FIGURE 4 The Standard DeviationSTEPS IN COMPUTING THE STANDARD DEVIATION- Compute the mean.
- Subtract the mean from each score.
- Square the resulting difference for each score.
- Total up the squared differences to get the sum of squares.
- Divide the sum of squares by the number of cases to get the variance.
- Take the square root of the variance, which is the standard deviation.
EXAMPLE OF COMPUTING THE STANDARD DEVIATION
[8 respondents, variable = years of schooling]
Score Score – Mean Squared (Score – Mean)15 15 – 12.5 = 2.5 6.25
12 12 – 12.5 =0.5 .25
12 12 – 12.5 =0.5 .25
10 10 – 12.5 =2.5 6.25
16 16 – 12.5 = 3.5 12.25
18 18 – 12.5 = 5.5 30.25
8 8 – 12.5 = 4.5 20.25
9 9 – 12.5 = –3.5 12.25
Mean 15 + 12 + 12 + 10 + 16 + 18 + 8 + 9 =100, 100/8 =12.5
Sum of squares 6.25 + .25 + .25 + 6.25 + 12.25 + 30.25 + 20.25 + 12.25 = 88
Variance =Sum of squares/Number of cases =88/8 = 11
Standard deviation Square root of variance = 11 =3.317 years.
Here is the standard deviation in the form of a formula with symbols.
Symbols:
X=SCORE of case Σ=Sigma (Greek letter) for sum, add together
X ̄ ̄=MEAN N=Number of cases
Formula:a
Standard deviation
S(X –X) ̄ ̄^2
N–1aThere is a slight difference in the formula depending on whether one is using data for the
population or a sample to estimate the population parameter.
ANALYSIS OF QUANTITATIVE DATAa standard deviation of .50, whereas the mean
grade-point average at Queens College is 3.24 with
a standard deviation of .40. The employer suspects
that grades at Queens College are inflated. Suzette
from Kings College has a grade-point average of
3.62; Jorge from Queens College has a grade-point
average of 3.64. Both students took the same
courses. The employer wants to adjust the gradesfor the grading practices of the two colleges (i.e.,
create standardized scores). She calculates z-scores
by subtracting each student’s score from the mean
and then divides by the standard deviation. For
example, Suzette’s z-score is 3.62 2.62 1.00/.50
2, whereas Jorge’s z-score is 3.64 3.24.
.40/.40 1. Thus, the employer learns that Suzette
is two standard deviations above the mean in her