In: Statistics and Probability
Here is a sample dataset: 126.3 258.9 298.4 345.2 89.2 459.2 688.1 441.3 459.2 487.1 647.2 784.9 647.2 675.5
(1) Draw a stem - and - leaf display for this dataset.
(2) What is the mean, median, mode?
(3) What is the range, variance, standard deviation?
(4) What is Q1, Q3?
(5) Is the smallest and largest outliers? Why?
(6) What is the percentage falling within 1 standard deviation? Does it satisfy the Empirical Rule?
1)
stem =100 | |
leaf=10 | |
stem | leaf |
0 | 8 |
1 | 2 |
2 | 5 9 |
3 | 4 |
4 | 4 5 5 8 |
6 | 4 4 7 8 |
7 | 8 |
2)
mean = ΣX/n = 6407.700
/ 14 = 457.6929
Median=0.5(n+1)th value = 7.5th value
of sorted data
= 459.2
mode= highest frequency data = 459.2 , 647.2
3)
range=max-min = 784.9 -
89.2 = 695.700
sample variance = Σ(X - X̄)²/(n-1)=
603711.5493 / 13 =
46439.350
sample std dev = √ [ Σ(X - X̄)²/(n-1)] =
√ (603711.5493/13) =
215.498
4)
quartile , Q1 = 0.25(n+1)th value=
3.75th value of sorted data
= 288.525
Quartile , Q3 = 0.75(n+1)th value= 11.25th
value of sorted data
= 654.275
5)
IQR = Q3-Q1 = 365.8
1.5IQR = 548.63
lower bound=Q1-1.5IQR= -260.10
upper bound=Q3+1.5IQR= 1202.90
outlier =values outside lower bound and upper
bound
there is no outlier
6)
X̄ ± 1 * s = ( 242.19 ,
673.19 )
percentage falling within 1 standard deviation=9/14 = 64.29%
according to Empirical rule , 68% of data values lies within 1 std dev away from mean,
So, it approximately satisfies the Empirical rule.