5016 - Investment and Financial Analysis - Personal Investment - Calculating Risk and Portfolio Theory p403 - 496 Flashcards
Risk is Volatility in Cashflows from…
- A Project (NPV based on forecast cashflow)
- Income (Interest/Dividends)
- Capital Gains (Sales - Purchases)
Volatility can be Measured by…
- Variance of periodic returns
- Standard Deviation of periodic returns
- Beta
What averages can be used to assess risk
Mean
Median
Mode
Variance
Are measures of how much the data varies or deviates from the mean
The mean of 4,5,6 is 5
The mean of 1,6,8 is 5
The second set of numbers has a greater variance
Standard Deviation
A quantity expressing how much the values differ or relate to the mean value of the entire group
How to calculate standard deviation
- Work out the mean
- From each number, subtract the mean and square the result
- Work out the mean of those squared differences
- Take the square root of that and that is it
Expected Value Standard Deviation Rule
If the return of project 1 is equal or more than project 2 and, the SD of project 1 is lower than project 2, project 1 should be done
or
If the expected return of project 1 is greater than project 2 and the SD of project 1 is equal to or more than project 2 it should be accepted
Risk depends upon what?
Covariance - how one performs and varies in comparison to the other
Correlation - The relation on investments in the portfolio e.g. if share A goes up and Share B goes down the Risk is offset
What determines the Risk of a 2 share portfolio
- Risk (SD) of asset/investment A by itself
- Risk (SD) of asset/investment B by itself
- Covariance/ Correlation between A and B
- Proportions of A and B in portfolio
What does Covariance show?
Positive Covariance shows a positive relationship between the returns of X and Y, negative shows the opposite. Looks at how one varies in relation to the other
What does Correlation show?
The correlation coefficient measures the strength of the relationship between A and B
What does r(Squared) represent
The Coefficient of Determination
What does the Coefficient of Determination indicate
It indicated the ‘explanatory power’ of the relationship, so by how much is an increase in costs explained by an increase in outputs (r^2)
What does the Coefficient of Determination Value show
The closer it is to 1, the greater its power, cannot rely on the relationship if it is not close to 1
For example if the change between the $ and Bitcoin was 0.85 or 85% we can see the change in the price of the dollar equates to 85% of the change in the price of Bitcoin, the other 15% would need to be investigated as this is down to other factors
What does The Correlation Coefficient Show
Indicates the strength of the relationship between 2 variables
The Correlation Coefficient has a value range of
-1 to 1
Correlation Coefficient Values and Meanings
r > 0 = They move in the same direction
r < 0 = They move in the opposite direction
r = 0 = No relationship
r = +1 = Perfectly Positive
r = -1 = Perfectly negative
Correlation Coefficient =
√r
Perfect Correlation
R = +1 is a perfectly positive correlation, goes up from left to right
R = -1 is a perfectly negative correlation goes down from left to right
For every unit increase or decrease in X, there is an equal increase or decrease in Y
Zero Correlation
r = 0, no correlation present
Partial Correlation
Where the data points are linked in a relationship.
Can either be positive or negative
Below 0.7 is considered a weak correlation and hence is unreliable
Calculating the Linear Regression Line (Correlation) y = bx + a
b =
nΣ XY – Σ X. Σ Y OVER nΣ X2 - (Σ X)2 (Gradient/slope)
a =
Σ Y - b Σ X OVER n (intercept of the line on the Y axis)
n = number of data pairs
Σ = Sum of total
Might need to know this for the exam, but id honestly rather die than try and figure this out on paper when we live in the 21st century - you would never need to do that in the real world
Fixed Costs
Costs that stay the same regardless of output
Variable Costs
Cost that change depending on output
What are Outliers?
An outlier is an observation that lies an abnormal distance from the other values in a random sample from a population, or an abnormal distance from the sample mean
Normal Distribution
Normal distribution is a probability distribution that is symmetric about the mean, showing the data near the mean are more frequent in occurrence than data far from the mean