to How Lie with Statistics Darrell Huff (1954)
"Over the last fifty years, How to Lie with Statistics has sold more copies than any other statistical text." J.M. Steele. "Darrell Huff and Fifty Years of How to Lie with Statistics. Statistical Science, 20 (3), 2005, 205209.
How to lie with statistics
Chapter 1 - The Sample with the Built-in Bias: We find that polls (while informative) are always biased (mainly toward conservative, higher salaried, better educated). Chapter 2 - The Well-Chosen Average: The word "average" (mean, median, or mode) is misused and (even when it is used appropriately) misunderstood. Chapter 3 - The Little Figures That Are Not There: Hidden numbers. "Science proves that tossed pennies come up heads 80 per cent of the time." Chapter 4 - Much Ado about Practically Nothing: unreported probable error. Chapter 5 - The Gee-Whiz Graph: Distorted graphs (choices of scales and origins).
How to lie with statistics
Chapter 6 - The One-Dimensional Picture: Distorted picture graphs (height vs. area). Chapter 7 - The Semiattached Figure: The reported data may even be irrelevant. This mouthwash kills germs (but maybe not cold germs in the mouth). Chapter 8 - Post Hoc Rides Again: Cause and effect, or some common cause, or coincidence, or what? "There is a close relationship between the salaries of Presbyterian ministers in Massachusetts and the price of rum in Havana." There are more weddings in June, and there are more suicides in June. Which causes which? Chapter 9 - How to Statisticulate: Lying with statistics = dishonesty or incompetence? Mostly dishonesty.
How to lie with statistics
Chapter 10 - How to Talk Back to a Statistic: How to detect lying (actually the real purpose of the entire book). Ask yourself: Who says so? How does he know? What's missing? Did someone change the subject? Does it make sense?
How to not lie with statistics
R 2 is often called the "coefficient of determination." The result (or cause) of this unfortunate terminology is that the R statistic is sometimes interpreted as a measure of the influence of x on y. Others consider it to be a measure of the fit between the statistical model and the true model. A high R is considered to be proof that the correct model has been specified or that the theory being tested is correct. A higher R2 in one model is taken to mean that that model is better. All these interpretations are wrong. R2 is a measure of the spread of points around a regression line, and it is a poor measure of even that (Achen, 1982).
Q&A on R2
Q: How can I tell how strongly my independent variables influence my dependent variable without R2 ? A: Interpret your regression coefficients. Q: But how can I tell how good these coefficients are? A: The standard errors are estimates of the variance of your parameter estimates. If they are small relative to your coefficients, then you should be more confident that similar results would have emerged even if a sample of 1500 different people were interviewed. Q: But how can I tell how good the regression is as a whole? A: If you want to test the hypothesis that all your coefficients are zero, use the F-test. More complex hypotheses about different theoretically relevant linear combinations of coefficients (e.g., that the first three coefficients are jointly zero, or that the next two add to 1.0) can also be tested. R2 is associated with, but is a poor substitute for, test statistics.
Why stress makes you fat
A recent study in the American Journal of Epidemiology looked at data on 1,355 men and women who had their weight and stress levels measured in 1995 and again in 2004. The findings showed that those who were overweight and obese packed on the pounds even more as time went by and stressors continued and increased. Those who were thin stayed thin and according to the lead author Jason Block on faculty at Harvard, The stress effect didnt appear to impact normal-weight people, just those who were overweight and obese from the beginning of the study.
Why makes stress you fat
Am J Epidemiology 2009;170:181192 To determine whether multiple domains of psychosocial stress were associated with weight gain from 1995 to 2004, the authors analyzed a nationally representative longitudinal cohort of 1,355 men and women in the United States. Change in body mass index was assessed for multiple domains of psychosocial stress related to work, personal relationships, life constraints, and finances, controlling for other factors associated with weight gain. All analyses were stratified by sex and weighted to account for the complex survey design. Among men with high baseline body mass index, weight gain was associated with increasing levels of psychosocial stress related to jobrelated demands (P < 0.001 for interaction with baseline body mass index), lack of skill discretion (P < 0.014), lack of decision authority (P < 0.026), and difficulty paying bills (P < 0.004). Among women with high baseline body mass index, weight gain was associated with job-related demands (P < 0.001 for interaction with baseline body mass index), perceived constraints in life (P < 0.001), strain in relations with family (P < 0.016), and difficulty paying bills (P < 0.010).
Here are a few ways to NOT let stress make you fat:
1. Dont isolate yourself. Reach out to friends, family and others. 2. Stay away from critical and negative people. 3. Exercise. 4. Relax. 5. Get 8 hours of sleep a night and watch the weight drop. 6. Balance your hormones. 7. Do not focus on diet alone. When trying to loose weight incorporate all the above into a healthy diet, exercise and stress management program.
Correlation is not Causation
A causes B B causes A C causes both A and B A influences B and B in turn influences A Coincidence
Young children who sleep with the light on are much more likely to develop myopia in later life.
This a recent scientific example that resulted from a study at the University of Pennsylvania Medical Center. Published in the May 13, 1999 issue of Nature, the study received much coverage at the time in the popular press. However, a later study at The Ohio State University did not find a link between infants sleeping with the light on and development of myopia. It did find a strong link between parental myopia and the development of child myopia, also noting that myopic parents were more likely to leave a light on in their children's bedroom. In this case, the cause of both conditions is parental myopia.
CELL PHONE TASK Light Vehicle/Cars Dialing Cell Phone Talking/Listening to Cell Phone Reaching for object (i.e. electronic device and other) Heavy Vehicles/Trucks Dialing Cell phone Talking/Listening to Cell Phone Use/Reach for electronic device Text messaging
Risk of Crash or Near Crash event
2.8 times as high as nondistracted driving 1.3 times as high as nondistracted driving 1.4 times as high as nondistracted driving
5.9 times as high as nondistracted driving 1.0 times as high as nondistracted driving 6.7 times as high as nondistracted driving 23.2 times as high as nondistracted driving
What do you call a tea party with more than 30 people? A Z party!!!
Correlation or Causation
http://jonathan.mueller.faculty.noctrl.edu/1 00/correlation_or_causation.htm
Normal theory
Q: How many statisticians does it take to change a light bulb? A: One plus or minus three.
Observation
Q: Did you hear about the statistician who was thrown in jail? A: He now has zero degrees of freedom.
Miscelaneous
Theory and practice are the same in theory. In practice they are different. Without geometry, life is pointless. Every day, innumeracy affects 8 out of 5 people.
A leg up
Did you know that the great majority of people have more than the average number of legs? It's obvious, really: Among the 57 million people in Britain, there are probably 5,000 people who have only one leg. Therefore, the average number of legs is 1.99. And because most people have two legs...
If had only one day left to live, I would live it in my statistics class: it would seem so much longer.