Formula Sheet for CPIT 603 (Quantitative Analysis) PROBABILITY
Probability of any event: 0 P (event) 1 P(A or B) = P(A) + P(B) – P(A and B) For Mutually exclusive events:
P(A or B) = P(A) + P(B) P(AB) = P(A | B) P(B) ) ( ) ( ) ( y Probabilit l Conditiona B B | A P AB P P Independent Events: P(A and B) = P(A)P(B) P(A | B) = P(A)
Dependent Events:
P(A and B) = P(A) * P(B given A)
P(A and B and C) = P(A) * P(B given A) * P(C given A and B) Bayes’ Theorem ) ( ) ( ) ( ) ( ) ( ) ( ) ( A A | B A A | B A A | B B | A P P P P P P P
A, B = any two events
A’ = complement of A Expected Value
) X ( X ... ) X ( X ) X ( X X X X 2 2 1 1 1 n n n i i i P P P P E
Xi = random variable’s possible values P(Xi) = probability of each of the random variable’s possible values
n
i 1
= summation sign indicating we are adding all n possible values
E(X) = expected value or mean of the random variable ) X ( )] X ( X [ 1 2 2
n i i i E P Variance Xi = random variable’s possible values E(X) = expected value of the random variable [Xi – E(X)] = difference between each value of the random variable and the expected value
P(Xi) = probability of each possible value of the random variable
2
Variance Deviation
Standard
Discrete Uniform Distribution
For a series of n values, f(x) = 1/ n
For a range that starts from a and ends with b (a, a+1, a+2, …, b) and a b
2 ) (ba 12 1 ) 1 ( 2 2 Variance ba Binomial Distribution r n rq p r n r n )! ( ! ! n trials in success r of y Probabilit
Expected value (mean) = np Variance = np(1 – p) Geometric Distribution p p)x 1 1 ( success first the until trials of number of y Probabilit Expected value (mean) = 1/p Variance = (1 – p)/p2 Poisson Distribution ! ) ( X X e P x
P(X) = probability of exactly X arrivals or occurrences
= average number of arrivals per unit of time
(the mean arrival rate), pronounced “lambda” e = 2.718, the base of natural logarithms X = number of occurrences (0, 1, 2, 3, …) Expected value = Variance =
Normal Distribution (Continuous Distribution)
2 2 2 ) ( 2 1 ) ( x e f X
Completely specified by the mean, , and the standard
Exponential Distribution
x
e f( X)
X = random variable (service times)
= average number of units the service facility can handle in a specific period of time
deviation,
X ZX = value of the random variable we want to measure = mean of the distribution
= standard deviation of the distribution
Z = number of standard deviations from X to the mean, m
e = 2.718 (the base of natural logarithms)
2 1 = Variance time service Average = 1 = value Expected t e t P(X )1 formula by the given is t time to equal or than less is customer a serve to required (X) time d distribute lly exponentia an y that probabilit The
Negative Binomial Distribution
x r r p p r x f 1 1 1 ) (x = r/p = variance = r(1-p)/p2Continuous Uniform Distribution
For a series of n values, f(x) = 1/ (b –a)
For a range that starts from a and ends with b (a, a+1, a+2, …, b) and a b
2 ) (ab 12 ) ( 2 2 Variance ba DECISION ANALYSIS Criterion of Realism
Weighted average = (best in row) + (1 – )(worst in row)
For Minimization:
Weighted average = (best in row) + (1 – )(worst in row)
Expected Monetary Value
( )= ative)
EMV(altern XiP Xi
Xi = payoff for the alternative in state of nature i
P(Xi) = probability of achieving payoff Xi (i.e., probability of state of nature i)
∑ = summation symbol EMV (alternative i) = (payoff of first state of nature) x
(probability of first state of nature) + (payoff of second state of nature) x (probability of second state of nature) + … + (payoff of last state of nature) x (probability of last state of nature)
Expected Value with Perfect Information EVwPI = ∑(best payoff in state of nature i)
(probability of state of nature i)
EVwPI = (best payoff for first state of nature) x (probability of first state of nature) + (best payoff for second state of nature) x (probability of second state of nature) + … + (best payoff for last state of nature) x (probability of last state of nature)
Expected Value of Perfect Information EVPI = EVwPI – Best EMV
Expected Value of Sample Information
EVSI = (EV with SI + cost) – (EV without SI) EVPI100%
EVSI = n informatio sample of Efficiency
Utility of other outcome = (p)(utility of best outcome, which is 1) + (1 – p)(utility of the worst outcome, which is 0)
REGRESSION MODELS error random line regression the of slope 0) X when Y of (value intercept y) explanator or (predictor t variable independen X (response) variable dependent Y 1 0 1 0 X Y results sample on based , of estimate results sample on based , of estimate Y of value predicted ˆ ˆ 1 1 0 0 1 0 b b b b Y X Y
