100 Formulas of Stats

Formula Marathon for Maths, LR and Stats by CAPRANAV
› Class Limits (CL) : CL is the minimum and maximum value the class interval may
contain
CL = UCL – LCL
UCL : Upper Class Limit
LCL : Lower Class Limit
1
stats Formula marathon
QUIZ NO. 1 CA Foundation Paper 3
Class Boundary (CB) : These are actual class limits of a class interval
› In case of Mutually Exclusive Classification

Class Boundary = Class Limit
UCB = UCL and LCB = LCL
› In case of Mutually Inclusive Classification
UCB = UCL + 0.5

LCB = LCL - 0.5
2
Mid Point of Class Interval : average of LCL and UCL or average of LCB and UCB
LCL+UCL
2
LCB+UCB
2
Mid point is also called as Mid Value of a class or Class Mark
3
Class Length / Width of Class / Size of Class
UCB - LCB
4
Frequency Density
Frequency of a class
Class length of that class
5
Relative Frequency
Frequency of class
Total Frequency of distribution
Percentage Frequency
Frequency of class
×100
Total Frequency of distribution
6
Arithmetic Mean of Discrete Distribution:
x1 + x2 + x3 + ... + xn x
x= x=
n n
7
Arithmetic Mean in case of Frequency Distribution :
 fx
x=
N
Here,
𝑥 will be equal to mid point of class interval when frequency distribution is grouped.
N is number of observations which is also equal to total of all frequencies.
8
AM using Assumed Mean / Step Deviation Method
 fd
x = A+ C
N
where d = x − A
C
A = assumed mean, C = class length
9
Property of AM
the algebraic sum of deviations of a set of observations from their AM is zero
( x − x ) = 0
10
Property of AM
Combined AM
– If there are two groups containing 𝑛1 & 𝑛2 observations with AMs as 𝑥1 & 𝑥2
respectively then the combined AM is given by
n1 x1 + n2 x2
xc =
n1 + n2
11
Median in case of discrete distribution

› above form
– If n = odd, then middle term
– If n = even, average of two middle terms
Same formula will be used for Simple Frequency distribution

› ula
12
Median in case of Grouped Frequency Distribution

– Step 1: Prepare a less than type cumulative frequency distribution.
– Step 2: Calculate N/2 and check between which class boundaries it falls and call it as
Median Class.
– Step 4: Find 𝑙1 = LCB of Median Class, 𝑁𝑢 as Cum Freq. of Median Class,

𝑁𝑙 as Cum. Freq. of Pre Median Class, C = Class length of Median Class
– Step 3: Apply the below formula

 N 
 2 − Nl 
Me = l1 +  C
13
 Nu − Nl 
 

Property of Median
For a set of observations, the sum of absolute deviations is minimum, when the
deviations are taken from the median.
14
Quartiles (in case of discrete observations)
Quartiles
th
 1
Q1 =  (n + 1)   term
 4
th
 2
Q2 =  (n + 1)   term
 4
th
 3
Q3 =  (n + 1)   term
 4
15
Deciles (in case of discrete observations)
Deciles
th
 1
D1 =  (n + 1)   term
 10 
th
 2
D2 =  (n + 1)   term
 10 
th
 9
Q9 =  (n + 1)   term
 10 
16
Percentiles (in case of discrete observations)
Percentiles
th
 1 
P1 =  (n + 1)   term
 100 
th
 2 
P2 =  (n + 1)   term
 100 
th
 99 
P99 =  (n + 1)   term
 100 
17
Quartiles (Grouped FD)
 N 
– For first Quartile 𝑸𝟏  4 − Nl 
› Find 𝑄1 class Q1 = l1 +  C
› Use Formula :  Nu − Nl 
 
 3N 
– For third Quartile 𝑸𝟑  4 − Nl 
› Find 𝑄3 class Q3 = l1 +  C
 Nu − Nl
18
› Use Formula : 
 

› Deciles (Grouped FD)
– For first Decile 𝑫𝟏  N 

› Find 𝐷1 class  10 − N l 
› Use Formula: D1 = l1 +  C
 Nu − Nl 
 
– For ninth Decile 𝑫𝟗  9N 

› Find 𝐷9 class  10 − N l 
› Use Formula: D9 = l1 +  C
 Nu − Nl 
 
19
› Percentiles (Grouped FD)
– For first Percentile 𝑷𝟏  N 

› Find 𝑃1 class  100 − N l 
› Use Formula:
P1 = l1 +  C
 Nu − Nl 
 
– For 99th Percentile 𝑷𝟗𝟗  99 N 

› Find 𝑃99 class  10 − N l 
› Use Formula: P99 = l1 +  C
 Nu − Nl 
 
20
Mode in case of discrete observation

Observation repeating for maximum no. of times/ max frequency
› When all observations have same frequency : No Mode

