Accuracy and Precision

"Lies, damned lies, and statistics." 

Mark Twain

I so often use statistics in my work that I forget that other do not. Not only is unfamiliarity a problem, but so often statistics are manipulated by those that use them to support one argument or another. When in doubt, ask for the raw data and do it yourself. One of the things that my father always reminded me when I was young was to look at my source. That is a very valuable thing in the day of the internet where anything and everything is out there.

To aid in some understanding I thought I would describe certain statistical terms that arise in journal articles in my field.

Accuracy: Accuracy is how close a measurement is to the "true" value. In a laboratory setting this is often how far a measured value is from a standard with a known value that was measured by different technology or on a different instrument.

Precision: Precision is how close repeated measurements are to each other. Precision has no bearing on a target value, it is simply how close multiple measurements are together. Reproducibility is key to scientific research and precision is important in this aspect.

Now obviously the goal is to have a measurement that is both accurate and precise, but being one doesn't mean that the other is as well. For example, if we had a bow and arrow and target, accurate shots would be ones in which hit the bulls eye. If we landed a shot in the bulls eye and others around the target we would be accurate, but not precise. If all of our shots landed close together, but not near the target than we would be precise but not accurate. To be accurate and precise we would need our shots to be together and in the bullseye.

The images above are a good reason to look further than just an average. If the average is based on a wide range of values than that average may indeed be meaningless. For example, if I have the values of 1 and 100, the average is 50.5. I could have that same average of 50.5 if my two values were 50 and 51. Both pairs of numbers result in the same average, but in the first example, the average is meaningless because the two numbers are so far apart.

This is where standard deviation comes in.

Standard Deviation: Standard deviation is a measure of the dispersion of numbers around a population average. So if you envision a bell curve of data, the standard deviation would be how far apart the numbers are from the average. Our first example above would have a very large standard deviation where as our second one would be small.Depending on how many standard deviations are used will tell you how many of the values are covered. One standard deviation will include 68% of all values whereas three standard deviations will include 99% of all values.

It's always important to look at how the data is being represented and to keep those three aspects in mind. If you are looking at a set of numbers or a conclusion drawn from repeated testing you want to be aware of the terms I mentioned above to know how much credibility to give the data.

Marijuana Soda

Now that Four Loko is being banned so frequently it was only a matter of time before another controversial drink would hit the news. This time it's not alcohol we're talking about, but marijuana.

In California, where the sale of medical marijuana is already legal, cannabis containing drinks are already sold in dispensaries. What makes this item newsworthy is more to do with it's packaging and marketing. Sold in fruity flavors and carbonated like soda these drinks from Canna Catering are marketed for their enjoyment factor and not for their medicinal purpose. Indeed for half the price of the medical beverages already sold it only contains a third of the marijuana as the medical beverages, so who really is this drink being made for?

Although Proposition 19 failed in November of this past year, which would have made personal recreational use of marijuana legal for those over 21 years, marijuana has been decriminalized so that possession of less than an ounce is only subjected to a $100 fine.

Is Canna Catering gambling that it's only a matter of time before it's legal? A company in Colorado, Dixie Elixers, is marketing their own line of drinks much like the soda from Canna Catering. It certainly seems like these companies are getting into line to be first in supermarkets should it become legal.

Oh Miley. Salvia in the News

Oh Miley, Miley. Hannah Montana is in the news again, but not for racy pictures. This time it's a video that was leaked with Miley Cyrus smoking something that looks suspiciously like marijuana. That could be a problem since marijuana is illegal but then she is a celebrity and that tends not to matter much, but wait! What is this? Miley says it's not marijuana but Salvia. Oh well, than that's ok.

So what is Salvia? Salvia divinorum is a plant native to Oaxaca Mexico and used by Mezatac Shamans to facilitate shamanic visions. Traditionally the fresh leaves are chewed or used in a tincture and produce effects that appear to be somewhat of a cross between LSD and marijuana though shorter lasting and more mild than either. Interestingly the Mezatac people view Salvia as the Virgin Mary incarnate and begin the ritual with an invocation to Mary, St Peter and the Holy Trinity.

Obviously Miley was not trying for shamanic visions and I'm pretty sure there was no invocation involved which brings us to use in the US. In the US Salvia is sold dried in packets and is typically smoked. It's legal in all 50 states and although the media has waged campaigns against the herb, emergency rooms and medical professionals have not reported cases that suggest any health concerns and police have not been reporting it as a factor in public order offenses.

I would hazard a guess and say that the reason there really hasn't been any problem with the herb is that the effects are very short lasting. The peak effect is within 1 minute of smoking with a high last 5 minutes, the subject's return to baseline occurs within 15-20 minutes. The two most commonly reported effects are "Increased insight" and "Improved Mood" which may also play a factor. When compared to something like LSD where effects last 8-12 hours that is a huge difference.

So back to Miley. Is the illegal potential the problem or the fact that she's a Disney star getting high the problem? If the former than Salvia saves the day, if the latter than I don't see Miley making the situation any better for herself. I suppose it's a matter of perspective. Why is alcohol legal and marijuana not? Both are impairing yet one is legal and the other is not. Should Salvia be illegal just because it seems to have mood altering effects? I'm not convinced.

Fowl Forensics

In honor of the holidays that have just passed us by too quickly, here is an eye witness account of a suspicious death copied for the American College of Forensic Examiners Institute.

