LIST OF FORMULAE
Descriptive Statistics for Grouped Data
Sample Mean Sample Variance Mode Median
n
x f (x − x ) f 2
1
f
x= or
i =1 xf
i i s2 =
( f ) − 1 x̂ = L + c
x = L+c 2
− Fj −1
n
f 1 + 2
f fj
( xf )
i 2
i =1 1
( f ) − 1
= x f−
2
f
Descriptive Statistics for Ungrouped Data
Sample Mean Sample Variance Sample Standard Deviation
1 n 2 1 n
2
1 n 1 n 2
s = s2
x= xi s2 = i ( x − x ) = i n
x − x i
n i =1 n − 1 i =1 n − 1 i =1 i =1
Miscellaneous
Interquartile Range Lower and Upper Fences Z-score (Population) Z-score (Sample)
Upper Fence = Q3 + 1.5(IQR) X − X −x
IQR = Q 3 − Q 1 Z= Z=
Lower Fence = Q1 − 1.5(IQR) s
Probability Distributions (PD)
Binomial PD Poisson PD Normal PD
e− x
X ~ B(n, p); P( X = x) = nCx p x (1 − p )
n−x
X ~ Po (); P( X = x) = X ~ N(, 2 )
x!
Sampling Distributions
Sample Mean Sample Proportion
2 p(1 − p)
x ~ N , ˆ ~ N p,
p
n n
Difference between Two Sample Means Difference between Two Sample Proportions
12 2 2 p (1 − p1) p2 (1 − p2 )
x1 − x 2 ~ N 1 − 2 , + ˆ1 − p
p ˆ2 ~ N p1 − p2 , 1 +
n1 n2 n1 n2
Confidence Interval for Single Population
Confidence Interval for Proportion
pˆ(1 − pˆ) x
pˆ z 2 ˆ=
where p
n n
Confidence Interval for Mean
is known is unknown, n 30 is unknown, n 30
s s
x z 2 x z 2 x t 2, n −1
n n n
* Institut Matematik Kejuruteraan * 2020*
LIST OF FORMULAE
Sample Size
For estimating population proportion For estimating population mean
2 2 2
z x z 2 z 2 s
n = /2 pˆ(1 − pˆ) where pˆ = n = or n = if unknown
E n
E E
E = margin of error
Hypothesis Testing for Single Population
Test Statistic for Proportion
ˆ − p0
p x
Z= N ( 0,1) , where p
ˆ=
p0 (1 − p0 ) n
n
Test Statistics for Mean
x − 0
i. known Z= N ( 0,1)
n
x − 0
ii. unknown, n 30 Z= N ( 0,1)
s
n
x − 0
iii. unknown, n < 30 t= tn −1
s
n
Confidence Interval for Two Populations
Confidence Interval for Difference between Two Proportions
ˆ1 (1 − p
p ˆ1 ) ˆ2 (1 − p
p ˆ2 )
( pˆ1 − pˆ2 ) z 2 n1
+
n2
Confidence Interval for Difference between Two Means
12 2 2
i. ( 1 , 2 ) known (x − x 2 ) z 2 +
2 2
1
n1 n2
s12 s2 2
ii. ( 1 , 2 ) unknown, , n1 and n2 30 (x − x 2 ) z 2 +
2 2 2 2
1
1 2
n1 n2
s12 s2 2
iii. ( ,
2
1
2
2 ) unknown, 2
1
, n1 and n2 30
2
2 (x 1
− x 2 ) tv , 2 + ; v = min ( n1 − 1, n2 − 1)
n1 n2
1 1
iv. ( 1 , 2 ) unknown, 12 = 22 , n1 and n2 30 ( x1 − x2 ) z 2Sp +
2 2
n1 n2
1 1
v. ( 12 , 22 ) unknown, 12 = 22 , n1 and n2 30 (x 1
− x 2 ) tv , 2 Sp + ; v = n1 + n2 − 2
n1 n2
where Sp =
(n 1
− 1) s12 + ( n2 − 1) s22
n1 + n2 − 2
* Institut Matematik Kejuruteraan * 2020*
LIST OF FORMULAE
Hypothesis Testing for Two Populations
Test Statistic for Difference between Two Proportions
ˆ2 ) − ( p1 − p2 )
ˆ1 − p
(p x1 + x 2
Z= where pˆ = , qˆ = 1 − pˆ
1 1 n1 + n2
