Page 229 - Statistics for Dummies

Chapter 13: Confidence Intervals: Making Your Best Guesstimate
one doing karaoke at some point). This may create some bias in the results.
(The last time I was in Vegas, I believe I really saw Elvis; he was driving a van
taxi to and from the airport. . . .)
Notice that you could get a negative value for
. For example, if you had

switched the males and females, you would have gotten –0.19 for this differ-
ence. That’s okay, but you can avoid negative differences in the sample pro-
portions by having the group with the larger sample proportion serve as the 213
first group (here, females).
Spotting Misleading Confidence Intervals
When the MOE is small, relatively speaking, you would like to say that these
confidence intervals provide accurate and credible estimates of their param-
eters. This is not always the case, however.
Not all estimates are as accurate and reliable as the sources may want you to
think. For example, a Web site survey result based on 20,000 hits may have a
small MOE according to the formula, but the MOE means nothing if the survey
is only given to people who happened to visit that Web site.

In other words, the sample isn’t even close to being a random sample (where
every sample of equal size selected from the population has an equal chance
of being chosen to participate). Nevertheless, such results do get reported,
along with their margins of error that make the study seem truly scientific.
Beware of these bogus results! (See Chapter 12 for more on the limits of
the MOE.)

Before making any decisions based on someone’s estimate, do the following:
✓ Investigate how the statistic was created; it should be the result of a sci-
entific process that results in reliable, unbiased, accurate data.
✓ Look for a margin of error. If one isn’t reported, go to the original source
and request it.
✓ Remember that if the statistic isn’t reliable or contains bias, the margin
of error will be meaningless.

(See Chapter 16 for evaluating survey data and see Chapter 17 for criteria for
good data in experiments.)

3/25/11 8:14 PM
20_9780470911082-ch13.indd 213 3/25/11 8:14 PM
20_9780470911082-ch13.indd 213