› When two observations have max frequency : Bimodal Observation
› In general, if we have two or more modes : Multi Modal Observation
21
› Mode in case of grouped frequency distribution

– First find modal class i.e. class with highest frequency
– Now, Find
› 𝑓0 = frequency of the modal class,
› 𝑓−1 = frequency of pre modal class,
› 𝑓1 = frequency of the post modal class
– Apply formula
 f 0 − f −1 
Mo = l1 +  C
 2 f 0 − f −1 − f1 
22
Relationship between Mean, Median and Mode

In case of symmetrical Distribution
Mean = Median = Mode
23
Relationship between Mean, Median and Mode

In case of moderately skewed distribution
Mean – Mode = 3 (Median – Median)
24
Geometric Mean (in case of discrete positive observations)
G = ( x1  x2  ...  xn )
1/ n
25
Geometric Mean (in case of frequency distribution)
𝑓1 𝑓2 𝑓3 𝑓𝑛 1/𝑁
𝐺 = (𝑥1 × 𝑥2 × 𝑥3 × ⋯ × 𝑥𝑛 )
26
Harmonic Mean (in case of discrete observations)
𝑛
𝐻=
Σ(1ൗ𝑥)
27
Harmonic Mean (in case of frequency distribution)
𝑁
𝐻=
𝑓ൗ
Σ( 𝑥)
28
Combined HM
𝑛1 +𝑛2
𝑥ҧ𝑐 = 𝑛 𝑛2
1
+
𝐻1 𝐻2
29
› Relationship between AM, GM and HM

When to use Relationship
When all the observations are same AM = GM = HM
When all the observations are distinct AM > GM > HM
In General AM ≥ GM ≥ HM
30
Range (in case of Discrete Observations)
L– S
L = Largest Observation
S = Smallest Observation
31
Range (in case of Grouped FD)
L– S
L = UCB of last class interval
S = LCB of first class interval
32
Coefficient of Range
L−S
 100
L+S
33
Mean Deviation (in case of discrete observations)
1
𝑀𝐷𝐴 = Σ 𝑥 − 𝐴
𝑛
Here A is mean or median or mode as given in question
34
Mean Deviation (in case of grouped frequency distributions)
1
𝑀𝐷𝐴 = Σ𝑓 𝑥 − 𝐴
𝑁
Here A is mean or median or mode as given in question
35
Coefficient of Mean Deviation
Mean Deviation about A

× 100
A
36
Standard Deviation (in case of discrete observations)
( x − x ) 2
 x = SDx =
n
x 2
−(x)
2
 x = SDx =
n
37
Standard Deviation (in case of grouped frequency observations)
 f (x − x ) 2
 x = SDx =
N
 fx 2
−(x)
2
 x = SDx =
N
38
Coefficient of Variation
SDx
 100
x
39
For any two numbers, SD = half of range
|a −b|
SD =
2
40
› Standard Deviation of first n natural numbers
n −1 2
s=
12
41
Combined SD
n s + n2 s2 + n d + n2 d 2
2 2 2 2
SDc = 1 1 1 1
n1 + n2
d1 = xc − x1
d 2 = xc − x2
42
Property of SD
If all the observations are constant, SD is Zero
43
Property of SD
› No effect of change of origin but affected by change of scale in the magnitude
(ignore sign)
44
Quartile Deviation
Q3 − Q1
QDx =
2
45
Coefficient of Quartile Deviation
Q3 − Q1
 100
Q3 + Q1
46
Relationship between SD, MD, QD
For a moderately skewed distribution
4 SD = 5MD = 6QD
SD : MD : QD = 15 :12 :10
47
Basic formula of Probability
𝑛𝑜. 𝑜𝑓 𝑓𝑎𝑣𝑜𝑟𝑎𝑏𝑙𝑒 𝑒𝑣𝑒𝑛𝑡𝑠 𝑡𝑜 𝐴

