1.2: Statistics Overview Flashcards

1
Q

What type of stocks tend to perform best over very long investment horizons (historically)?

A

Small stocks, but they also have periods of significant losses

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What do investors demand to bear a give level of risk?

A

A risk premium (in terms of a higher expected return)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What does a probability distribution do?

A

Assign a probability (pR) that each possible return R will occur

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What variance and standard deviation does a risk-free return have?

A

Zero

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What is the variance of a return?

A

A measure of how spread out the distribution of the return is

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What is a popular estimation approach when we don’t know the probability distribution?

A

To extrapolate from historical data. By counting the number of times realised return falls within a particular range, we can estimate the underlying probability distribution.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What does the mean return capture?

A

How much we make on average

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What probability distribution do monthly stock returns follow?

A

Approximately a normal distribution

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is the realised return?

A

The return that actually occurs over a particular time period

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Does the average return provide an estimate of the expected return?

A

Yes, it the probability distribution of returns is the same over time

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What is the standard error?

A

The estimation error of a statistical estimate; the standard deviation of the average return

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What are the necessary assumptions for how we calculate the standard error?

A
  • The distribution of returns is identical each year
  • Each year’s return is independent from prior years’ returns
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What is the excess return and what does it measure?

A

The difference between the average return for an investment and the average return for treasury bills (risk-free investment).

Measures the average risk premium investors earn for bearing the risk of the investment

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Is there a relationship historically between risk and return?

A
  • For large portfolios, yes! Higher risk is rewarded with higher average return as a compensation
  • For individual stocks, no.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What is an observed relationship between size and risk?

A

Larger stocks have lower volatility overall.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What are the two types of risk?

A
  1. Common risk: perfectly correlated and affects all securities
  2. Independent risk: uncorrelated and affects a particular security
17
Q

What is diversification?

A

The averaging out of independent risks in a large portfolio

18
Q

What does the risk of a portfolio depend on?

A

Whether the individual risks within it are common or independent. Independent risks are diversified in a large portfolio, while common risks are not

19
Q

What is firm-specific risk?

A

Only affects the company itself = independent risk. Also called idiosyncratic, unique, or diversifiable risk.

20
Q

What is systematic risk?

A

Affects the entire market = common risk. Also called undiversifiable, or market risk.

21
Q

How does volatility depend on the size of the portfolio?

A

When risk is diversified, the volatility declines with the size of the portfolio, until only the systematic risk remains

22
Q

What is the risk premium for diversifiable risk?

A

0.

Investors are not compensated for holding firm-specific risk, since they can “diversify it away”

23
Q

Why do investors require a risk premium for holding systematic risk?

A

Because they are risk averse and otherwise would be better off selling their stocks and investing in risk-free bonds

24
Q

What is the risk premium determined by?

A

The systematic risk of the security

25
Q

What are portfolio weights?

A

The fraction of the total investment in the portfolio held in each individual investment in the portfolio

26
Q

What is the total value of all the portfolio weights?

A

They always add up to 1. Individual weights can be negative (shorting or borrowing).

27
Q

What determines how much risk is eliminated in a portfolio?

A
  • The degree to which the stocks face common risks
  • The degree to which their prices move together
28
Q

What numbers is the correlation always between?

A

-1 and 1

29
Q

What is the variance of a portfolio?

A

The sum of the covariances of the returns of all pairs of stocks in the portfolio multiplied by each of their portfolio weights

30
Q

What can be said about the volatility of buying shares on margin (borrowing) compared to the volatility of the stock?

A

Your positions volatility will be higher than the volatility of the stock

31
Q

What is the formula for the standard error of the estimated expected return?

A

SE = SD(individual risk) / sqrt(number of observations)

32
Q

What is the formula for the 95% confidence interval for the expected return?

A

Historical average return +- (2*SE)

33
Q

What is the formula for the estimated covariance between the returns of two stocks?

A

Cov(Ri, Rj) = (1 / (n-1)) * (SUMOF (Ri -meanRi)*(Rj - meanRj)

34
Q

What is the formula for the correlation between the returns of two stock returns?

A

Corr(Ri, Rj) = Cov(Ri, Rj) / (SD(Ri) * SD(Rj) )

35
Q

How can we calculate the portfolio variance for a large portfolio?

A

Using the box method.

Each box is calculated by:
Weight(i) * Weight(j) * Cov(Ri, Rj)

Then, all boxes are summed up to get the portfolio variance