Notes about the chapter

Chapter 10

• The argument might deceive us with statistics!

• Statistics can and often lie. They do not necessarily prove what they appear to prove.

1. Unknowable and biased statistics

• Any statistic requires that some events somewhere have been defined and accurately identified, but these conditions are often not met.

• Statistics are often in the form of educcated guesses.

• One common use of unknowable statistics is to impress or alarm others with large numbers, often presenting them with suspicious precision.

• Before reacting to such statistics, we need to ask how they were determined.

2. Confusing averages

• Mean: determined by adding all the values and dividing by the total number of values.

• Median: Determined by listing all the numbers from highest to lowest and finding the one in the middle.

• Mode: Determined by counting the frequency of different values and then finding the value that appears most frequently.

• Consider how using the various meanings of average might change the significance of the information.

• Important to determine the gap between the smallest and largest values-the range-and how frequently each of the values occurs-the distribution

• A general benefit of keeping the range and distribution in mind when encountering averages is that doing so should remind you that most people or events will not match the exact average value and that outcomes quite distant from the average are to be expected.

3. Measurement errors

• Statistics result from measurement. But measurements are always subject to error.

• Another illustration of measurement error is in the measurement of levels of alcohol consumption.

4. Concluding one thing, proving another

• blind yourself to the communicator's statistics abd ask yourself, " what statistical evidence would be helpful in proving her conclusion". Then, compare the "needed" statistics to the statistics given.

• pay very close attention to both the wording of the statistic and the wording of the conclusion

5. Deceiving by omitting information

• Locating flaws in statistical reasoning is to ask, " what further infor do you need before you can judge the impact of the statistics?"

• When only absolute numbers are presented, ask whether percentages might help you make a better judgment; when only percentages are presented, ask whether absolute numbers would enrich their meaning.

• When you encounter statistics, be sure to ask, “What relevant informa- tion is missing?”