systems. Meanwhile, outside a row of houses in Rhode Island, a burglar, equipped with high-tech gear, scratches their head in confusion as they are unable to break into any homes due to the lack of skilled hackers to help them.

*Variations in the User Prompts from chart to chart are just the result of random number generation in Python. I wrote a few arrays of various styles and methods to ask questions to change up the results. Every time this site writes an explanation or generates an image, the script picks from each at random.

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.
^{Show prompt for explanation} Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how a decrease in Associates degrees awarded in Management information systems caused Burglaries in Rhode Island to decrease. Include one good pun.

AI academic paper

(Because p < 0.01)

Associates in Advancement: Exploring the Link Between Management Information Systems and Mischief Missed

The Journal of Prankology and Information Systems

Jan 2024

Reminder: This paper is AI-generated. Not real!

^{Show prompt used to generate this paper} Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the discussion section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the discussion section of an academic research paper presenting the findings of the connection between Associates degrees awarded in Management information systems and Burglaries in Rhode Island. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

Here are the title, abstract, literature review, and results sections. Please harken back to 1-2 of the goofy items in the literature review, but pretend to take them completely seriously. Discuss how your results supported the prior research.

Do not write a conclusion. I will add a conclusion after this.

[[TITLE]]
Associates in Advancement: Exploring the Link Between Management Information Systems and Mischief Missed

[[ABSTRACT]]
In this study, we delved into the seemingly unlikely correlation between the number of Associates degrees awarded in Management Information Systems and the incidence of burglaries in the charming state of Rhode Island. Our research team meticulously analyzed data from the National Center for Education Statistics and the FBI Criminal Justice Information Services to unravel this enigmatic connection. To our surprise, we uncovered a correlation coefficient of 0.9478559, with a statistically significant p-value of less than 0.01 for the years 2011 to 2021. These findings suggest a noteworthy correlation between the educational pursuits in managing information and the mishaps of miscreants. Our research not only sheds light on this unconventional association but also raises intriguing questions about the impact of academic achievements on illicit activities.

[[LITERATURE REVIEW]]
The investigation into the seemingly peculiar connection between Associates degrees awarded in Management Information Systems (MIS) and burglaries in Rhode Island has prompted an examination of existing literature on related topics. In "The Impact of Education on Criminal Behavior," Smith et al. explore the influence of educational pursuits on involvement in illicit activities. Similarly, Doe's study, "Educational Attainment and Criminal Behavior," provides insights into the potential correlations between academic achievements and misdemeanors. Additionally, Jones' work, "Exploring the Role of Technology Education in Society," sheds light on the broader implications of technological education on societal behaviors.
Turning to non-fiction literature, works such as "Data Analytics in Crime Prevention" and "Criminal Minds: Understanding the Psychology of Offenders" offer valuable perspectives on the intersection of technology education and criminal activities. Furthermore, fictional narratives such as "The Codebreaker's Dilemma" and "Cyber Sleuth Chronicles" provide imaginative glimpses into the potential ramifications of information systems expertise on unlawful endeavors.
As the examination of the literature progressed, the research team also ventured into unexpected sources of insight. While traditional research databases yielded valuable scholarly publications, the authors found themselves perusing unconventional repositories of knowledge, including the backs of cereal boxes, fortune cookies, and even the labels of household cleaning products. While these unconventional sources did not provide scholarly citations, they did offer a refreshing perspective on the intersection of educational pursuits and mischievous behaviors, albeit in a rather unconventional manner.
The diverse array of literature consulted throughout this review has served to provide a comprehensive foundation for understanding the potential link between the attainment of Associates degrees in Management Information Systems and the occurrences of burglaries in Rhode Island. While some sources have provided rigorous empirical evidence, others have offered imaginative speculation, and still, others have inspired a lighthearted approach to this intriguing research endeavor.
Now, with the backdrop of literary insights laid before us, let us delve into the empirical findings that will shed light on the fascinating correlation awaiting discovery. Get ready to embark on a whimsical journey through the world of academia and mischief, where the unexpected awaits at every turn!

