/opt/scribd/conversion/tmp/scratch10056/39291534.

doc -1-

PERCENTILE
Any of the 100 equal parts into which the range of the values of a set of data can be divided in order
to show the distribution of those values. The percentile of a given value is determined by the
percentage of the values that are smaller than that value. For example, a test score that is higher
than 95 percent of the other scores is in the 95th percentile.
per·cen·tile n.
One of a set of points on a scale arrived at by dividing a group into parts in order of magnitude. For
example, a score equal to or greater than 97 percent of those attained on an examination is said to
be in the 97th percentile.
(Mathematics & Measurements / Statistics) one of 99 actual or notional values of a variable dividing
its distribution into 100 groups with equal frequencies; the 90th percentile is the value of a variable
such that 90% of the relevant population is below that value Also called centile

A percentile is best described as a comparison score. It’s a common term in all kinds of testing of
data, but many will be most familiar with percentiles as they relate to standardized testing in K-12
schools. Unlike percentages, where you are given a percent number that is related only to your
performance, percentiles relate the number to the performance usually of 100 similar students.
It’s easier to understand this when you can look at comparisons of percentages and percentiles. For
the sake of simplicity, consider a test with 100 problems on it, each problem worth 1% of the test. If
you get 80 problems correct, you get 80% on the test.
80% refers to the number you got correct, not to your score in reference to anyone else’s
performance. Some teachers grade on a curve, and award the highest grade not based on actual
percentage, but on highest test score. So if your 80% was the highest score in the class, you’d earn
an A. More standard is assigning As to 90% and up, Bs to 80-89%, Cs to 70-79% and so on.
Especially when testing is standardized, it is meant to serve a diverse group of people and accurately
gauge not only individual performance but comparative performance. If we look at the same test
again, your score in percentiles would be based on the number of students who scored below you on
the test. So if you did get the top grade, and there were 100 students taking the class, you would
score in the 99th percentile. This means you had a score better than 99% of the people taking the
test. This is far different than your base 80% score.
When looking at a data set, percentiles can help better gauge the middle or median performance of
students, or of any type of data. Many students will cluster into the median area, earning percentiles
anywhere from 25 to 75. A few students will far surpass this, with percentiles in the 90s range. Even
when the student population or data set being tested is large, average and median scores are
computed into expected results, and can gauge the average desired performance of a student.
Percentiles can show us how most people are performing, as well as how each individual student is
performing.
Percentiles can further show if performance in certain areas is poor. If every student taking a test
misses the same question, or if most of the average students taking it miss it, this may suggest a few
things. The students may not understand the question, or they may need more instruction in this area.
In this way percentiles can also reflect how well prepared a test is. With increasingly
more standardized tests in the academic setting, percentiles have a way of weeding out bad
questions, when a large number of students don’t answer a question correctly.
Percentiles can be used to check testing in population groups. Say for example, a whole high school
in an urban neighborhood scores well below average. Even if a couple of people score well (called
outliers), the school is evidencing a couple of things. Either the children are not prepared properly to
take a test, or the test is not understood by the students because of cultural or language barriers. By
considering percentiles as well as percentage scores, schools can better address the needs of their
students in a holistic fashion.
/opt/scribd/conversion/tmp/scratch10056/39291534.doc -2-

It bears repeating that percentiles are a comparison score. The number of a percentile represents
how well or how poorly you did as compared to other students. It does not represent the number of
questions you answered correctly. If you score in the 70th percentile, you scored better than 70 out of
100 people who took the test. If you score in the 50th, read this as better than 50 people who took the
test.