𝑃 𝐴 =
𝑇𝑜𝑡𝑎𝑙 𝑛𝑜. 𝑜𝑓 𝑒𝑣𝑒𝑛𝑡𝑠
48
Odds in Favor of Event A
no. of favorable events

no. of unfavorable events
49
› Odds against an Event
no. of unfavorable events

no. of favorable events
50
› No. of total outcome of a random experiment
If an experiment results in p outcomes and if it is repeated q times then
Total number of outcomes is
q
p
51
Relative Frequency Probability
no. of times the event occurred during experimental trials fA

Relative Frequency = = n
total no. of trials
Probability by this method is defined as

𝑓𝐴
𝑃 𝐴 = lim
𝑛→∞ 𝑛
52
› Set Based Probability
no.of sample points in A 𝑛(𝐴)

P A = =
no.of sample points in S 𝑛(𝑆)
53
Addition Theorem 1
In case of two mutually exclusive events A and B
P A∪B = P A+B = P A or B = P A + P B
54
Addition Theorem 2
In case of two or more mutually exclusive events
𝑃 𝐴1 ∪ 𝐴2 ∪ 𝐴3 ∪ ⋯ = 𝑃 𝐴1 + 𝑃 𝐴2 + 𝑃 𝐴3 + …
55
Addition Theorem 3
For any two events
𝑃 𝐴 ∪ 𝐵 = 𝑃 𝐴 + 𝑃 𝐵 − 𝑃(𝐴 ∩ 𝐵)
56
Addition Theorem 4
In case of any three events
𝑷 𝑨∪𝑩∪𝑪
= 𝑃 𝐴 + 𝑃 𝐵 + 𝑃 𝐶 − 𝑃 𝐴∩𝐵 − 𝑃 𝐵∩𝐶
− 𝑃 𝐴 ∩ 𝐶 + 𝑃(𝐴 ∩ 𝐵 ∩ 𝐶)
57
Conditional Probability of Event B

knowing that Event A is already occurred
𝐵 𝑃 𝐵∩𝐴
𝑃 =
𝐴 𝑃 𝐴
𝑝𝑟𝑜𝑣𝑖𝑑𝑒𝑑 𝑃(𝐴) ≠ 0
58
Conditional Probability of Event A

knowing that Event B is already occurred
𝐴 𝑃 𝐴∩𝐵
𝑃 =
𝐵 𝑃 𝐵
𝑝𝑟𝑜𝑣𝑖𝑑𝑒𝑑 𝑃(𝐵) ≠ 0
59
Compound Theorem
In case of two dependent events
P(A∩B) = P(B) × P(A/B) or
P(A∩B) = P(A) × P(B/A)
60
Compound Theorem
In case of two independent events
P(A∩B) = P(A) × P(B)

Same thing applies for two or more independent events
61
Expected value of a Probability Distribution
E ( x) =  pi xi
E ( x) = 
62
Variance of Probability Distribution
𝑉 𝑥 = 𝜎 2
𝐸 𝑥−𝜇 2 = 2
𝐸(𝑥) −𝜇 2
63
Probability Mass Function in case of Binomial Distribution
𝑛 𝑥 𝑛−𝑥
𝑓 𝑥 = 𝑃 𝑋 = 𝑥 = 𝐶𝑥 𝑝 𝑞
64
Mean and Variance in case of Binomial Distribution
𝜇 = 𝑛𝑝
𝜎 2 = 𝑛𝑝𝑞
65
Mode in case of Binomial Distribution

Calculate 𝑛+1 𝑝
if the resulting value is integer 𝜇0 = 𝑛 + 1 𝑝 𝑎𝑛𝑑

then Bi-modal [ 𝑛 + 1 𝑝 − 1]
If the resulting value is non- 𝜇0 = largest integer contained in
integer then Uni-modal 𝑛+1 𝑝
66
Probability Mass Function in case of Poisson Distribution
−𝑚 𝑥
(𝑒 . 𝑚 )
𝑓 𝑥 = 𝑃 𝑋=𝑥 =
𝑥!
67
Mean, Variance and SD in case of Poisson Distribution
𝜇=𝑚
𝜎 2 =𝑚
𝜎= 𝑚
68
Mode in case of Poisson Distribution
if the value of m is integer 𝜇0 = 𝑚 𝑎𝑛𝑑

