3 Controversies & 2 Paradoxes H. James Norton, Carolinas Medical Center, Charlotte, NC George W. Divine, Henry Ford Hospital, Detroit MI

Keeping undergraduate biology students and medical residents interested in statistics, when the majority of the students are taking the class as a requirement, can be challenging

The following are examples of controversies and paradoxes that you might find helpful in your course instruction.

Paradoxes Paradoxes, by their very nature, can be interesting to students. An example from: Introduction to the Practice of Statistics by David S. Moore & George P. McCabe

Patients in Good Condition DiedSurvivedDeath Rate Hospital A % Hospital B % a. If you are in good condition, in which hospital would you want to have your surgery, A or B?

Patients in Poor Condition DiedSurvivedDeath Rate Hospital A % Hospital B % a. If you are in poor condition, in which hospital would you want to have your surgery, A or B?

Patient’s Survival Rates DiedSurvivedDeath Rate Hospital C % Hospital D % a. If this is the only data available, in which hospital would you want to have your surgery, C or D?

d. What is the relationship between hospitals A, B, C, and D? Hospital C is the combined data from the 2 tables for Hospital A, and similarly Hospital D is really Hospital B. e. What has happened when the tables for patients in good condition and patients in poor condition were combined into the third table?

Simpson’s Paradox Refers to the reversal of the direction of a comparison or an association when data from several groups are combined to form a single group.

Cancer patients are classified by stage TNM staging protocol T - Tumor N - Nodes M - Metastases More advanced disease is assigned a higher stage

A paradoxical situation can occur over time, where the overall death rate from a cancer may remain constant, but the death rate for every stage can go down. This paradox is known as “The Will Rogers phenomenon.”

Key Patients who will be classified Stage I in 2009  (will survive next 5 years) Patients who will be classified Stage II in 2009 m (will survive next 5 years) l (will die in next five years) Patients who will be classified Stage III in 2009 o (will survive next 5 years) n (will die in next five years)

As it was Will Rogers who said of the poor farmers who migrated from Oklahoma to California during the dust bowl era of the 1930’s, “When the Okies left Oklahoma and moved to California, they raised the average intelligence of both states.”

Gregor Mendel Monk at Abbey of St.Thomas Taught school but never could pass the exam for certification. Presented his paper “Experiments on Plant Hybridization” at meetings of the Natural History Society of Brunn in 1865.

Fact from: The Monk in the Garden By Robin Henig Mendel originally bred mice for his experiments. Bishop Schaffgotsch thought this was vulgar and ordered Mendel to stop.

7 Characteristics of Peas that Mendel Studied

+ Stem Length (Tall or Short)

R. A. Fisher in 1916 ”It is interesting that Mendel’s original results all fall within the limits of probable error; if his experiments were repeated the odds of getting such good results is about 16 to 1. It may have been just luck, or it may be that the worthy German abbot, in his ignorance of probable error, unconsciously placed doubtful plants on the side which favored his hypothesis.”

Statistical topics with Mendel’s data Probability Binomial distribution Statistical independence p-values Chi-square distribution Chi-square goodness-of-fit test

Advanced Statistical Topic Sum of independent chi-square distributions Distribution of p-values under the null hypothesis Kolmogorov-Smirnov test

Cross breed two hybrids (heterozygous) with recessive trait (white flower) Probability of white flower = 1/4

Bifactorial or dihybrid cross Two independent recessive traits (green & wrinkled) Resulting ratio (9:3:3:1)

Results from 5 of Mendel’s experiments RatioObs (Exp) chi-squarep-value 3:1787 (798)277 (266) :1428 (435)152 (145) :1353 (346)166 (173) :1705 (696.75)224 (232.25) :1651 (643.5)207 (214.5)

Sum of Chi-squares The sum of independent chi-squares is also a chi-square with d.f. = Σ d.f.’s For Mendel’s 37 experiments, Σ X 2 = Σ d.f.’s = 45 The p-value of a chi-square = with d.f. = 45 is

Reason’s for Different Conclusions Concerning Possible Fabrication of Data Among Statisticians Not using all the datasets. Subdividing the experiments. Employing different statistical tests. Subjective opinions in making conclusions.

Some conclusions about Mendel’s data Ira Pilgram, “I have no reason to suspect that the data were not honestly derived.” Sewall Wright, “Taking everything into account, I am confident there was no deliberate effort at falsification.” A.W. Edwards, “It is concluded that in spite of many attempts to find an explanation, Fisher’s suggestion that the data have been subjected to some kind of adjustment must stand.”

Sister, some statisticians think my results are too good to be true. Bother Mendel, of course you would get good results. You’re a saint!