[[RESULTS]]
Our investigation into the connection between Associates degrees awarded in Management Information Systems (MIS) and the occurrence of burglaries in Rhode Island yielded some remarkably intriguing results. The data, spanning from 2011 to 2021, revealed a striking correlation coefficient of 0.9478559. This correlation coefficient, often referred to as "r," indicates a strong positive linear relationship between the number of MIS degrees and the incidence of burglaries.
Furthermore, the coefficient of determination, denoted as r-squared, was calculated to be 0.8984308. This value suggests that approximately 89.84% of the variation in burglary rates can be explained by the variation in the number of MIS degrees awarded. In other words, the pursuit of knowledge in managing information systems appears to be closely intertwined with the mischievous activities of those up to no good.
The p-value, a stalwart indicator of statistical significance, was found to be less than 0.01. This noteworthy p-value provides robust evidence to support the validity of the observed correlation. In simpler terms, the likelihood of this correlation occurring purely by chance is less than 1 in 100, or as we academics like to say, "statistically significant enough to make a scientist do a little happy dance."
Upon visual examination of the data, our team created a scatterplot (see Fig. 1) that vividly illustrates the strong positive association between the number of MIS degrees awarded and the frequency of burglaries in Rhode Island. The figure provides a compelling visual narrative of how these two seemingly disparate variables are in fact intertwined, much like the entangled lines of code in a particularly nefarious computer virus.
In summary, our findings illuminate a surprising relationship between educational pursuits in MIS and the incidence of burglaries in Rhode Island. This correlation not only challenges conventional wisdom but also underscores the intricate connections that can emerge in the complex tapestry of societal phenomena. The implications of this link between academic achievements and criminal behavior are bound to spark lively debates and potentially inspire a new wave of interdisciplinary research. After all, who knew that the study of information management could hold the key to unraveling the adventures of modern-day bandits in the Ocean State?

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of our study have revealed a striking association between the number of Associates degrees awarded in Management Information Systems (MIS) and the prevalence of burglaries in the picturesque state of Rhode Island. This unexpected correlation, with a correlation coefficient of 0.9478559 and a p-value of less than 0.01, raises intriguing questions about the underlying mechanisms linking educational pursuits in information management to illicit activities. Our findings not only support prior research examining the influence of education on criminal behavior but also provide a whimsical twist to the traditional paradigm of academic achievements.

Harkening back to the literature review, our research journey took us through a diverse array of sources, from scholarly publications to unconventional repositories of knowledge. The lighthearted approach showcased in fictional narratives such as "The Codebreaker's Dilemma" and "Cyber Sleuth Chronicles" unexpectedly resonated with the serious empirical findings of our study. Who would have thought that the comical musings found on the backs of cereal boxes and the enigmatic messages nestled within fortune cookies could offer a refreshing perspective on the intersection of academic pursuits and mischievous behaviors?

In aligning with the literature on the potential influence of education on criminal activities, our research provides empirical evidence to support the notion that academic achievements, particularly in the realm of information management, may indeed play a role in shaping societal behaviors. The correlation coefficient of 0.9478559 signifies a robust positive linear relationship between the number of MIS degrees awarded and the frequency of burglaries, illuminating the entangled nature of academic pursuits and criminal mischief.

The coefficient of determination, with a value of r-squared at 0.8984308, underscores the considerable influence of educational endeavors in MIS on the variation in burglary rates. This value serves as a quirky reminder that approximately 89.84% of the mischief in burglary rates can be attributed to the pursuit of knowledge in managing information systems - a statistic that undoubtedly prompts a raised eyebrow or two within academic circles.

The statistical significance of our findings, as evidenced by the p-value of less than 0.01, is akin to stumbling upon a rare gem in the world of statistical analysis - a delight that may even elicit a spontaneous celebratory dance from the most stoic of researchers. Our study's results not only challenge conventional wisdom but also beckon researchers to explore the uncharted territories of interdisciplinary inquiry, where the unexpected awaits at every turn.

In the grand tapestry of academic research, our study serves as a whimsical reminder that even the most improbable connections can yield remarkable insights. The link between Associates degrees in MIS and the shadowy exploits of burglars in Rhode Island stands as a testament to the uncanny interplay of academic pursuits and societal phenomena. As we conclude this discussion, we leave you with a playful nod to the unexpected twists and turns that await researchers who dare to embark on unconventional scholarly endeavors. After all, who knew that the world of academic research held such tantalizing surprises?

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the discussion section of goofy academic research papers that sounds like it belongs based on the title and abstract provided.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Associates degrees awarded in Management information systems and Burglaries in Rhode Island. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 300 tokens. At the very end, assert that no more research is needed in this area.

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Associates in Advancement: Exploring the Link Between Management Information Systems and Mischief Missed

[[ABSTRACT]]
In this study, we delved into the seemingly unlikely correlation between the number of Associates degrees awarded in Management Information Systems and the incidence of burglaries in the charming state of Rhode Island. Our research team meticulously analyzed data from the National Center for Education Statistics and the FBI Criminal Justice Information Services to unravel this enigmatic connection. To our surprise, we uncovered a correlation coefficient of 0.9478559, with a statistically significant p-value of less than 0.01 for the years 2011 to 2021. These findings suggest a noteworthy correlation between the educational pursuits in managing information and the mishaps of miscreants. Our research not only sheds light on this unconventional association but also raises intriguing questions about the impact of academic achievements on illicit activities.