then Bi-modal [𝑚 − 1]
If the value of m is non- 𝜇0 = largest integer
integer then Uni-modal contained in 𝑚
69
Probability Density Function in case of Normal Distribution
1 −(
𝑥−𝜇 2 1
) ×
𝑓 𝑥 = × 𝑒 𝜎 2
𝜎 2𝜋
70
Mean Deviation in case of Normal Distribution
MD = 0.8 𝜎
71
Quartiles in case of Normal Distribution
𝑄1 = 𝜇 − 0.675𝜎
𝑄3 = 𝜇 + 0.675𝜎
72
Quartile Deviation in case of Normal Distribution
𝑄𝐷 = 0.675𝜎
73
Points of Inflexion
𝜇−𝜎 & 𝜇+ 𝜎
74
Ratio between
QD : MD : SD = 10:12:15
75
Conditions of Standard Normal Distribution
Mean μ 0
Standard Deviation σ 1
76
Z Value
𝑥−𝜇
𝑍=
𝜎
77
Area under Normal Curve
From To Area/Probability
μ +σ 34.135%
+σ +2σ 13.59%
+2σ +3σ 2.14%
3σ ∞ 0.135%
78
For a bivariate frequency distribution
No. of marginal distributions = 2
No. of conditional distributions = m + n
79
Karl Pearson’s Product Moment Correlation Coefficient
𝐶𝑜𝑣 𝑥, 𝑦
𝑟𝑥𝑦 =
𝜎𝑥 . 𝜎𝑦
80
Covariance
𝛴 𝑥 − 𝑥ҧ 𝑦 − 𝑦ത 𝛴𝑥𝑦
𝐶𝑜𝑣 𝑥, 𝑦 = 𝑜𝑟 − 𝑥.ҧ 𝑦ത
𝑛 𝑛
81
Spearman’s Rank Correlation Coefficient
6𝛴𝑑 2
𝑟𝑅 = 1 −
𝑛 𝑛2 −1
here d means difference in ranks
82
Adjustment value in case of Tie
𝑡 3 −𝑡
𝛴
12
83
Coefficient of Concurrent Deviations
2𝑐 − 𝑚
𝑟𝑐 = ± ±
𝑚
84
Regression Coefficients
𝜎𝑦 𝐶𝑜𝑣(𝑥,𝑦)
𝑏𝑦𝑥 = 𝑟. or 𝑏𝑦𝑥 =
𝜎𝑥 𝜎𝑥 2
𝜎𝑥 𝐶𝑜𝑣(𝑥,𝑦)
𝑏𝑥𝑦 = 𝑟. or 𝑏𝑥𝑦 =
𝜎𝑦 𝜎𝑦 2
85
Regression Property
𝑟 = ± 𝑏𝑥𝑦 × 𝑏𝑦𝑥
𝑏𝑥𝑦 , 𝑏𝑦𝑥 𝑎𝑛𝑑 𝑟 𝑎𝑙𝑙 𝑤𝑖𝑙𝑙 ℎ𝑎𝑣𝑒 𝑠𝑎𝑚𝑒 𝑠𝑖𝑔𝑛
86
Regression Property
› Change of Origin and Scale
– Origin: No Impact
– Scale: If original pair is 𝑥, 𝑦 and modified pair is 𝑢, 𝑣
then,
change of scale of y
bvu = byx 
change of scale of x
change of scale of x
buv = bxy 
change of scale of y
87
Regression Property
› Intersection of two regression lines:
– Two regression lines (if not identical) will intersect at the point [means]
( x, y )
88
Coefficient of determination
Explained Variance
Accounted Variance
2
𝑟
89
Coefficient of non-determination
Unexplained Variance
Unaccounted Variance
2
1−𝑟
90
Probable Error
1− r2
0.6745 
N
– where, 𝒓 = correlation coefficient, 𝑵 = no. of pairs of observation
91
Limits of Population Correlation Coefficient
r  PE
92
Index Relatives
𝑃𝑛
Price Relative Price Relative =
𝑃0
Quantity 𝑄𝑛
Quantity Relative =
Relative 𝑄0
𝑉𝑛 𝑃𝑛 𝑄𝑛
Value Relative Value Relative = =
𝑉0 𝑃0 𝑄0
𝑃1 𝑃2 𝑃3 𝑃𝑛
Link relative
, , ,…,
𝑃0 𝑃1 𝑃2 𝑃𝑛−1
Same can be created for quantities also
When the above relatives are in respect to a fixed base period these are
also called the chain relatives
Chain relatives 𝑃1 𝑃2 𝑃3 𝑃𝑛
, , ,…,
93
𝑃0 𝑃0 𝑃0 𝑃0