People v. Collins (1968) A woman had her purse stolen. The witnesses did not get a good look at the robber’s face. Witnesses were able to describe some characteristics of the robber, the get- away car, and the driver. Prosecution calls an Instructor of Mathematics to testify. Instructor explains the product rule for multiplying probabilities of independent events.

Prosecutor suggests these probabilities: Black man with a beard 1 in 10 Man with a moustache 1 in 4 White woman with pony tail 1 in 10 White woman with blonde hair 1 in 3 Yellow automobile 1 in 10 Interracial couple in car 1 in 1000 Asks instructor what the probability would be under these estimates. 1 in 12,000,000. Prosecutor claims these estimates are conservative. “Chances of having every similarity … something like 1 in a billion.” Jury finds defendant guilty.

The ruling of the appeal’s court: “It is a curious circumstance of this adventure in proof that the prosecutor not only made his own assertions of these factors in the hope that they were conservative… but invited the jury to substitute their estimates.” “There was another glaring defect in the prosecution’s technique, namely an inadequate proof of the statistical independence of the six factors.”

The final ruling of the appeals court: “Mathematics, a veritable sorcerer in our computerized world, while assisting the trier of fact in the search for truth, must not cast a spell over him. We reverse the judgment.”

The Sally Clark Case

Sally Clark was a solicitor in Cheshire, England. Her son, Harry Clark, born 3 weeks premature, died 8 weeks after birth. In addition, her first child had died less than 3 weeks after birth. His autopsy concluded he had died of natural causes. He had signs of a respiratory infection. She was arrested for 2 counts of murder, despite the fact that there was very little evidence against her.

Sally had no history of violent or unusual behavior. Harry had some evidence of being shaken but this was consistent with her report to the police that she had shaken the baby when she noticed that he was not breathing. Prosecutor’s main argument was that it would be very unlikely that 2 babies in same family would die of cot death. In the U.S. we would use the term Sudden Infant Death Syndrome (SIDS).

Prosecution calls Sir Roy Meadow Professor of Paediatrics St. James University Hospital President British Paediatric Association

His testimony was based on the Confidential Enquiry for Stillbirths and Deaths, a study of deaths of babies in infancy, in 5 regions of England from 1993 to Probability random baby dies of a cot death = 1 in Probability random baby dies of a cot death if the mother is > 26 years old, affluent, and a non smoker = 1 in Probability two children from such a family both die from a cot death = (1 in 8543) x (1 in 8543) = 1 chance in 73 million.

Judge’s summary to jury, “Although we do not convict people in these courts on statistics, … the statistics in this case are compelling.” Jury convicts on a 10 to 2 vote. One juror said, “Whatever you say about Sally Clark, you can’t get round the 1 in 73 million figure.” Sally’s conviction upheld on appeal.

2001, Royal Statistical Society issues a news brief condemning the use of the multiplication rule for independence. “This approach is statistically invalid. … The well publicized figure of 1 in 73 million has no statistical basis.” 2002, Ray Hill, Professor of Mathematics at the University of Salford, analyses other published data. He concludes the probability of having a second child die a cot death, given a first child in a family died a cot death, may be as high as 1 in 60.

In 2003, after spending 3 years in jail, Sally’s second appeal was upheld, and she was released from jail. This was only after a new pro bono lawyer, while reviewing the evidence, discovered a pathology report revealing that Harry was infected with staphylococcus aureus and that this fact had been hidden from her defense team. Two other women whom Meadow had testified against at the murder trial of their children were released upon appeal. In 2007, Sally Clark died, of apparently natural causes, due to acute alcohol intoxication.

New Evidence on S. aureus & SIDS “Infection and sudden unexpected death in infancy (SUDI): a systematic retrospective case review. M.A. Weber. Lancet May ;371: “Significantly more cultures from infants whose death was unexplained contained S. aureus (262/1628, 16%) than did those from infants whose deaths were of a non infective cause (19/211, 9%, p=0.005). From editorial by Morris, “but this work … provides support for the idea that S. aureus and E. coli could have a causal role in some cases of unexplained SUDI.”

The misuse of statistics has lead to the following observations: A politician uses statistics like a drunk uses a lamppost. For support – not illumination.

Facts are stubborn but statistics are more pliable.

There are 2 kinds of statistics- the kind you look up & the kind you make up.

Statistics can be used to support just about anything...

including statisticians!!

Conclusions: Hopefully, the use of the controversies & paradoxes, will improve the learning experience for the students. Most students seem receptive to this style.

Also available on request at Today’s presentation. Norton HJ. Teaching Undergraduate Students and Medical Residents How to Identify Fallacies in Numerical Reasoning. Presented American Statistical Association, 1998.