Correlation, causation, and association – What does it all mean???

A comment posted by a reader on a post reprimanded me for suggesting that marijuana caused relationships to go bad.

In this instance the reader was mistaken, as I had specifically used the word “associated”, but the comment made me think that maybe I should explain the differences between correlation, causation, and association. I’m a scientist studying addiction, and in the field, it’s very important to be clear about what each of the words you use means.

Being clear about inferences in research

Correlation – When researchers find a correlation, which can also be called an association, what they are saying is that they found a relationship between two, or more, variables. For instance, in the case of the marijuana post, the researchers found an association between using marijuana as a teen, and having more troublesome relationships in mid, to late, twenties.

Correlations can be positive – so that as one variable (marijuana smoking) goes up, so does the other (relationship trouble); or they can be negative, which would mean that as one variable goes up (methamphetamine smoking) another goes down (grade point average).

The trouble is that, unless they are properly controlled for, there could be other variables affecting this relationship that the researchers don’t know about. For instance, education, gender, and mental health issues could be behind the marijuana-relationship association (these variables were all controlled for by the researchers in that study). Researchers have at their disposal a number of sophisticated statistical tools to control for these, ranging from the relatively simple (like multiple regression) to the highly complex and involved (multi-level modeling and structural equation modeling). These methods allow researchers to separate the effect of one variable from others, thereby leaving them more confident in making assertions about the true nature of the relationships they found. Still, even under the best analysis circumstances, correlation is not the same as causation.

Causation – When an article says that causation was found, this means that the researchers found that changes in one variable they measured directly caused changes in the other. An example would be research showing that jumping of a cliff directly causes great physical damage. In order to do this, researchers would need to assign people to jump off a cliff (versus lets say jumping off of a 12 inch ledge) and measure the amount of physical damage caused. When they find that jumping off the cliff causes more damage, they can assert causality. Good luck recruiting for that study!

Most of the research you read about indicates a correlation between variables, not causation. You can find the key words by carefully reading. If the article says something like “men were found to have,” or “women were more likely to,” they’re talking about associations, not causation.

Why the correlation-causation difference?

The reason is that in order to actually be able to claim causation, the researchers have to split the participants into different groups, and randomly assign some to the behavior or condition they want to study (like taking a new drug), while the rest receive something else. This is in fact what happens in clinical trials of medication because the FDA requires proof that the medication actually makes people better (more so than a placebo). It’s this random assignment to conditions (or randomization) that makes experiments suitable for the discovery of causality. Unlike in association studies, random assignment assures (if everything is designed correctly) that its the behavior being studied, and not some other random effect, that is causing the outcome.

Obviously, it is much more difficult to prove causation than it is to prove an association.

Should we just ignore associations?

No! Not at all!!! Not even close!!! Correlations are crucial for research and still need to be looked at and studied, especially in some areas of research like addiction.

The reason is simple – We can’t randomly give people drugs like methamphetamine as children and study their brain development to see how the stuff affects them, that would be unethical. So what we’re left with is a the study of what meth use (and use of other drugs) is associated with. It’s for this reason that researchers use special statistical methods to assess associations, making certain that they are also considering other things that may be interfering with their results.

In the case of the marijuana article, the researchers ruled out a number of other interfering variables known to affect relationships, like aggression, gender, education, closeness with other family members, etc. By doing so, they did their best to assure that the association found between marijuana and relationship status was real. Obviously other possibilities exist, but as more researchers assess this relationship in different ways, we’ll learn more about its true nature.

This is how research works.

It’s also how we found out that smoking causes cancer. Through endlessly repeated findings showing an association. That turned out pretty well, I think…

The placebo effect: So strong, doctors don’t even have to lie!

Almost everyone has heard about the placebo effect – the finding that treatment that have no particularly relevant effect (like a sugar or vitamin pill, or a behavioral equivalent) can make patients feel better. The placebo effect is actually the reason that all FDA approved drugs have to go through a double-blind placebo-controlled clinical trial before being approved for use – It has to be shown that using a specific medication is more beneficial than a non-active placebo even when the experimenter (or doctors) and the patient have no idea which treatment the patients are receiving. Otherwise, companies could simply continuously create placebos, show that they produce improvements in patients, and bring in the dollars.

