Vous êtes sur la page 1sur 7

Alphabetical Statistical Symbols:

Symbol Text Meaning Formula Link to Glossary


Equivalent (if appropriate)
a Y- intercept of least a = y − b x , for line y = a + bx Regression: y on x
square regression line
b Slope of least
squares regression b=
∑ ( x − x)( y − y) for line y = a + bx
Regression: y on x
2
line ∑ ( x − x)
B (n, p) Binomial Discrete probability If X follows B (n, p) then, Binomial Distribution
distribution with distribution for the n
P (X = r) = C r p r (1 − p) n − r ,
parameters n and probability of number
p of successes in n
independent random Where, 0 < p <1,
trials under the r = 0,1,2, ...n
identical conditions.
c Confidence level c = P(− z c < Normal (0,1) < z c ) Confidence interval
n n-c-r Combinations n!
C r
(number of
n
C = , where n ≥ r
r
r!(n − r )!
combinations of n
objects taken r at a
time)
C n-c-r Combinations n!
n, r
(number of C n,r = r!(n − r )! , where n ≥ r
combinations of n
objects taken r at a
time)
Cov (X, Y) Covariance Covariance between Cov (X) =E [(X-E (X))(Y- E (Y)]
between X and Y X&Y
CV Coefficient of S tan dard Deviation
variation CV= .
Arithmatic mean
df Degree(s) of freedom
Symbol Text Meaning Formula Link to Glossary
Equivalent (if appropriate)
E Maximal error σ
tolerance E = zc for large samples.
n

E (f (x)) Expected value of E (f (x)) = ∑ f ( x) P ( x)


f (x)
f Frequency f = number of times score.
F F-distribution χ 12 F-distribution,
variable n1 Hypothesis testing for
F= where n1 and n2 are the equality of 2
χ 2
2
variances.
n2
corresponding degrees of freedom.
F (x) or F x Distribution function x
Fx = ∫ f x dx
−∞
f (x) or f x Probability mass Depends on the distribution.
function f x ≥ 0 & ∫ f x dx = 1.
x
H0 H-not Null hypothesis. The null hypothesis is the hypothesis Testing of hypothesis
about the population parameter.
H1 H-one Alternate hypothesis. An alternate hypothesis is constructed in Testing of hypothesis
such a way that it is the one to be
accepted when the null hypothesis must
be rejected.
IQR Interquartile range IQR = Q - Q Measures of central
3 1
tendency.
MS M-S Mean square SS Analysis of variance
MS= (ANOVA)
df
n Sample size. n = number of units in a sample.
N Population size N = Number of units in the population.
Symbol Text Meaning Formula Link to Glossary
Equivalent (if appropriate)
P n, r
n-p-r Permutation (number
of ways to arrange in P =
n!
, where n ≥ r
n,r
(n − r )!
order n distinct
objects taking them r
at a time)
Pr n-p-r Permutation (number n!
n
of ways to arrange in n Pr = , where n ≥ r
(n − r )!
order n distinct
objects taking them r
at a time)
p̂ p-hat Sample proportion number of success Binomial distribution
pˆ = .
number of trials
P (A | B) Probability of A Conditional P( A ∩ B)
given B probability P (A | B) =
P( B)
P (x) Probability of x Probability of x No.of favorable outcomes
P (x) =
Total no.of outcomes
p-value The attained level of P value is the smallest level of
significance. significance for which the observed
sample statistic tells us to reject the null
hypothesis.
Q Probability of not q=1–p
happening of the
event
Q 1
Q-one First quartile Q = Median of the lower half of the Measures of central
1
tendency
data that is data below median.
Q 2
Q-two Second quartile
Or Median
Q2 = Central value of an ordered data. Measures
tendency
of central

Q 3
Q-three Third quartile Q3 = Median of the upper half of the Measures
tendency
of central
data that is data above the median.
Symbol Text Meaning Formula Link to Glossary
Equivalent (if appropriate)
R Sample Correlation Co var iance( X , Y )
coefficient r=
[ SD( X )] * [ SD(Y )]
2 r-square Coefficient of 2
r
2
r = (Correlation coefficient )
determination
R2 r-square Multiple correlation mean square error
coefficient R2 = 1−
S y2
S Sample standard
deviation s=
∑ (x − x) 2

for ungrouped data.


Measures of
dispersion
n −1

s=
∑ f (x − x) 2

for grouped data.


