Title | CFA level II formula sheet |
---|---|
Author | bag bar |
Course | Finance |
Institution | Harvard University |
Pages | 4 |
File Size | 730.2 KB |
File Type | |
Total Downloads | 13 |
Total Views | 166 |
formula sheet...
Formula Sheet
Level II 2020
FinQuiz Formula Sheet CFA Program Level II 𝑆𝑆𝑇
(for single independent variable R2 = r2) Reading 4: Introduction to Regression 1
/) ∑-23(,- ., / )(0- .0
1.
Sample!Cov!(X, Y) =
2.
Correlation Coefficient = r,0 = r=
3.
789(,,0)
4.5
789:;
(?(0)
t-test (for normally distributed variables) =
•
?√4.B
t==
!t!distribution!with!(n − C
5.?
2)deg. of!freedom 4.
• •
5.
Intercept (b0) =
b0 = y - b1 x=
Slope or regression coefficient = !b5 = 789(S,T) or 9>?(S)
=
U )(T.T/) ∑(S.S ∑( S.SU)C
9.
! b - b1 Test statistic = t = 1 sb1 Confidence Interval =
YYW
4.Z.5
=X
∑1 [ )C -23 (T- .T 4.Z.5
Coefficient of Determination (R2) = =
YY\.YYW YY\
b1 ± t cs b1
d
= ` (𝑦c ce5
− 𝑦U)B
Source of Variability
DoF
Sum of Squares
Mean Sum of Squares
Regression (Explained)
1
RSS
MSR = RSS/1
Error (Unexplained)
n-2
SSE
MSE = SSE/n-2
Total
n-1
SST= RSS + SSE
ANOVA (Analysis of variance) = ANOVA
SS 𝑆𝑆𝑅
Regression df = k
d
= ` (𝑦bc ce5 B
− 𝑦U)
Standard Error of Estimate SEE = SW =
X 6.
•
Linear Regression = Yi = b0 + b1Xi + εi,
Total df = n-1
𝑆𝑆𝐸 Error df = n-k-1
d
= ` (𝑦c ce5
− 𝑦b)B
MSS 𝑆𝑆𝑅 𝑘
F 𝑆𝑆𝑅g 𝑘
𝑆𝑆𝐸 g(𝑛 − 𝑘 − 1)
𝑆𝑆𝐸 𝑛−𝑘 −1
10. F-Statistic or F-Test =
www.finquiz.com All rights reserved
lmo
=!
pqq )! r qqs (turu3)
(
(df numerator = k = 1) (df denominator = n – k – 1 = n – 2) 11. Prediction Intervals = Yv ± t 7 sx 5
(,., / C
) 𝑤ℎ𝑒𝑟𝑒!sxB = sB }1 + + • and (4.5) 0) = 𝜆 ∑’…e5 ‘𝑏U… ‘ 2. 3.
∑dce5 (𝑌c − 𝑌c )B + 𝜆 ∑’…e5 ‘𝑏•’ ‘ When l = 0, LASSO penalized regression = OLS regression
Reading 8: Big Data Projects 1.
yˆt +1 = bˆ0 + bˆ1 (T + 1)
𝑋c(d“”•–—c˜™š) =
›œ .›•œt ›•žŸ.›•œt
where Xi = value of observation
www.finquiz.com All rights reserved
µt is
ˆ 0 +α1 εˆ 2t t+1 = σˆ 2t +1 = α
Reading 6: Time Series Analysis 1.
where
an error term • Predicting variance of errors in period
xˆ t+2 = bˆ 0 + bˆ1 xt+1 6.
Correcting Seasonality in Time Series Models: •
xˆ t+1 = bˆ0 + bˆ1 xt •
Smoothing Past Values with n-Period Moving Average =
xt + xt -1 + xt -2 + ..... + xt -( n -1)
5. Chain Rule of Forecasting: • One-period ahead forecast =
∑ •Ž2C( •bŽ.•bŽu3 ) C
•
Level II 2020
Formula Sheet
Performance Metrics: 2. Accuracy = (TP + TN)/(TP + FP + TN + FN) F1 score = (2*P*R)/(P + R) 3.
4.
Level II 2020
5
•
(1 + i°) = S∫ ¹1 + i∫ º » g
•
F∫ /° = S∫ ‰( g
•
Using day count convention:
°
' )1+ id (
Receiver Operating Characteristic (ROC): False positive rate (FPR) = FP/(TN + FP) and True positive rate (TPR) = TP/(TP + FN), which is same as recall
° 5¾‡∫
5¾‡¼ )
Š
½
®∫ /¼
7.
Ff / d -S f / d S f/d
! Actual $* &, = #" 360 %+
' ! Actual $*' 1 * , S f /d )1+ i f # &,) " 360 %+)( Ff /d ,+ (
d
(𝑃𝑟𝑒𝑑𝑖𝑐𝑡𝑒𝑑c − 𝐴𝑐𝑡𝑢𝑎𝑙c )B 𝑛
ce5
•
Reading 9: Excerpt from ‘Probabilistic Approaches, Scenario Analysis, Decision Tree & Simulations’
6.
Uncovered Interest Rate Parity : •
Reading 10: Currency Exchange Rates 1. 2.
Bid-offer Spread = Offer price – Bid price Fwd!rate! = Spot!Exchange!rate! +
3.
Forward!premium/discount!(in!%) ! =
!
• • •
4·µ!?>²µ
4.
To convert spot rate into forward quote: • Spot exchange rate × (1 + % premium) • Spot exchange rate × (1 - % discount)
5.
Covered interest rate parity:
% DS
e
f /d
= i f - id
Forward premium or discount: For one year horizon =
"i −i % S f /d $ f d ' ≅ S f /d (i f − id ) # 1+ id &
5ƒ,ƒƒƒ
−1
i f - %DS e f / d = i d
Ff /d − S f /d =
®8?¯>?°!±8‡4²<
4·µ!?>²µ.(x8?¯>?°!±8‡4²...