In the wake of the horrific floods that struck Colorado recently, many people have debated whether global warming is to blame. The same goes for wildfires that hit that state this summer and for the massive tornado that struck in Oklahoma this spring. In the wake of that tornado, for instance, Senator Sheldon Whitehouse from Rhode Island claimed that Republican opposition to climate change legislation was at fault, for trying to “protect the market share of polluters.”  Senator Barbara Boxer was confident about the cause of the terrible twister too: “This is climate change” she said.

The same finger pointing occurred after super storm Sandy, with some people even claiming that global warming could make storms like Sandy into the new normal, occurring as often as every other year, and Governor Chris Christie just as adamantly denying that global warming played any role in this storm.

The problem with these debates is familiar to those of us in the medical community who have followed controversies about breast cancer screening — people mistakenly and all too understandably seek out explanations for individual events when science can only tell us about aggregate truths.  For the same reason we cannot tell whether an individual mammogram saved a woman’s life, we cannot determine whether any specific storm is the result of climate change.  Instead, we are left with what we can learn from statistics.

Wondering why we don’t know whether a specific mammography test saved a woman’s life?  Suppose a routine mammogram reveals a tumor in an otherwise healthy 56-year-old woman.  She is treated with surgery and pills and lives 20 more years before dying of a heart attack.  It may seem obvious that the mammogram saved her life.  But in fact, there is no way to know whether she would have died of breast cancer within that 20 year period if it hadn’t been for that mammogram.  For all we know, her cancer might never have progressed. In fact, experts now realize that some early tumors actually shrink over time, even when left alone.  It is also possible that this woman would have discovered the tumor without a mammogram, and the tumor still would have been susceptible to treatment.

For many of the same reasons, we also have a hard time knowing whether people who die of breast cancer would have avoided that fate had they received more frequent mammograms.  When I took care of patients with advanced cancer — patients who had avoided physicians like me and all of our pesky screening tests — I would find myself bemoaning their avoidable fates: “If they had only come to my clinic sooner, I would have found their cancers before they became incurable.”  But of course, I couldn’t know whether that was true for any individual patient.  Some women die of breast cancer despite receiving annual mammograms, after all.

Pretty unsatisfying huh?  It is natural to seek out causal explanations for good and bad events.  We want to know whether this hurricane and that tornado are caused by climate change, and whether this prostate cancer or that breast cancer could have been prevented by more aggressive screening.  Instead, we are only left with the data, and with scientists telling us how much more or less likely these events would have been if circumstances had been different.

Climate scientists run predictive models to estimate the likelihood of extreme weather events if temperatures rise due to carbon accumulation in the environment.  Most such experts contend that hurricanes will become more common and more dangerous if temperatures continue to rise, but aren’t so sure tornadoes will become more common.  But no respectable climate expert would blame any single hurricane on global warming.  Such an attribution would be horrific science.

By the same token, most medical experts contend that mammography reduces breast cancer deaths.  But no respectable physician would argue that a given mammogram saved a specific woman’s life.

We need to be cautious about claiming we know the specific causes of individual tragedies — whether they involve horrific storms or heart wrenching cancer deaths.  Instead, we should leave speculation about causation up to the experts.

Peter Ubel is a physician and behavioral scientist who blogs at his self-titled site, Peter Ubel and can be reached on Twitter @PeterUbel.  He is the author of Critical Decisions: How You and Your Doctor Can Make the Right Medical Choices Together. This article originally appeared in Forbes.