Simple Aggregative Method of Index
Price Index is expressed as total of commodity prices in a given year as a
percentage of total of commodity prices in the base year
› Formula
Σ𝑃𝑛
× 100
Σ𝑃0
94
Simple Average of Relatives – Method of Index
› Under this method, we invert the actual price for each variable into percentage
of the base period. These percentages are called relatives.
› Formula
𝑃𝑛
Σ
𝑃0
N
95
Weighted Index Methods
› Laspeyres’ Index
Σ𝑃𝑛 𝑄0
× 100
Σ𝑃0 𝑄0
96
› Passche’s Index
Σ𝑃𝑛 𝑄𝑛
× 100
Σ𝑃0 𝑄𝑛
97
› Marshall-Edgeworth Index
Σ𝑃𝑛 (𝑄0 + 𝑄𝑛 )
× 100
Σ𝑃0 (𝑄0 + 𝑄𝑛 )
98
› Fisher’s Index
(GM of Laspeyres’ and Paasche’s)
Σ𝑃𝑛 𝑄0 Σ𝑃𝑛 𝑄𝑛
× × 100
Σ𝑃0 𝑄0 Σ𝑃0 𝑄𝑛
99
Deflated Value
Current Value
Deflated Value =
Price Index of the current year
100

100 Formulas of Stats

Uploaded by

Copyright:

Available Formats

You might also like

100 Formulas of Stats

Uploaded by

Document Information

Original Description:

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

100 Formulas of Stats

Uploaded by

Copyright:

Available Formats

Formula Marathon for Maths, LR and Stats by CAPRANAV

› In case of Mutually Exclusive Classification

UCB = UCL and LCB = LCL

› In case of Mutually Inclusive Classification

UCB = UCL + 0.5

Class Length / Width of Class / Size of Class

Arithmetic Mean of Discrete Distribution:

Arithmetic Mean in case of Frequency Distribution :

AM using Assumed Mean / Step Deviation Method

Median in case of discrete distribution

Same formula will be used for Simple Frequency distribution

Median in case of Grouped Frequency Distribution

– Step 4: Find 𝑙1 = LCB of Median Class, 𝑁𝑢 as Cum Freq. of Median Class,

– Step 3: Apply the below formula

stats Formula marathon

Quartiles (in case of discrete observations)

Deciles (in case of discrete observations)

Percentiles (in case of discrete observations)

Quartiles (Grouped FD)

stats Formula marathon

› Deciles (Grouped FD)

– For first Decile 𝑫𝟏  N 

– For ninth Decile 𝑫𝟗  9N 

› Percentiles (Grouped FD)

– For first Percentile 𝑷𝟏  N 

– For 99th Percentile 𝑷𝟗𝟗  99 N 

Mode in case of discrete observation

› When all observations have same frequency : No Mode

› Mode in case of grouped frequency distribution

Relationship between Mean, Median and Mode

Mean = Median = Mode

Relationship between Mean, Median and Mode

Mean – Mode = 3 (Median – Median)

Geometric Mean (in case of discrete positive observations)

Geometric Mean (in case of frequency distribution)

Harmonic Mean (in case of discrete observations)

Harmonic Mean (in case of frequency distribution)

› Relationship between AM, GM and HM

Range (in case of Discrete Observations)

Range (in case of Grouped FD)

Mean Deviation (in case of discrete observations)

Here A is mean or median or mode as given in question

Mean Deviation (in case of grouped frequency distributions)

Coefficient of Mean Deviation

Mean Deviation about A

Standard Deviation (in case of discrete observations)

Standard Deviation (in case of grouped frequency observations)

For any two numbers, SD = half of range

› Standard Deviation of first n natural numbers

Coefficient of Quartile Deviation

Basic formula of Probability

𝑛𝑜. 𝑜𝑓 𝑓𝑎𝑣𝑜𝑟𝑎𝑏𝑙𝑒 𝑒𝑣𝑒𝑛𝑡𝑠 𝑡𝑜 𝐴

Odds in Favor of Event A

no. of favorable events

› Odds against an Event

no. of unfavorable events

› No. of total outcome of a random experiment

If an experiment results in p outcomes and if it is repeated q times then