Uses and Abuses of Statistics
Statistics is used to organize, summarize, present, and/or analyze data -- often with the intent of approximating the behavior of a population through examination of samples taken from that population; testing hypotheses; determining relationships between variables; and making predictions from existing data.
However, statistics can be abused too. The following lists some ways in which this frequently happens:
- Quoting statistics based on non-representative samples
- Choosing the "average" value for a sample which most lends itself to your position, when a different "average" value would be more appropriate
- Speaking of changes in a variable in terms of actual values or percentages to either inflate or deflate their importance psychologically. (How happy would you be if your net worth increased by $10,000,000. What if that only represented a 0.3% increase?)
- Using detached statistics like "1/3 fewer carbs" (fewer than what?)
- Implying causal connections between variables without a well-designed experiment to back it up (i.e., "Doctors say that taking lipotrim twice a day ''may reduce'' your weight by up to 30 lbs in the first 2 weeks!")
- Formatting graphs to mislead the eye
- Designing questions to be used on a survey that will bias the results