CFA

HPR

3 types of return

• Realized Return
• Expected Return
• Required Return

Required Return

• on common stock: cost of equity
• on debt: cost of debt

Expected Alpha

Expected Return - Required Return

Realized Alpha

Actual HPR - Contemporaneous required returnbook

Hypothesis Testing

Lv 1 Reading 12

What does it do?

• Essensially the "Equal" sign in statistics world

• the process of making judgments about a larger group (a population) on the basis of a smaller group actually observed (a sample).

• The concepts and tools of hypothesis testing provide an objective means to gauge whether the available evidence supports the hypothesis.

Steps

1. Stating the hypothesis

2. Identifying the appropriate test statistic & its probability distribution

3. Specifying the significance level

4. Stating the decision rule

5. Collecting the data & calculating the test statistic

6. Making the statistical decision

Sorts of Tests

• Single mean
• Diff between two means
• Single variance
• Equality (Inequality) of Two Variances
• Correlation Coefficient diff from 0 （Level 2)
• Regression Model (intercept / slope coefficient) (Level 2)

Single Mean

t-test for single mean

• test statistic:

• probability distribution: t-distribution

z-test for single mean

• test statistic:

• probability distribution: normal distribution

Diff between two means

Single Variance

• test statistic:

• probability distribution: chi square distribution

Equality (Inequality) of Two Variances

• test statistic:

• probability distribution: F-distribution

Correlation Coefficient diff from 0

• test statistic:

• probability distribution: t-distribution

Regression Model

• test statistic:

• probability distribution: t-distribution

* Warning: for linear regression with 2 or more variables, the df need to minus more than 2

Diff between regression t-sest & anova's F-test

• F-statistic tests whether all the slope coefficients in a linear regression are equal to 0.
• t-statistic tests whether certain slope coefficient is equal to 0.

Assumptions

Level 2 Reading 9,10

Assumptions for single regression

Assumptions for multiple regression

Violations of regression assumptions

1. Heteroskedasticity

2. Serial Correlation

3. Multicollinearity

Heteroskedasticity

1. how it affects

2. how to test( Breusch-Pagan test)

3. how to correct it（robust standard errors / generalized least squares)

1. unconditional heteroskedasticity

2. conditional heteroskedasticity

Model Specification

How to choose model?

metrics

1. SEE ( valuate how certian we are )

2. Coefficient of Determination ( valuate how well it explains )

Calculation: Coefficient of Determination

* If is one-variable dependency, R2 = square(correlation)

* unexplained variation: ( Y - Yhat ) ^ 2

* there is a adjusted R^2 for multiple regression

ANOVA

a statistical procedure for dividing the total variability of a variable into components that can be attributed to different sources

The F-statistic tests whether all the slope coefficients in a linear regression are equal to 0.

Abbreviates

SSE: sum of squared errors or residuals, sum[(Y - Yhat)^2]

RSS: regression sum of squares, sum[ (Yhat - Ymean)^2 ]

Time-Series Analysis

Level2 Reading 11

Models

1. Linear Trend

2. Log-Linear Trend

3. Autoregressive

4. Random Walks

5. Moving-Average

6. Autoregressive Moving-Average

Economic Growth & Investment Decision

A Long-Term Framework

A Trading Strategy

Related Factors

Valuation: Applications & Processes

CFA II Reading 27

What is Value?

• Intrinsic Value
• Going-concern Value
• Liquidation Value
• Fair Value
• Investment Value

Who uses equity valuations

• Selecting Stock
• Inferring(extracting) Market Expectations
• Evaluating corporate events(Investment Bankers, Corporate Analysts, Investment Analysts)
• Rendering Fairness Opinions
• Evaluating business strategies & models
• Communicating with analysts & shareholders
• Appraising Private Businesses
• Share-based payment(compensation)

Valuation Process

• Understanding the business
• Forecasting company performance
• Selecting the appropriate valuation model
• Converting forecasts to a valuation
• sensitivity analysis
• situational adjustments
• control premium
• lack of marketability discount
• illiquidity discount
• blockage factor
• Applying the valuation conclusions

Importance of Indeustry Knowleadge

• Labor Costs
• Natural Resource Costs
• Frameworks: Such as Porter's Five Forces

3 Generic Corporate Strategies

• Cost leadership
• Differentiation
• Focus

How can analyst communicate his analysis?

Intrinsic Value

• Grossman-Stiglitz paradox
• Abnormal Return(Alpha)
• Ve - P = (V - P) + (Ve - V)
• 有些人Someone look not only for mispricing but also for catalyst

Other

Conglomerate discount (Page. 28)

Equity Returns

CFA Level II Reading 28

Required Return

• CAPM
• multifactor model(Fama-French)
• build-up method(bond yield + risk premium)

Industry Analysis & Company Analysis

CFA Level 2 Reading 29

Goal: Forecast company's future financial results

Financial Modeling

• Income Statement Modeling
• Balance Sheet & Cash Flow Statement Modeling

Mainly forcus on revenue & cost

Competitive factors

Affect price & costs. use Porter's five forces

Inflation & Deflation

Technological Developments

Cannibalize demand

Long-term Forecasting

Discounted Dividend Valuation

Free Cash Flow Valuation

Market-Based Valuation

Residual Income Valuation

Private Company Valuation

Criterias

• NPV
• IRR
• Payback Period
• Discounted Payback Period
• AAR
• PI
• NPV Profile

Cash Flow Projection

How to choose projects

Project analysis and evaluation