STANDARD DEVIATION
Standard deviation is a statistical value used to determine how spread out the data in a sample are,
and how close individual data points are to the mean, or average, value of the sample. A standard
deviation of a data set equal to zero indicates that all values in the set are the same. A larger value
implies that the individual data points are farther from the average value.
In a normal distribution of data, also known as a bell curve, the majority of the data in the distribution
— approximately 68% — will fall within plus or minus one standard deviation of the statistical
average. This means that if the standard deviation of a data set is 2, for example, the majority of data
in the set will fall within 2 more or 2 less than the average. Roughly 95.5% of normally distributed data
is within two standard deviations of the mean, and over 99% are within three.
To calculate the standard deviation, statisticians first calculate the mean value of all the data points.
The mean, or average, is the sum of all the values in the data set divided by the total number of data
points. Next, the deviation of each data point from the average is calculated by subtracting its value
from the mean value. Each data point’s deviation is squared, and the individual squared deviations
are averaged together. The resulting value is known as the variance. Standard deviation is the square
root of the variance.
Typically, statisticians find the standard deviation of a sample from a population and use that to
represent the entire population. Finding the exact data for a large population is impractical, if not
impossible, so using a representative sample is often the best method. For example, if someone
wanted to find the number of adult men in the state of California who weighed between 180 and 200
pounds, he could measure the weights of a small number of men and calculate their average,
variance, and standard deviation and assume that the same values hold true for the population as a
whole.
In addition to the statistical analysis uses, standard deviation can also be used to determine the
amount of risk and volatility associated with a particular investment. Investors can calculate the
annual standard deviation of an investment’s returns and use that number to determine how volatile
the investment is. A larger standard deviation would imply a more risky investment, assuming that
stability was the desired result.

In probability theory and statistics, the standard deviation of a statistical population, a data set, or
a probability distribution is the square root of its variance. Standard deviation is a widely used
measure of the variability or dispersion, being algebraically more tractable though practically
lessrobust than the expected deviation or average absolute deviation.[citation needed]
It shows how much variation there is from the "average" (mean, or expected/budgeted value). A low
standard deviation indicates that the data points tend to be very close to the mean, whereas high
standard deviation indicates that the data is spread out over a large range of values.
For example, the average height for adult men in the United States is about 70 inches (178 cm), with
a standard deviation of around 3 in (8 cm). This means that most men (about 68 percent, assuming
a normal distribution) have a height within 3 in (8 cm) of the mean (67–73 in/170–185 cm), one
standard deviation. Whereas almost all men (about 95%) have a height within 6 in (15 cm) of the
mean (64–76 in/163–193 cm), 2 standard deviations. If the standard deviation were zero, then all
men would be exactly 70 in (178 cm) high. If the standard deviation were 20 in (51 cm), then men
/opt/scribd/conversion/tmp/scratch10056/39291534.doc -3-

would have much more variable heights, with a typical range of about 50–90 in (127–229 cm). Three
standard deviations account for 99.7% of the sample population being studied, assuming the
distribution is normal (bell-shaped).
In addition to expressing the variability of a population, standard deviation is commonly used to
measure confidence in statistical conclusions. For example, themargin of error in polling data is
determined by calculating the expected standard deviation in the results if the same poll were to be
conducted multiple times. The reported margin of error is typically about twice the standard deviation–
the radius of a 95% confidence interval. In science, researchers commonly report the standard
deviation of experimental data, and only effects that fall far outside the range of standard deviation
are considered statistically significant—normal random error or variation in the measurements is in
this way distinguished from causal variation. Standard deviation is also important in finance, where
the standard deviation on the rate of return on an investment is a measure of the volatility of the
investment.
The term standard deviation was first used[1] in writing by Karl Pearson[2] in 1894, following his use of
it in lectures. This was as a replacement for earlier alternative names for the same idea: for
example, Gauss used mean error.[3] A useful property of standard deviation is that, unlike variance, it
is expressed in the same units as the data. Note, however, that for measurements with percentage as
unit, the standard deviation will have percentage points as unit.
When only a sample of data from a population is available, the population standard deviation can be
estimated by a modified quantity called the sample standard deviation, explained below.

Basic examples
Consider a population consisting of the following eight values:

The eight data points have a mean (or average) value of 5:

To calculate the population standard deviation, first compute the difference of each data
point from the mean, and square the result:

Next divide the sum of these values by the number of values and take the square root to
give the standard deviation:

Therefore, the above has a population standard deviation of 2.

The above assumes a complete population. If the 8 values are obtained by random
sampling from some parent population, then computing the sample standard
deviation would use a denominator of 7 instead of 8. See the
section Estimation below for an explanation.