Error = (Actual value) – (Predicted value)
Y Y ˆ e X Y X X Y Y X X Y Y Y X X X 1 0 2 1 ) ( ) )( ( values of (mean) average values of (mean) average b b b n n
2 ) ( SST Total Squares of Sum
Y Y SSE + SSR SST
SSE 2 ( ˆ)2 Error Squares of Sum e Y Y
SSR (ˆ )2 Regression Squares of Sum Y Y SST SSE – 1 SST SSR ion Determinat of t Coefficien r2 Correlation Coefficient =r r2 1 SSE MSE 2 k n s Error Squared Mean MSE s Estimate of ErrorStandard GenericLinearModelY 0 1X
model in the s t variable independen of number k SSR MSR k MSE MSR F : Statistic F
degrees of freedom for the numerator = df1 = k degrees of freedom for the denominator = df2 = n – k – 1 0 : 0 : 1 1 1 0 H H Test Hypothesis 1 if Reject 2 1 , , 1 2 k n k F Fcalculated df df df df value -if Reject ) statistic test calculated ( value -p F P p Y = 0 + 1X1 + 2X2 + … + kXk +
Y = dependent variable (response variable) Xi = ith independent variable (predictor or explanatory variable)
0 = intercept (value of Y when all Xi = 0) i = coefficient of the ith independent variable k = number of independent variables
= random error k k b b b b X X X Yˆ 0 1 1 2 2 ...
Yˆ = predicted value of Y
b0 = sample intercept (an estimate of 0) bi = sample coefficient of the i th variable (an estimate of i) ) 1 /( SST ) 1 /( SSE 1 Adjusted 2 n k n r FORECASTING n
forecast error (MAD) Deviation Absolute Mean n
2 ) error ( (MSE) Error Squared Mean100% actual error (MAPE) Error Percent Absolute Mean n
n n n t t t t 1 1 1 ... periods n previous in demands of sum Forecast Average Mean F Y Y Y n n t n t t t w w w w w w i
... ... ) Weights ( ) period in value Actual )( period in Weight ( 2 1 1 1 2 1 1 Y Y Y F : Average Moving Weighted forecast) s period’ Last – demand actual s period’ Last ( forecast s period’ Last forecast New ) ( 1 t t t t F Y F F : Smoothing l Exponentia 1 1 1 1 1 1 ) ( ) ( : Trend with Smoothing l Exponentia t t t t t t t t t t t T F FIT FIT F T T FIT Y FIT F X timeperiod(i.e.,X1,2,3, ,n) line the of slope b1 intercept b0 value predicted ˆ where ˆ 0 1 Y X Y b b 4 4 3 3 2 2 1 1 ˆ X X X X Y ab b b b MAD error) (forecast MAD RSFE signal Tracking
INVENTORY CONTROL MODELS 2 = level inventory Average Q o o QC D C order each in units of Number Demand Annual order) per cost (Ordering year per placed orders of Number cost ordering Annual h C Q 2 year) per unit per cost (Carrying 2 quantity Order year) per unit per cost (Carrying Inventory Average cost holding Annual
Economic Order Quantity
Annual ordering cost = Annual holding cost
h o C 2 Q C Q D h o C DC Q 2 EOQ * Total cost (TC) = Order cost + Holding cost
h o C Q C Q D TC 2
Cost of storing one unit of inventory for one year = Ch = IC, where C is the unit price or cost of an inventory item and I is Annual inventory holding charge as a percentage of unit price or cost
IC DC Q* 2 o ROP without Safety Stock:
Reorder Point (ROP) = Demand per day x Lead time for a new order in days
d L
Inventory position = Inventory on hand + Inventory on order
EOQ without instantaneous receipt assumption
Maximum inventory level (Total produced during the production run) – (Total used during the production run)
(Daily production rate)(Number of days production) – (Daily demand)(Number of days production)
p d Q p Q d p Q p dt pt – – 1– Total produced Q pt p d Q – 1 2 inventory Average Ch p d Q 1– 2 cost holding Annual s C Q D cost setup Annual Co Q D cost ordering Annual
D = the annual demand in units
Q number of pieces per order, or production run
Production Run Model: EOQ without instantaneous receipt assumption
Annual holding cost Annual setup cost
s h QC D C p d Q 1– 2 p d C DC Q h s – 1 2 *
Quantity Discount Model IC
DCo 2 EOQ
If EOQ < Minimum for discount, adjust the quantity to Q = Minimum for discount
Total cost Material cost + Ordering cost + Holding cost
h o C Q C Q D DC 2 + + cost Total
Holding cost per unit is based on cost, so Ch = IC Where I = holding cost as a percentage of the unit cost (C)
Safety Stock
ROP = Average demand during lead time + Safety Stock
Service level = 1 – Probability of a stockout Probability of a stockout = 1 – Service level
Safety Stock with Normal Distribution
ROP = (Average demand during lead time) + ZsdLT Z = number of standard deviations for a given service level
dLT = standard deviation of demand during the lead time