 ***************************

While conducting fully uniformed patrol on Thursday, November 25^th, 2010, I was dispatched to a priority call for a suspicious death. I immediately activated my emergency lights and siren and proceeded to 123 Gobbler Lane.  Upon arrival at the scene, I swiftly and tactically made entry into the residence. I conducted a protective sweep of the entire premises, ensuring that no immediate threats were present. 

When I entered the final room to clear, the kitchen, my suspicion was immediately piqued when I observed that the door to the oven was left cracked open and heat was radiating from within.  When I opened the oven door, I could see the remains of the deceased victim, later identified as Tom T. Turkey. After visually inspecting the remains, I immediately suspected fowl play.

With the residence now a homicide crime scene, I immediately secured the perimeter and called in our forensic unit.  Forensic practitioners then began to arrive on scene to search, document, and analyze any existing evidence. Detective Mayflower, Registered Investigator® was among the first to arrive.  He began a slow and methodical search for evidence, utilizing other personnel in a grid search method, combing the exterior of the house (curtilage) for physical evidence.

On the anterior portion of the property, a housing structure constructed with "chicken wire" was located. Upon careful examination of this structure, not only was blood spatter found to be present, but a possible murder weapon was also located. The weapon was a standard kitchen cleaver, Oneida brand, serial number 54783. The weapon had blood visible on it with what appeared to be a feather stuck to the blade. After this evidence was marked by triangulation and photographed, it was collected and sealed to be sent to the laboratory for processing. 

With the exterior search concluded, the investigative team began a thorough search of the interior of the residence.  Culminating in the kitchen, we began to process the scene.  Although the apparent cause of death was decapitation, the body was also burned and appeared to be basted with a substance consistent with butter. The Medical Examiner and Certified Forensic Physician®, Dr. Bob Butterball, then arrived on scene. Due to the exigent circumstances present, he decided to conduct an immediate autopsy of the victim on scene.

After opening the body, Dr. Butterball concluded that the cavity seemed to be filled with a substance consistent with Stove Top stuffing and lacked the vital organs. After collecting samples of the white tissue and dark tissue, Dr. Butterball packaged the remains as evidence and sent them to the laboratory for processing. When the toxicology results returned, there were copious amounts of tryptophan present, along with traces of cranberry and sage. 

With no witnesses to be found and the scene lacking any latent fingerprints, this case remains open. If you have any information about the events of November 25^th on Gobbler lane, please contact me at the American College of Forensic Examiners Institute.      

10 Worst Drinking Trends of 2010

Glad to see Four Loko made the list!

Merry Christmas!

Wishing everyone a wonderful holiday filled with joy, magic and friends and family!

The Trouble with DUID: Part II

So in the last post we began our discussion on DUID and some of the many problems that go along with the legislation involved to enforce it. We spoke of how legislation is often reactionary and because of that only focuses on the minutia and not the overall concern.

So what is our concern with DUID?

I would hazard a guess and say that our concern is that we do not want potentially dangerous people driving on our roads, and by having a DUID law we have said that people using drugs fit into that category of dangerous people.

So what's the problem? Well, lots of people are on "drugs" in this country at any one time. Does that mean that anyone using a prescription drug should be banned from driving? The legislature clearly doesn't want that, and I agree that would go too far. Some prescription drugs are impairing and others are not. How do we know that the person is impaired? With drugs, impairment seems to occur at different levels in different people, making per se limits controversial even in the scientific community.

Some countries have operators accused of DUID examined by doctors at arrest and have the doctor determine whether they are impaired or not, which is then confirmed by blood test. In this country we have a DRE program, which in theory, should do the same thing. Specially trained officers certified by this program are trained to conduct a 12 point exam to determine whether a person is impaired by drugs or not. The blood is then tested to confirm their observations.

So that should solve it right? Well, no and for two reasons.

#1. In our state at least the statute states that when drugs are involved, the operator must be incapable of operating safely. So, if the subject crashed their car and they are under the influence of an illegal drug, then great! The reality is that's not what you see most often. What if the drug they're using is prescription and within therapeutic ranges? Are they impaired or not? It depends. What about on a snowy day where lots of car crashes have occurred? Can you prove it was the drug and not the snow?

#2. DRE's are often told to ensure they don't make errors to simply have the blood screened for everything. Ok. Now what? Although it's not the intention, screening for everything implies that they cannot determine the impairment or at least what caused it. Is it enough for them simply to see impairment without knowing what drug or class of drug caused it? That depends on how we want to use the information. Don't get me wrong, I think the DRE program is an excellent system with well trained officers. I just think it's not always used to it's fullest potential.

Now, if the statute was like the alcohol statute where impairment was to the slightest degree rather than incapable of operating safely, I think the DRE program would be able to work more effectively. We would have a subject suspected of impairment from drugs, the DRE would confirm they were impaired and the test result would support the observations. Then it wouldn't matter so much whether they were stopped for speeding or for crashing their car.

The trouble with impairment in driving however is that there are many things that will impair your driving and most aren't illegal. Experience, age, fatigue, distraction. People have tried to address issues like these by banning hand held cell phones only to find that it's the actual conversation that distracts people and not the holding of the phone.Others are in the same boat as prescription drugs, we don't want to ban grandma from driving just because this happens.

So what do we do?

I'm not going to pretend I know the answer to that. But I do believe it's time that we start looking at the big picture rather than chasing lists. The idea of banning any chemical which binds to a certain receptor is an interesting idea, and it is going towards the right direction of thinking about the problem rather than the specific instant.

It's something to think about anyway.