Chapter 2: Misconceptions
When people read, hear, or prepare research summaries,
they sometimes have misconceptions about what is or isn't "sound
practice" regarding the collection, analysis, and interpretation
of data. Here are some of these common (and dangerous) misconceptions
associated with descriptive statistics.
- The mean is superior to either the median or the
- If a mean and a standard deviation are cited
for a group of data, those two indices "say it all."
- Data that approximate the normal distribution are
superior to data that are skewed.
- Frequency distributions, bargraphs, stem-and-leaf
displays, and box plots are so elementary that they don't belong in
sophisticated research summaries.
- A standard deviation indicates how far a typical
score will deviate from the mean.
- The highest score in a group will always be about
six standard deviations higher than the lowest score in that group.
- If drawn correctly, a normal curve must resemble
- Standard scores (such as z-scores or T-scores) are
computed by researchers only when the original data are normally distributed.
- The only three measures of central tendency are the
mean, the median, and the mode.
- The word "average" is synonymous with the
- The normal curve is curved most at the points of
inflection (i.e., above the baseline points of z = +1.0 and z = -1.0)
- If the male test scores have a SD = 10 and the female
test scores have a SD = 20, the SD for the combined group of males and
females will be equal to 15.