Until now, it’s been assumed that in order for placebos to work, the patients have to be told that they are effective medications, amounting to an unethical lie by the doctors that prescribe them. This is the reason that very few doctors use pure placebos, though in a recent survey more than 50% of doctors reported using mild prescriptions (like over-the-counter pain medications) that they don’t believe are actually relevant to the condition as “impure placebos.” Given the large placebo effect, we can expect that these treatment, even if unethical, resulted in significant improvements in conditions that those same doctors were unable to treat using conventional methods. Still, it doesn’t feel good to know your doctors have to lie to you to make you feel better, right? Well they might not have to.

This fake placebo pill might make you feel better

A very recent study conducted at Harvard and published in the journal PLoS One examined whether placebos would still work for irritable bowel syndrome (IBS) patients even if they were explicitly told that the pills were inactive. The 80 IBS patients were randomly selected to receive either no treatment (the control condition) or a pill they were told was inactive “like a sugar pill” without any medication in it. Patients in the placebo condition were also told about the placebo effect and that such inactive sugar pills have been shown to produce significant mind-body self-healing processes. The placebo pills were marked with clear labels that read “placebo pills” so that there would be no confusion and so that patients would be constantly reminded that they pills they were taking were placebo pills 2 times a day. Amazingly, the placebo effect was still found to be present.

At the end of 3 weeks of treatment, participants in the placebo group reported significantly greater improvement in their symptoms on a number of different scales used for IBS as well as an overall Quality of Life measure. Even more amazingly, nearly twice as many patients in the placebo condition (59% versus 35%) reported that the treatment gave them “adequate relief” from their IBS symptoms!!! Patients got better taking pills that did nothing even though they knew that the pills were completely inactive. In fact, the effect was so great it was similar to the effects commonly seen with actual approved medications for IBS.

Conclusion and implications

Overall, these findings are encouraging on a number of fronts: If confirmed by future studies and using other conditions, these results suggest that doctors don’t have to lie to their patients since the placebo effect is strong enough to work even when patients are aware of it as long as the person giving the treatment is trusted. In fact, even this last piece should probably be put to the test since as far as I know, it has never been put to the test itself. Still, there is a whole body of literature in psychology telling us that when people of authority, people we respect, tell us to do something we react favorably.

Unfortunately, this has resulted in some pretty disturbing results including Stanley Milgram’s 1960s studies that revealed the power of authority in directing people to harm others (if you’ve never looked into these experiments you really should – here’s a video link to get you started). However, this time the results suggest that doctors may be able to help patients for whom there is no specific approved treatment. Obviously this is of interest to me because of the relatively low success in clinical addiction treatment. It may actually also suggest that a number of the treatments we’re using now – especially those that have never been subjected to a Randomized Placebo-Controlled Clinical Trial – may in fact simply be placebos. I have my own sneaking suspicions about some specific treatments…

Like every other study, this one is not without limitations. First of all, these results have to be replicated with other conditions and in other hospitals with other patients before doctors should feel comfortable simply prescribing placebos. There could be specific aspects of this sample that made the results so convincing. Indeed, even the no treatment condition got some benefit from their interaction with the medical and research staff involved in the study (or maybe just due to the passage of time). It’s as if we are now comparing the placebo effect to the time/human-interaction effect, gradually making our way towards some “no-effect” condition.  We also want to see these sort of results with a larger sample, and although conducting a double-blind trial isn’t possible (one group takes pills and the other doesn’t so everyone knows who is in what condition), I’m certain that future experiment will figure out more subtle controls.

Still, this study definitely indicates that giving placebos openly can work for patients who are open to it. It should also make everyone aware that just because someone tells you a treatment is objectively helpful doesn’t mean it is. In the end though, if the psychological placebo effect brings about actual improvement in symptoms, shouldn’t we consider it effective?


