2. STANDARDIZATION: WHAT IS IT?
STANDARDIZATION INVOLVES CONSISTENT FORMS OF MEASUREMENT AND INTERPRETATION, AN ATTEMPT
TO CONSIDER THE RELATIVE POSITION OF OBJECTS ON A SINGLE DIMENSION.
1. IQ (INTELLIGENT QUOTIENT)
2. SAT (SCHOLASTIC APTITUDE TEST )
3. LSAT (LAW SCHOOL ADMISSION TEST)
4. GMAT ( GRADUATE MANAGEMENT ADMISSION TEST)
5. GRE ( GRADUATE RECORD EXAM)
3. Y
X
40 55 70 85 100 115 130 145 160
𝝁
Figure 5.1. Hypothetical distribution of scores on an IQ test
Third Second First First Second Third
𝜎 𝜎 𝜎 𝜎 𝜎 𝜎
Below 𝜇 Below𝜇 Below 𝜇 Above 𝜇 Above 𝜇 Above 𝜇
Pop mean (𝜇) of 100
Standard deviation 𝜎15
110 1st 𝜎 around the mean
4. CONVERTING RAW SCORE INTO A
STANDARD SCORE
• A RAW SCORE IS ANY SCORE OR DATUM THAT
HAS NOT BEEN ANALYZED OR OTHERWISE
TRANSFORMED BY A STATISTICAL PROCEDURE
• A STANDARDIZED SCORE IS DERIVED FROM A
RAW SCORE. STANDARDIZED SCORES REPORT
THE RELATIVE PLACEMENT OF INDIVIDUAL
SCORES IN DISTRIBUTION AND ARE USEFUL FOR
VARIOUS INFERENTIAL STATISTICAL
PROCEDURES.
6. Z-SCORE
• A DESCRIPTIVE STATISTIC, THE Z SCORE INDICATES THE DISTANCE BETWEEN SOME OBSERVED SCORE (X)
AND THE MEAN OF A DISTRIBUTION IN STANDARD DEVIATION UNITS.
• THE Z-SCORE TELLS THIS: HOW MANY STANDARD DEVIATIONS AWAY FROM THE MEAN IS A GIVEN SCORE?
7. 35 40 45 50 55 60 65
- 3.0 - 2..0 - 1.0 0.0 + 1.0 +2.0 +3.0
Figure 5.2 Distribution of Raw Scores and Corresponding Z Scores Where 𝜇 = 50 𝐚𝐧𝐝 𝜎 = 5
Y
X
8. RELATIVE DIFFERENCE BETWEEN MEAN
Mean = 50
i.E., 55 – 50 = 5
Standard deviation is 5, therefore 5 ÷ 5 = + 1.0
i.E., 40 – 50 = -10
Standard deviation is 5, therefore -10.0 ÷ 5 = -2.0
9. KEY POINTS: Z-SCORE
• 1. THE MEAN OF ANY Z DISTRIBUTION IS ALWAYS 0
• 2. THE STANDARD DEVIATION OF ANY Z DISTRIBUTION IS
ALWAYS 1.0
• 3. Z SCORE IS (+) WHEN THE SCORE FALLS ABOVE THE
MEAN OF 0, IT IS (-) WHEN IT FALLS BELOW IT. THE ONLY
TIME A Z SCORE LACKS A SIGN IS WHEN IT IS EQUAL TO 0.
• 4. THE DISTRIBUTION OF Z SCORES WILL ALWAYS RETAIN
THE SHAPE OF THE DISTRIBUTION OF THE ORIGINAL
SCORES.
Z-SCORE
10. FORMULAS FOR Z-
SCORES
•Z = X - X‾/S
•X REPRESENTS RAW SCORE
•X‾ IS THE SAMPLE MEAN
•S IS SAMPLE’S STANDARD
DEVIATION
•TRANSFORMATION FORMULA
BACK TO SAMPLE’S RAW SCORE
•X = X‾ + Z (S)
Z SCORE CAN BE CALCULATED FROM SAMPLE
DATA
11. Z-SCORE
•Z = X - 𝜇/𝜎
•X IS RAW SCORE
• 𝜇 IS MEAN OF THE POPULATION
• 𝜎 IS THE STANDARD DEVIATION
•TRANSFORMATION FORMULA
BACK TO POPULATION-BASED Z
SCORE
•X = 𝜇 + Z (𝜎)
POPULATION DATA
12. -2 - 1 0 + 1 + 2
Y
X
Figure 5.3 Bell-curve to represent a Distribution of z-scores
13. FORMULA OF THE SHAPE OF NORMAL
DISTRIBUTION
f(𝑥) =
1
√2𝜋𝝈2 𝑒‾
𝑥−𝜇 ²
2𝜎²
Relative frequency or function of any score (x) is dependent upon the population
mean (𝝁) and variance (𝝈𝟐), the constant 𝝅 (which is ≅
𝟑. 𝟏𝟒𝟔), 𝐚𝐧𝐝 𝐭𝐡𝐞 𝐜𝐨𝐧𝐬𝐭𝐚𝐧𝐭 𝐞 (𝐭𝐡𝐞 𝐛𝐚𝐬𝐞 𝐨𝐟 𝐭𝐡𝐞 𝐧𝐚𝐭𝐮𝐫𝐚𝐥 𝐥𝐨𝐠𝐚𝐫𝐢𝐭𝐡𝐦, 𝐰𝐡𝐢𝐜𝐡 𝐢𝐬 ≅
𝟐. 𝟕𝟏𝟖𝟑). In other words, if the relative frequencies of X were entered into the
equation, we would be able to see how they must form the now familiar normal
curve.
14. STANDARD DEVIATION REVISITED: THE
AREA UNDER THE NORMAL CURVE
Y
X
34.1
3%
13.59%
2.15%
0.500.50
−∞
+∞
Z =-3.0 z = -2.0 z = -1.0 z = 0.0 z = +1.0 z = +2.0 z = +3.0
𝜎 𝜎 𝜎 𝜎 𝜎 𝜎 𝜎68
%
95%
15. Fig. 5.4, on either side of the mean 0 is one standard deviation interval equal to 34.13% of the
area under normal curve (i.e., 2 x 34.14% = 68.26, the available area under the curve).
The area between the first and second standard deviation on either side of the mean is equal to
13.59% (i.e., 2 x 13.58% = 27.18% of the available area)
In the third standard deviation from the mean resides 2.15% of observations (2 x 2.15% = 4.30%
of the available area.
If you add the total area accounted for under the curve in Figure 5.4 – you have accounted for
99.74% of the available observations or z scores.
Under Normal Distribution Curve
16. Measure Raw score Pop. parameters Z-Score
Depression 80 𝜇= 110, 𝜎 = 15 -2.00
Self-esteem 90 𝜇 = 75, 𝜎= 8 +1.88
Life-satisfaction 25 𝜇 = 40, 𝜎= 5 -3.00
Fig.5.1 Scores on three hypothetical measures of psychological well-being
A. Z score for client’s depression level (z = -2.00) is relatively far below the mean, which
indicates a low likelihood of depression (i.e., higher scores reflect a greater incidence
of depression).
B. Z score of Life-satisfaction (z = -3.00) is not in the desired direction– the client is
clearly dissatisfied with salient aspects of his life– as it is the three standard
deviations below the mean.