# Applied Statistics IV

47 %
53 %
Information about Applied Statistics IV
Finance

Published on February 27, 2014

Author: vinzjeannnin

Source: slideshare.net

## Description

Fourth Session, MSc 4th Year

Q1 2012 ESGF 4IFM Q1 2012 Vincent JEANNIN – ESGF 4IFM vinzjeannin@hotmail.com Applied Statistics 1

Interim Exam Sum Up Reminders of last session Capital Asset Pricing Model Thinking algorithmic ESGF 4IFM Q1 2012 • • • • vinzjeannin@hotmail.com Summary of the session (est. 4.5h) 2

ESGF 4IFM Q1 2012 1 vinzjeannin@hotmail.com Interim Exam Sum-Up 3

When E is minimal? When partial derivatives i.r.w. a and b are 0 Attention, logarithms are not additive! vinzjeannin@hotmail.com Minimising residuals ESGF 5IFM Q1 2012 Two parameters to estimate: • Intercept α • Gradient β 4

Change the variable Z=ln(X) vinzjeannin@hotmail.com ESGF 5IFM Q1 2012 Solution? 5

vinzjeannin@hotmail.com ESGF 4IFM Q1 2012 Leads easily to the intercept 6

7 vinzjeannin@hotmail.com ESGF 5IFM Q1 2012

vinzjeannin@hotmail.com ESGF 5IFM Q1 2012 We have and Finally… 8

Z=ln(X) vinzjeannin@hotmail.com ESGF 5IFM Q1 2012 Don’t forget… 9

Accept or reject the regression? vinzjeannin@hotmail.com Hedging is linear… ESGF 5IFM Q1 2012 No forecast possible (one particular stock against the market) Check correlation and R Squared 10 Check the normality of residuals

11 vinzjeannin@hotmail.com ESGF 5IFM Q1 2012

N(-1,2) vinzjeannin@hotmail.com ESGF 5IFM Q1 2012 2 N(0,1) 12

Let’s build a tree with 5 steps, with S=104.57, σ=10%, 1 year to maturity 125.05 119.58 114.45 109.35 104.57 100 104.57 95.62 114.45 109.35 109.35 104.57 100 91.44 119.58 95.62 87.44 100 91.44 83.62 vinzjeannin@hotmail.com 130.77 ESGF 4IFM Q1 2012 3 13

130.77 119.58 20 19.58 109.35 5 100 5 91.44 0 83.62 vinzjeannin@hotmail.com • Pay off capped to 20 • Pay off between 100 inclusive and 109.35 inclusive: 5.00 ESGF 4IFM Q1 2012 Last node value 0 14

vinzjeannin@hotmail.com Final Value 12.50 15 ESGF 4IFM Q1 2012

What is the new price of the Call (initial price \$8.00) if S moves up \$2.5 with delta=0.5525 and a gamma of 0.0222, volatility moves up 1.75 point with a 0.8422 Vega, r moves up 1.2 basis point with Rho=178.5448 and placing you 3 days after with a final Theta of -0.9723? 10.73 vinzjeannin@hotmail.com ESGF 4IFM Q1 2012 4 16

Random walk! Past series has no importance! Trial s Independents! vinzjeannin@hotmail.com ESGF 4IFM Q1 2012 5 17

Reminder of the last session ESGF 4IFM Q1 2012 Multiple regression vinzjeannin@hotmail.com More than one explanatory variables R-Square is very often very poor Extension APT 18 “Pure” factors

• • • • • Corruption: current corruption CorruptionPrediction: future corruption School: level of education GDP: GDP Distortion: how badly policies are run vinzjeannin@hotmail.com Let’s discuss… ESGF 4IFM Q1 2012 Ratio Investment / GDP , World Bank, developing countries 19

Be logic vinzjeannin@hotmail.com • General to specific: this starts off with a comprehensive model, including all the likely explanatory variables, then simplifies it. • Specific to general: this begins with a simple model that is easy to understand, then explanatory variables are added to improve the model’s explanatory power. ESGF 4IFM Q1 2012 How to find the right model? Have the best R-Squared 20 Not over complicate

3 steps Identify Fit Forecast vinzjeannin@hotmail.com ESGF 4IFM Q1 2012 What is a model? 21

Trend Seasonality Residual vinzjeannin@hotmail.com ESGF 4IFM Q1 2012 3 components 22

ESGF 4IFM Q1 2012 vinzjeannin@hotmail.com Variation (price or percentage is a differentiation) 23 Series with stationarity much easier to modelise

On the values On the residuals vinzjeannin@hotmail.com Most cases you will find autocorrelation ESGF 4IFM Q1 2012 Once the series is stationary, look for autoccorrelation 24