[[INTRDUCTION]]
In the world of academia, researchers are often drawn to investigate the most perplexing of connections, no matter how seemingly bizarre they may be. The intersection of Management Information Systems (MIS) education and criminal activities certainly qualifies as one such enigmatic puzzle. While the pursuit of an Associates degree in MIS may appear unrelated to the mischievous machinations of burglars, our inquisitive minds have led us to delve into this unlikely correlation in the charming state of Rhode Island.
The allure of delving into this unconventional association demanded our attention, prompting us to carefully collect and analyze data from the National Center for Education Statistics and the FBI Criminal Justice Information Services. Our team of researchers, armed with statistical tools and a passion for uncovering the unexpected, embarked on a journey to unravel the mysterious link between educational advancements and the escapades of evildoers.
Now, if you'll bear with me, I promise we'll unearth some fascinating statistics that will leave you feeling like you just stumbled upon a rare gem in a field of mundane rocks. So, hold onto your lab coats and let's venture into the realm of education and crime, where numbers don't lie, but they might just crack a sly smile at the correlations they reveal!

[[RESULTS]]
Our investigation into the connection between Associates degrees awarded in Management Information Systems (MIS) and the occurrence of burglaries in Rhode Island yielded some remarkably intriguing results. The data, spanning from 2011 to 2021, revealed a striking correlation coefficient of 0.9478559. This correlation coefficient, often referred to as "r," indicates a strong positive linear relationship between the number of MIS degrees and the incidence of burglaries.
Furthermore, the coefficient of determination, denoted as r-squared, was calculated to be 0.8984308. This value suggests that approximately 89.84% of the variation in burglary rates can be explained by the variation in the number of MIS degrees awarded. In other words, the pursuit of knowledge in managing information systems appears to be closely intertwined with the mischievous activities of those up to no good.
The p-value, a stalwart indicator of statistical significance, was found to be less than 0.01. This noteworthy p-value provides robust evidence to support the validity of the observed correlation. In simpler terms, the likelihood of this correlation occurring purely by chance is less than 1 in 100, or as we academics like to say, "statistically significant enough to make a scientist do a little happy dance."
Upon visual examination of the data, our team created a scatterplot (see Fig. 1) that vividly illustrates the strong positive association between the number of MIS degrees awarded and the frequency of burglaries in Rhode Island. The figure provides a compelling visual narrative of how these two seemingly disparate variables are in fact intertwined, much like the entangled lines of code in a particularly nefarious computer virus.
In summary, our findings illuminate a surprising relationship between educational pursuits in MIS and the incidence of burglaries in Rhode Island. This correlation not only challenges conventional wisdom but also underscores the intricate connections that can emerge in the complex tapestry of societal phenomena. The implications of this link between academic achievements and criminal behavior are bound to spark lively debates and potentially inspire a new wave of interdisciplinary research. After all, who knew that the study of information management could hold the key to unraveling the adventures of modern-day bandits in the Ocean State?

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our investigation into the correlation between the awarding of Associates degrees in Management Information Systems (MIS) and the incidence of burglaries in Rhode Island has uncovered a rather unexpected relationship. Our results revealed a strikingly high correlation coefficient, indicating a strong positive linear relationship between these seemingly disparate variables. It seems that the pursuit of knowledge in managing information systems might just be closely intertwined with the mischievous activities of those up to no good. It's as if the burglars are attempting to "break into" the world of information management, albeit with less than honorable intentions - talk about a data breach of a different kind!

The statistically significant p-value further supports the validity of our findings, leaving little room to attribute this correlation to chance. As we dive deeper into the statistical sea, it becomes increasingly clear that the link between educational pursuits in MIS and burglary rates is no mere coincidence. It appears that these two realms, one of academic advancement and the other of illicit activities, have found themselves tangled in an intricate web of statistical connection, much like a sneaky algorithm hidden within a labyrinth of code.

Our study not only sheds light on this curious correlation but also launches a fruitful discussion within the scientific community. The implications of this unexpected relationship between academic achievements and criminal behavior are bound to intrigue researchers from diverse fields. It seems that there is more to the world of information management than meets the eye, and perhaps, in unraveling the mysteries of MIS, we have unearthed a hidden connection to the adventures of modern-day bandits in the Ocean State. Who knew that unraveling the mysteries of academic pursuits could help us understand the escapades of mischief makers?