(∑ f ) − 1
s 2 S-square Sample variance 2 ∑ (x − x) 2 Measures of
s =
n −1
for ungrouped data. dispersion

2 ∑ f (x − x) 2

s = (∑ f ) − 1 for grouped data

S e2 s-e- square Error variance sum of squares of residuals


S e2 = .
n
SD Sample standard
deviation s=
∑ (x − x) 2

for ungrouped data.


n −1

s=
∑ f (x − x) 2

for grouped data.


(∑ f ) − 1
skb Bowley’s coefficient (Q3 − Q 2) − (Q 2 − Q1) Measures of skew
of skewness skb = ness
(Q3 − Q1)
skp Pearson’s coefficient Mean − Mode Measures of skew
of skewness skp = ness
S tan dard Deviation
Symbol Text Meaning Formula Link to Glossary
Equivalent (if appropriate)
SS x Sum of Squares SS x = ∑ ( x − x) 2 for ungrouped data.
SS x = ∑ f ( x − x) 2 for grouped data.
t Student’s t variable. Normal (0,1) t-distribution
t=
χ n 2
n

tc t critical The critical value for t c =Number such that the area under the Testing of hypothesis
a confidence level c. t distribution for a given number of
degrees of freedom falling between
− t c and t c is equal to c.
Var (X) Variance of X Variance of X Var (X) = E (X- µ ) 2
x Independent variable Eg. In the study of, yield obtained & the
or explanatory irrigation level, independent variable is,
variable in regression X= Irrigation level.
analysis
x x-bar Arithmetic mean or
x=
∑x for ungrouped data.
Measures of central
Average of X scores. tendency
n

x=
∑ fx for grouped data.
∑f
y Dependent variable Eg. In the study of, yield obtained & the
or response variable irrigation level, dependent variable is,
in regression analysis Y= Yield obtained.
Z Z-score Standard normal x−µ Standard normal
variable z= , where X follows distribution
σ
(Normal variable Normal ( µ , σ ).
with mean = 0 & SD
= 1)
zc z critical The critical value for z c = Number such that the area under Testing of hypothesis
a confidence level c. the standard normal curve falling
between − z c and z c is equal to c. Confidence interval
Greek Statistical Symbols:

Symbol Text Meaning Formula Link to Glossary (if


Equivalent appropriate)
α Alpha Type I error or α = P [Rejecting the null hypothesis | Hypothesis Testing
Level of Significance. Null hypothesis is true].
β Beta Type II error or β = P [Accepting the null hypothesis | Hypothesis Testing
Power of the test. Null hypothesis is False].
χ 2
Chi-square Chi-square distribution χ = Sum of n independent Standard Chi-square distribution.
2

normal variables
χ 2
Chi-square Chi-square distribution
χ2 = ∑
(O − E ) 2
where O is the
Goodness of fit test
E
observed frequency and E is the
expected frequency.
Or
(n − 1) s 2
χ2 = (?)
σ
2

Γ(n) Gamma-n Gamma function Γ(n) = (n-1) !


λ Lambda Parameter used for λ = Mean of Poisson distribution Poisson distribution
Poisson distribution
µ Mu Arithmetic mean or
µ=
∑x
Average of the
N
population.
µ = E (x) = ∑ xP(x)
Symbol Text Meaning Formula Link to Glossary (if
Equivalent appropriate)
µ r
Mu-r rth central moment µ r
= E [(X- µ )r] Measures of central tendency.

µ 'r Mu-r-dash rth Raw moment µ 'r = E (Xr) Measures of central tendency.
ρ Rho Population correlation Co var ianvce( X , Y )
coefficient ρ=
SD( X ) * SD(Y )
∑ Sigma Summation ∑ x = Sum of x scores.
σ Sigma Population Standard
Deviation σ =
∑ (x − µ) 2 Measures of dispersion
N
σ= E[( x − µ ) 2 ] = ∑ ( x − µ ) P ( x)
2

σ Sigma square Population variance ∑ (x − µ) Measures of dispersion


2 2

σ= 2

Mathematical Statistical Symbols:

Symbol Text Meaning Formula Link to Glossary


Equivalent (if appropriate)
! Factorial Product of all integers up n! = n (n-1) (n-2) …….. 1.
to the given number 0! = 1
c Complement not For example: A is not A
c

∪ Union or For example:(A ∪ B) is happening of


either event A or event B
∩ Intersection And For example: (A ∩ B) is happening of
both event A and event B