ˆˆ +
pq
n1 n2
Test Statistics for Difference between Two Means
i. ( 2
1
, 22 ) known Z=
(x 1
− x 2 ) − ( 1 − 2 )
N ( 0,1)
12 22
+
n1 n2
(2 2
)
ii. 1 , 2 unknown, 12 22 , n1 and n2 30 Z=
(x 1
− x 2 ) − ( 1 − 2 )
N ( 0,1)
s12 s2 2
+
n1 n2
iii. ( 1 , 2 ) unknown, 1 2 , n1 and n2 30
2 2 2 2
t=
(x 1
− x 2 ) − (1 − 2 )
tv ;
s12 s22
+
n1 n2
v = min ( n 1 − 1, n2 − 1)
(2 2
)
iv. 1 , 2 unknown, 12 = 22 , n1 and n2 30 Z=
(x 1
− x 2 ) − ( 1 − 2 )
N ( 0,1)
1 1
Sp +
n1 n2
v. ( 2
, 22 ) unknown, 12 = 22 , n1 and n2 30 t=
(x 1
− x 2 ) − (1 − 2 )
tv ; v = n1 + n2 − 2
1
1 1
Sp +
n1 n2
where Sp =
(n1
− 1) s12 + ( n2 − 1) s22
n1 + n2 − 2
Analysis of Variance
One-Way ANOVA (CRD)
Y••2
) = Yn Y••2
ni ni 2
( ) = y
k k
(
k k
SST = y ij − Y
2
SSTR = ni y i − Y
2
2
ij
− i
−
i =1 j =1 i =1 j =1 N i =1 i =1 i
N
k ni k
SSE = ( y ij − y i ) = ( ni − 1) s
2
2
i
i =1 j =1 i =1
k = number of treatments, n = sample size for each treatment
Two-Way ANOVA without Replication (RCBD)
Y••2 1 k 2 Y••2
( ) = y ( )
k n k n k
SST = y ij − Y SSTR = ni y i − Y Yi• − kn
2 2
2
ij
− =
i =1 j =1 i =1 j =1 N i =1 n i =1
1 Y 2
( )
n n
( )
k n
SSBL = k y • j − Y Y•2j − kn
2
SSE = y ij − y i • − y • j + Y
2
= ••
= SST − SSTR − SSBL
j =1 k j =1 i =1 j =1
k = number of treatments, n = number of blocks
* Institut Matematik Kejuruteraan * 2020*
LIST OF FORMULAE
Two-Way ANOVA with Replication (Two-Factors Experimental Design)
1 a 2 Y••• 2
( )
a
a b r
Y2
( ) SSA = br y i •• − Y = Yi•• − abr
a b r 2
SST = y ijk − Y = y − •••
2
2
ijk
i =1 j =1 k =1 i =1 j =1 k =1 abr i =1 br i =1
1 b 2 Y2 1 a b 2 Y••• 2
( )
a
( )
b
SSAB = r y ij • − y i •• − y • j • + Y = Yij • −
2
SSB = ar y • j• − Y
2
= Y• j• − ••• − SSA − SSB
j =1 ar j =1 abr i =1 r i =1 j =1 abr
a b r
SSE = ( y ijk − y ij • ) = SST − SSA − SSB − SSAB
2
i =1 j =1 k =1
Nonparametric Tests
Mann-Whitney Statistic
T1 = R 1
where R1 = ranks from group with smaller sample size
T1* = n1 ( n1 + n2 + 1) − T1 , TU = n1 ( n1 + n2 + 1) − TL , TL = Critical value from Mann-Whitney Table
Kruskal-Wallis Statistic
12 k
Ri2
H= − 3 ( N + 1)
N ( N + 1)
i =1
ni
where Ri = sum of ranks of i-th group, N = n 1 +n 2 +... + n k , k = number of groups
Simple Linear Regression
Linear Regression Model: ŷ = ˆ0 + ˆ1x
2
1 n
2
n n
1 n
n
1 n n
Sxx = xi 2 − xi Syy = y i − y i
2
Sxy = xi y i − xi y i
i =1 n i =1 i =1 n i =1 i =1 n i =1 i =1
n
n n n n n
(x − x )( y i − y ) n xi y i − xi y i y i − ˆ1 xi
= i =1 i =1 i =1 = Sxy
i
ˆ1 = i =1
n 2 ˆ0 = i =1 i =1
= y − ˆ1x
Sxx n
(x − x) n
2 n
i n x i − x i
2
i =1
i =1 i =1
(S )
2
SSR
, SSR = ˆ1Sxy , SST = Syy
xy
r 2
= =
Sxx Syy SST
Test Statistic: t = r n − 22 tn − 2
1− r
* Institut Matematik Kejuruteraan * 2020*
LIST OF FORMULAE