Safety stock = ZdLT Demand is variable but lead time is constant
L
Z L d d ROP days in time lead demand daily of deviation standard demand daily average L d d Demand is constant but lead time is variable
dL
Z L d ROP demand daily time lead of deviation standard time lead average d L L Both demand and lead time are variable2 2 2
ROPdLZ Ld d L
Total Annual Holding Cost with Safety Stock
Total Annual Holding Cost = Holding cost of regular inventory + Holding cost of safety stock
h h C C Q (SS) 2 THC
The expected marginal profit = P(MP) The expected marginal loss = (1 – P)(ML) The optimal decision rule
Stock the additional unit if P(MP) ≥ (1 – P)ML P(MP) ≥ ML – P(ML) P(MP) + P(ML) ≥ ML P(MP + ML) ≥ ML MP + ML ML P
PROJECT MANAGEMENT
Expected Activity Time
6 + 4 + = a m b t 2 6 – = Variance b a Earliest finish time = Earliest start time + Expected
activity time EF = ES + t
Earliest start = Largest of the earliest finish times of immediate predecessors
ES = Largest EF of immediate predecessors Latest start time = Latest finish time – Expected
activity time LS = LF – t
Latest finish time = Smallest of latest start times for following activities
LF = Smallest LS of following activities
Slack = LS – ES, or Slack = LF – EF Project Variance = sum of variances of activities on the critical path riance Project va deviation standard Project T T completion of date Expected date Due Z Value of work completed = (Percentage of work
complete) x (Total activity budget)
Activity difference = Actual cost – Value of work completed Crash time time Normal Cost Normal cost Crash Period cost/Time Crash
WAITING LINES AND QUEUING THEORY MODELS Single-Channel Model, Poisson Arrivals,
Exponential Service Times (M/M/1)
= mean number of arrivals per time period (arrival rate)
= mean number of customers or units served per time period (service rate)
The average number of customers or units in the system, L L
The average time a customer spends in the system, W
1 W
The average number of customers in the queue, Lq ) ( 2 q L
The average time a customer spends waiting in the queue, Wq ) ( q W
The utilization factor for the system, (rho), the probability the service facility is being used
The percent idle time, P0, or the probability no one is in the system
Multichannel Model, Poisson Arrivals, Exponential Service Times (M/M/m)
m = number of channels open = average arrival rate
= average service rate at each channel
The probability that there are zero customers in the system
m m m m n P m – m n n n for ! 1 ! 1 1 1 = 0 = 0The average number of customers or units in the system ( – 1)!( )2 0 ) / ( P m m L m
The average time a unit spends in the waiting line or being served, in the system
L P m m W m 1 ) ( )! 1 – ( ) / ( 0 2
The average number of customers or units in line waiting for service
L Lq
The average number of customers or units in line waiting for service
q q L W W 1
1 0 P
The probability that the number of customers in the system is greater than k, Pn>k
1 k k > n P
waiting for service (Utilization rate)
m
Finite Population Model (M/M/1 with Finite Source) = mean arrival rate
= mean service rate N = size of the population
Probability that the system is empty
N n n n – N N P 0 0 )! ( ! 1 Average length of the queue
1 P– 0
N Lq Average number of customers (units) in the system
1 P– 0
L L q
Average waiting time in the queue ) (N – L L W q q
Average time in the system
1
Wq
W
Probability of n units in the system
N – n P n N N P n n ! for 0,1,..., ! 0
Total service cost = (Number of channels) x (Cost per channel)
Total service cost = mCs m = number of channels
Cs = service cost (labor cost) of each channel Total waiting cost = (Total time spent waiting by all arrivals) x (Cost of waiting)
= (Number of arrivals) x (Average wait per arrival)Cw = (W)Cw
Total waiting cost (based on time in queue) = (Wq)Cw Total cost = Total service cost + Total waiting cost Total cost = mCs + WCw
Total cost (based on time in queue) = mCs + WqCw
Constant Service Time Model (M/D/1)
Average length of the queue
) ( 2 2 q L
Average waiting time in the queue
) ( 2 q W
Average number of customers in the system
Lq
L
Average time in the system
1
Wq
W
Little’s Flow Equations L = W (or W = L/) Lq = Wq (or Wq = Lq/)
Average time in system = average time in queue + average time receiving service
W = Wq + 1/
(i) = vector of state probabilities for period i
= (1, 2, 3, … , n) where
n = number of states
1, 2, … , n = probability of being in state 1, state 2, …, state n