Parameters of the model White noise vinzjeannin@hotmail.com ESGF 5IFM Q1 2012 Auto Regressive model AR(n) 25

f ( x) n! x! ( n x p (1 p) (n x) x )! Large sample: Normal Distribution N np , np (1 p) n is the size of the sample, x, the number individuals with the particular characteristic vinzjeannin@hotmail.com Small sample: Binomial Distribution ESGF 4IFM Q1 2012 Estimations 26

Estimate a proportion Normal approximation Standardisation possible Normal approximation works only if vinzjeannin@hotmail.com ESGF 4IFM Q1 2012 Binomial Distribution 27

Easy solve! vinzjeannin@hotmail.com ESGF 4IFM Q1 2012 Let’s look for p with a 95% confidence interval 28

vinzjeannin@hotmail.com 95% confidence interval ESGF 4IFM Q1 2012 52 Heads out of 100 toss… 29

Mean estimation vinzjeannin@hotmail.com Student’s Statistic ESGF 4IFM Q1 2012 Mean has a Student’s distribution Degree of freedom 30 n-1

SD: DF: S: ESGF 4IFM Q1 2012 vinzjeannin@hotmail.com IPO Premiums IPO1 / 12% IPO2 / 15% IPO3 / 13% IPO4 / 18% IPO5 / 20% IPO6 / 5% t: 31

vinzjeannin@hotmail.com ESGF 4IFM Q1 2012 Is Martingale safe? 32

How many portfolio can be built? How to chose the weights? Using Variance/Covariance Matrix to select the portfolio Optimisation of either the risk or the return vinzjeannin@hotmail.com 5 stocks available ESGF 5IFM Q1 2012 Capital Asset Pricing Model 33

vinzjeannin@hotmail.com ESGF 5IFM Q1 2012 Infinite number of long only portfolios 34

vinzjeannin@hotmail.com ESGF 5IFM Q1 2012 Would you buy just Air Liquide? 35

vinzjeannin@hotmail.com ESGF 5IFM Q1 2012 You’d only invest on the so called Efficient Frontier 36

vinzjeannin@hotmail.com ESGF 5IFM Q1 2012 For a particular return, you take the lowest risk 37 For a particular risk, you take the highest return

vinzjeannin@hotmail.com ESGF 5IFM Q1 2012 Unless there’s a risk free rate 38

Straight forward, mean is linear, weighted average ESGF 5IFM Q1 2012 vinzjeannin@hotmail.com For a particular combination you need to calculate the expected return 39

We already know ESGF 5IFM Q1 2012 vinzjeannin@hotmail.com For a particular combination you need to calculate the variance (or SD) Not enough, need the general case for a bigger number of assets 40

No linear formula to select the good one Need a computer and algorithms vinzjeannin@hotmail.com Millions of portfolio ESGF 5IFM Q1 2012 Thinking Algorithmic 41

## Add a comment

 User name: Comment:

## Related presentations

#### Conférence Droit & Croissance 2 Avril - Key Note ...

March 28, 2014

Les changements sur le marché du distressed aux Etats-Unis et en Europe

March 31, 2014

April 1, 2014

#### Technical trades march 2014 - by www.nooreshtech...

April 1, 2014

Main Sections of the Report 1) Nifty Technical View 2) 4 Large Cap Trade Ide...

#### Yearly results of Kinepolis Group

April 6, 2009

This presentation consits the yearly results of Kinepolis Group

April 1, 2014

PRESENTACIONES

## Related pages

### Presentation IV Wokshop on Applied Statistics by Diana ...

The 4th International Workshop on Applied Statistics (IWAS 2015) is a biannual event organized by the Faculty of Stastistics of Universidad Santo Tomas. In ...

### Applied Statistical Methods - Department of Statistics

Applied Statistical Methods Larry Winner Department of Statistics University of Florida February 23, 2009. 2. Contents 1 Introduction 7

### APPLIED STATISTICS - scribd.com

applied statisticsiv semester complementary course b sc mathematics (2011 admission) university of calicut school ...

### Complementary Course of BSc Mathematics IV Semester ...

APPLIED STATISTICS Complementary Course of BSc Mathematics IV Semester CUCBCSS 2014 Admission Onwards CALICUT UNIVERSITY SCHOOL OF DISTANCE EDUCATION 985.

### School of Distance Education - University of Calicut

School of Distance Education Applied Statistics Page 3 CONTENTS PAGE SYLLABUS 5 1. SKEWNESS AND KURTOSIS 6 – 17 Skewness Test of skewness

### Instrumental variable - Wikipedia

Instrumental variable methods allow for consistent ... Olav Reiersøl applied the same approach in the context of ... IV helps to fix this problem ...

### Graduate Course Offerings | Department of Statistics ...

Graduate Course Offerings. Course Number Title Credits; ... Advances in Applied Statistics IV: 3: 2401: Methods in Mathematical Statistics: 3: 2521: Time ...