In light of these compelling findings, it is safe to say that further research in this area may not yield as much value as one might hope. Sometimes, a statistical anomaly such as this one is best left as a quirky quirk of the scientific world, a charming statistical oddity that reminds us that the universe is full of delightful surprises. As the curtain falls on this particular exploration, we can take solace in the fact that our scholarly pursuit has uncovered a correlation that is as intriguing as it is unexpected. So, let's raise a toast to the curious connections that science continues to unveil, and embrace the baffling beauty of statistical serendipity.

No more research needed in this area - it's time for these findings to safely reside in the annals of quirky statistical oddities!

Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of academic journals. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding research, scientific, or academic journal that would publish a paper entited Associates in Advancement: Exploring the Link Between Management Information Systems and Mischief Missed. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Prankology and Information Systems

Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited Associates in Advancement: Exploring the Link Between Management Information Systems and Mischief Missed. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Management Information Systems and Social Shenanigans

Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Associates in Advancement: Exploring the Link Between Management Information Systems and Mischief Missed with an abstract of In this study, we delved into the seemingly unlikely correlation between the number of Associates degrees awarded in Management Information Systems and the incidence of burglaries in the charming state of Rhode Island. Our research team meticulously analyzed data from the National Center for Education Statistics and the FBI Criminal Justice Information Services to unravel this enigmatic connection. To our surprise, we uncovered a correlation coefficient of 0.9478559, with a statistically significant p-value of less than 0.01 for the years 2011 to 2021. These findings suggest a noteworthy correlation between the educational pursuits in managing information and the mishaps of miscreants. Our research not only sheds light on this unconventional association but also raises intriguing questions about the impact of academic achievements on illicit activities.

ChatGPT:

Associates degrees, Management Information Systems, Rhode Island, burglaries, correlation, National Center for Education Statistics, FBI, criminal activities, academic achievements, educational pursuits, statistics, correlation coefficient, p-value

*There is a bunch of Python happening behind the scenes to turn this prompt sequence into a PDF.

Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error

Data details

Associates degrees awarded in Management information systems
Detailed data title: Associate's degrees conferred by postsecondary institutions with a field of study of Management information systems and services
Source: National Center for Education Statistics
See what else correlates with Associates degrees awarded in Management information systems

Burglaries in Rhode Island
Detailed data title: The burglary rate per 100,000 residents in Rhode Island
Source: FBI Criminal Justice Information Services
See what else correlates with Burglaries in Rhode Island

Correlation r = 0.9478559 (Pearson correlation coefficient)
Correlation is a measure of how much the variables move together. If it is 0.99, when one goes up the other goes up. If it is 0.02, the connection is very weak or non-existent. If it is -0.99, then when one goes up the other goes down. If it is 1.00, you probably messed up your correlation function.

r² = 0.8984308 (Coefficient of determination)
This means 89.8% of the change in the one variable (i.e., Burglaries in Rhode Island) is predictable based on the change in the other (i.e., Associates degrees awarded in Management information systems) over the 11 years from 2011 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 9.2E-6.^Show 0.0000091641778069730560000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

But I am a p-villain. I absolutely did not test only one pair of variables one time. I correlated hundreds of millions of pairs of variables. I threw boatloads of data into an industrial-sized blender to find this correlation.

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.95 in 0.00092% of random cases. Said differently, if you correlated 109,121 random variables^Note You don't actually need 109 thousand variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

p-value calculations are useful for understanding the probability of a result happening by chance. They are most useful when used to highlight the risk of a fluke outcome. For example, if you calculate a p-value of 0.30, the risk that the result is a fluke is high. It is good to know that! But there are lots of ways to get a p-value of less than 0.01, as evidenced by this project.

In this particular case, the values are so extreme as to be meaningless. That's why no one reports p-values with specificity after they drop below 0.01.

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 10 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 10 because we have two variables measured over a period of 11 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.81, 0.99 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

This one is a bit more complciated than the other calculations, but I include it because many people have been pushing for confidence intervals instead of p-value calculations (for example: NEJM. However, if you are dredging data, you can reliably find yourself in the 5%. That's my goal!

All values for the years included above: ^Note If I were being very sneaky, I could trim years from the beginning or end of the datasets to increase the correlation on some pairs of variables. I don't do that because there are already plenty of correlations in my database without monkeying with the years.

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.

	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021
Associates degrees awarded in Management information systems (Degrees awarded)	1244	1164	1085	1176	987	935	953	921	943	854	766
Burglaries in Rhode Island (Burglary rate)	650.6	564.5	533.6	457.9	373.1	345.1	304.7	266.2	219.3	166.8	137.4

Why this works

Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
Lack of causal connection: There is probably^Note Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple^Note Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
p-value calculation does not take this into account, so mathematically it appears less probable than it really is.
Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. ^Note Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.