Pij = conditional probability of being in state j in the future given the current state of i
mn m m n n P P P P P P P P P 2 1 2 22 21 1 12 11 P
For any period n we can compute the state probabilities for period n + 1
(n + 1) = (n)P Equilibrium condition = P Fundamental Matrix F = (I – B)–1 Inverse of Matrix r a r c r b r d d c b a d c b a 1 1 -P P r = ad – bc
M represent the amount of money that is in each of the nonabsorbing states
M = (M1, M2, M3, … , Mn)
n = number of nonabsorbing states M1 = amount in the first state or category M2 = amount in the second state or category Mn = amount in the nth state or category
Partition of Matrix for absorbing states
B A O I P I = identity matrix O = a matrix with all 0s
Computing lambda and the consistency index
1 CI n n Consistency Ratio RI CI CR
STATISTICAL QUALITY CONTROL x x z x z x (LCL) limit control Lower (UCL) limit control Upper
x = mean of the sample means
z = number of normal standard deviations (2 for 95.5% confidence, 3 for 99.7%)
x
= standard deviation of the sampling distribution of the sample means =
n x R A x R A x x x 2 2 LCL UCL
R = average of the samples
A2 = Mean factor
x = mean of the sample means
R D R D R R 3 4 LCL UCL
UCLR = upper control chart limit for the range LCLR = lower control chart limit for the range D4 and D3 = Upper range and lower range
p-charts p p p p z p z p LCL UCL
p= mean proportion or fraction defective in the sample
examined records of number Total errors of number Total p
z = number of standard deviations
p
= standard deviation of the sampling distribution
p
is estimated by ˆp
Estimated standard deviation of a binomial distribution n p p p ) 1 ( ˆ
where n is the size of each sample c-charts
The mean is c and the standard deviation is equal to
c
To compute the control limits we use c3 c (3 is used for 99.7% and 2 is used for 95.5%)
c c c c c c 3 LCL 3 UCL
OTHERS
Computing lambda and the consistency index
1 CI n n Consistency Ratio RI CI CR
The input to one stage is also the output from another stage
sn–1 = Output from stage n The transformation function
tn = Transformation function at stage n General formula to move from one stage to another using the transformation function sn–1 = tn (sn, dn)
The total return at any stage fn = Total return at stage n Transformation Functions
n n
n n
n n a s b d c s 1 Return Equations
n n
n n
n n a s b d c r v s f cost/unit Variable – Price/unit cost Fixed (units) point even-Break Probability of breaking even
break-even point Z
P(loss) = P(demand < break-even) P(profit) = P(demand > break-even)
costs Fixed demand) (Mean unit cost Variable – unit Price EMV BEP X $0for BEP X X)for – point even -K(break Loss y Opportunit where
K = loss per unit when sales are below the break-even point
X = sales in units
Using the unit normal loss integral, EOL can be computed using
EOL = KN(D)
EOL = expected opportunity loss
K = loss per unit when sales are below the break-even point
= standard deviation of the distribution
N(D) = value for the unit normal loss integral for a given value of D
– break even point
D
C AB ce be ae cd bd ad e d c b a
ad be cf
f e d c b a dh cf dg ce bh af bg ae h g f e d c b a d c b aDeterminant Value = (a)(d) – (c)(b)
i h g f e d c b a
Determinant Value = aei + bfg + cdh – gec – hfa – idb t determinan r denominato of value Numerical t determinan numerator of value Numerical X
a c b d a b c d cb ad d c b a matrix the of Adjoint cofactors of Matrix matrix original of t value Determinan matrix Original cb ad a cb ad c ad cb b cb ad d d c b a 1
Equation for a line Y = a + bX
where b is the slope of the line
Given any two points (X1, Y1) and (X2, Y2)
1 2 1 2 – – in Change in Change X X Y Y X Y X Y b
For the Nonlinear function Y = X2 – 4X + 6
Find the slope using two points and this equation 1 2 1 2 – – in Change in Change X X Y Y X Y X Y b c b a c b a ) ( ) ( X 2 2 2 1 X X X X Y X Y 2 1 2 Y ( X) 2 X( X) ( X) Y Y b a c X X X X X X X X X X X Y c a b c a b X c a b 2 ) 2 ( ) ( ) ( 2 ) ( 2 ) ( ) ( ) ( ) ( 1 x h x g x h x g c n n n Y Y X Y X Y X Y C Y ) ( ) ( ) ( ) ( 0 1 1 1 x h x g x h x g n cn n n n n Y Y X Y X Y X Y Y
Total cost (Total ordering cost) + (Total holding cost) + (Total purchase cost)
DC C Q C Q D TC o h 2 + Q = order quantity D = annual demand
Co = ordering cost per order Ch = holding cost per unit per year C = purchase (material) cost per unit
Economic Order Quantity 2 – 2 o Ch Q DC Q TC d d h o C DC Q 2 3 2 2 Q DC Q TC o d d