Ted J. Kaptchuk, Elizabeth Friedlander, John M. Kelley, M. Norma Sanchez, Efi Kokkotou, Joyce P. Singer, Magda Kowalczykowski, Franklin G. Miller, Irving Kirsch, Anthony J. Lembo1 (2010) Placebos without deception: A randomized controlled trial in irritable bowel syndrome. PLoS One, 5,

These Fake Pills May Help You Feel Better – Science Now

Talking to NIDA about addiction research- Nicotine, cocaine, treatment matching and more

It’s not everyday that I get an invite to speak with NIDA‘s director, Dr. Nora Volkow, and so, even though it required my creative use of some VOIP technology from a living room in Tel-Aviv, I logged onto a conference call led by the leading addiction researcher. When my colleagues, Dirk Hanson and Elizabeth Hartney, were introduced, I knew I was in good company.

Addiction research directions the NIDA way

The call focused on some NIDA interests, including a nicotine vaccine, which Dr. Volkow seemed confident will triumphantly exit phase 3 trials in less than two years and potentially enter the market after FDA approval in three years or less. The vaccine, which seems to significantly and effectively increase the production of nicotine antibodies in approximately 30% of research participants, has shown promise as a tool for smoking cessation in trials showing complete cessation, or significant reduction in smoking among participants that produced sufficient antibodies. Obviously, this leaves a large gap for the 70% of participants for which the vaccine was not effective, but a good treatment for some is much better than no treatment for all. For more on the vaccine, check out Mr. Hanson’s post here.

Aside from the nicotine vaccine (and on a similarly conceived cocaine vaccine), our conversation centered on issues relevant to the suggested new DSM-5 alterations in addiction-related classifications. Dr. Volkow expressed satisfaction at the removal of dependence from the title of addictive disorders, especially as physical dependence is often part of opiate administration for patients (especially pain patients) who are in no way addicted to the drugs. Dr. Volkow also noted that while physical dependence in relatively easy to treat, addiction is not, a matter that was made all the more confusing by the ill-conceived (in her opinion, and in mine) term. Additionally, the inclusion of severity ratings in the new definition, allowing for a more nuanced, spectrum-like, assessment of addiction disorders, seemed to make Dr. Volkow happy in her own, reserved, way.

Treatment matching – rehab search for the 21st century

As most of my readers know, one of my recent interests centers on the application of current technology to the problem of finding appropriate treatment for suffering addicts. I brought the problem up during this talk, and Dr. Volkow seemed to agree with my assessment that the current tools available are nowhere near adequate given our technological advancements. I talked a bit about our upcoming addiction-treatment-matching tool, and I hope that NIDA will join us in testing the utility of the tool once we’re up and running. I truly believe that this tool alone will allow more people to find appropriate treatment increasing the success rate while maximizing our system’s ability to treat addicts.

Involving the greater public in addiction research

It wasn’t until the end of the conversation that I truly understood the reason for the invitation (I’m slow when it comes to promotional issues) – NIDA is looking to move the discussion about it’s goals and directions out of the academic darkness in which they’ve lurked for years, and into the light of online discussion. I’m in no way offended by this, especially since this was exactly my point in starting All About Addiction in the first place. If anything, I’m honored to be included in the select group of people NIDA has chose to carry their message, especially since the conversation was an open, respectful, and data-centered one. I hope more of these will occur in the future.

Resolving confusion about addiction

One of the final points we got to discuss in the too-short hour we had Dr. Volkow on the “phone” had to do with the oft misunderstood concept of physical versus psychological addictions. I’ve written about this misconception in the past, and so I won’t belabor the point here, but it’s time that we gave our brain the respect it deserves by allowing it to join the rank, along with the rest of our body, and the physical realm. We’re no longer ignorant of the fact that our personalities, memories, feelings, and thoughts are driven by nothing more than truly physical, if miniature, happenings in our brains. In the same way that microbe discovery improved our well-being (thank you Pasteur), it’s time the concept of the very physical nature of our psychological-being improves our own conceptualization of our selves.

We are physical, spiritual, and awesome, but only if we recognize what it is that makes “us.”

About addiction: Bankers, courts, Obama, and painkillers

Hey everyone, here’s another roundup of some good links about addiction from around the globe –

Addiction today – U.S. bankers seek treatment

Breaking the cycles – Offender sentencing that makes sense

Addiction tomorrow – Obama says NO to legalization

Physorg – FDA cracks down on unapproved narcotic painkillers

Don’t forget to look at our own related posts by clicking on this post’s title.