Try it yourself

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. ^{Show the steps to do this.} Step 1: Download and install Python on your computer.

Step 2: Open a plaintext editor like Notepad and paste the code below into it.

Step 3: Save the file as "calculate_correlation.py" in a place you will remember, like your desktop. Copy the file location to your clipboard. On Windows, you can right-click the file and click "Properties," and then copy what comes after "Location:" As an example, on my computer the location is "C:\Users\tyler\Desktop"

Step 4: Open a command line window. For example, by pressing start and typing "cmd" and them pressing enter.

Step 5: Install the required modules by typing "pip install numpy", then pressing enter, then typing "pip install scipy", then pressing enter.

Step 6: Navigate to the location where you saved the Python file by using the "cd" command. For example, I would type "cd C:\Users\tyler\Desktop" and push enter.

Step 7: Run the Python script by typing "python calculate_correlation.py"

If you run into any issues, I suggest asking ChatGPT to walk you through installing Python and running the code below on your system. Try this question:

"Walk me through installing Python on my computer to run a script that uses scipy and numpy. Go step-by-step and ask me to confirm before moving on. Start by asking me questions about my operating system so that you know how to proceed. Assume I want the simplest installation with the latest version of Python and that I do not currently have any of the necessary elements installed. Remember to only give me one step per response and confirm I have done it before proceeding."

# These modules make it easier to perform the calculation
import numpy as np
from scipy import stats

# We'll define a function that we can call to return the correlation calculations
def calculate_correlation(array1, array2):

    # Calculate Pearson correlation coefficient and p-value
    correlation, p_value = stats.pearsonr(array1, array2)

    # Calculate R-squared as the square of the correlation coefficient
    r_squared = correlation**2

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([1244,1164,1085,1176,987,935,953,921,943,854,766,])
array_2 = np.array([650.6,564.5,533.6,457.9,373.1,345.1,304.7,266.2,219.3,166.8,137.4,])
array_1_name = "Associates degrees awarded in Management information systems"
array_2_name = "Burglaries in Rhode Island"

# Perform the calculation
print(f"Calculating the correlation between {array_1_name} and {array_2_name}...")
correlation, r_squared, p_value = calculate_correlation(array_1, array_2)

# Print the results
print("Correlation Coefficient:", correlation)
print("R-squared:", r_squared)
print("P-value:", p_value)

Reuseable content

You may re-use the images on this page for any purpose, even commercial purposes, without asking for permission. The only requirement is that you attribute Tyler Vigen. ^Note Attribution can take many different forms. If you leave the "tylervigen.com" link in the image, that satisfies it just fine. If you remove it and move it to a footnote, that's fine too. You can also just write "Charts courtesy of Tyler Vigen" at the bottom of an article.

You do not need to attribute "the spurious correlations website," and you don't even need to link here if you don't want to. I don't gain anything from pageviews. There are no ads on this site, there is nothing for sale, and I am not for hire.

For the record, I am just one person. Tyler Vigen, he/him/his. I do have degrees, but they should not go after my name unless you want to annoy my wife. If that is your goal, then go ahead and cite me as "Tyler Vigen, A.A. A.A.S. B.A. J.D." Otherwise it is just "Tyler Vigen."

When spoken, my last name is pronounced "vegan," like I don't eat meat.

Full license details.
For more on re-use permissions, or to get a signed release form, see tylervigen.com/permission.

Download images for these variables:

High resolution line chart ^Note The image linked here is a Scalable Vector Graphic (SVG). It is the highest resolution that is possible to achieve. It scales up beyond the size of the observable universe without pixelating. You do not need to email me asking if I have a higher resolution image. I do not. The physical limitations of our universe prevent me from providing you with an image that is any higher resolution than this one.

If you insert it into a PowerPoint presentation (a tool well-known for managing things that are the scale of the universe), you can right-click > "Ungroup" or "Create Shape" and then edit the lines and text directly. You can also change the colors this way.

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only Associates degrees awarded in Management information systems
Line chart for only Burglaries in Rhode Island
AI-generated correlation image
The spurious research paper: Associates in Advancement: Exploring the Link Between Management Information Systems and Mischief Missed

View another random correlation

How fun was this correlation?

You're the rating guru we've been waiting for!

Correlation ID: 3176 · Black Variable ID: 1216 · Red Variable ID: 20118


Problem variable:
Issue:
Additional details: Optional
Confirm you are a human: