Você está na página 1de 4

Standar Deviasi

Standard deviation is useful for describing a data set by measuring the extent to which the individual observations are spread out around their mean. There are at least two additional applications for the standard deviation.
Chebyshevs Theorem Appropriate only if the distribution meets specific conditions of normality.

Kemiringan dan Penggunaan Standar Deviasi

Chebyshevs Theorem (Tchebysheffs Theorem)


Formulated by the Russian mathematician P.L. Chebyshev (1821-1894). 1 It states that for any data set, at least 1 K 2 percent of the observations lie within K standard deviations of the mean, where K is any number greater than 1. Dirumuskan
1 1 K2

K = three standard deviation above the mean to three standard deviation below the mean, then at least
1 1 = 88.89 % 32

of all the observation will be within that interval. Example : Passenger for P&P avereged 78.3 per day, a standard deviation of 10.8. In order to schedule times for a new route P&P opened, management wants to know how often the number of passenger is within K = two standard deviation of the mean, and what that interval is.

Answer : If we move two standard deviation, 21.6 passengers above and below the mean of 78.3. We would have and interval 78.3 21.6 = 56.7 to 78.3 + 21.6 = 99.9 passenger. We can then be certain at least
1 1 = 75 % 22

Normal Distribution
Standard deviation can be used to draw certain conclusions if the data set in question is normal distributed. Normal distribution is a distribution of continuous (not discrete) data that produces a bell-shaped, symmetrical curve. In normal distribution, the mean, median, and mode are all equal. Observation closer to middle occur with increasing frequency.

of the time, the number of daily passenger was between 56 and 99 Interpretation : On at least 75 percent of the days, the number of passengers was between 56 and 99. This provides the management of P&P with valuable information regarding how many passengers to prepare for in flight operations.

Normal Distribution
One half of the observations are above the mean and one half are below it. This means that one half of the area under the curve is to the left of the mean and one half to the area under the curve is to the right of the mean. If the observations are highly dispersed, the bell-shaped curve will be flattened and spread out. (berarti standard deviasinya semakin besar)

Empirical Rule
The empirical rule specifies that
68.3 percent of the observations lie within plus or minus one standard deviation of the mean. 95.5 percent of the observations lie within plus or minus two standard deviation of the mean. 99.7 percent of the observations lie within plus or minus three standard deviation of the mean.

Mean 10, standar deviasi 2, 1000 kali percobaan.


683 percobaan jatuh diantara 8 hingga 12. 997 percobaan jatuh diantara 4 hingga 16.

Skewness
Not all distribution are normal. Skewness : left or right. Skew right if mode > median > mean. Skew left if mean < median < mode. Mode : observation occuring with the greatest frequency. Its therefore at the peak of the distribution. Pearsonian coefficient of skewness

Example
Diberikan rata-rata 78.3, standar deviasi 10.8, dan median 77.9, selidiki apakah data tersebut berdistribusi normal, miring ke kanan, atau miring ke kiri ?

P=

3(X median ) s

P < 0 : skewed left P > 0 : skewed right P = 0 : normally distributed

Koefisien Variansi
Jika terdapat perbedaan rata-rata atau banyaknya data, ukuran standar deviasi kurang tepat untuk digunakan. Koefisien variansi merupakan ukuran relatif dari penyebaran data.
CV = s 100 % X

Example
Markus Boggs computed the average price of a certain stock to be $81.29, with standard deviation of $21.58. Assume that a second stock has recorded the following closing prices : $147, $120, $115, $110, $100, $73, and $105. He wishes to compare the variation in the prices of these two stocks.

Answer
Rata-rata stock kedua $110 dan standar deviasinya $22.3 Stock kedua memiliki standard deviasi dan rata-rata yang lebih tinggi dari stock kesatu. In general, he is working with large numbers in the second data set. CV1 = 26.55 dan CV2 = 20.27 Interpretation : Disamping the larger standard deviation of the second stock, its prices, relative to their mean, deviate less than do the prices of the first stock relative to their mean. Markus can therefore conclude that the price of the second stock is less volatile than the first in a relative sense.

Furthermore, since the coefficient of variation is expressed as a percentage, it can be used to compare measures of dispersion expressed in different units.

Você também pode gostar