QTA 2 - RANDOM VARIABLES Flashcards

1
Q

What is the difference between a probability mass function (PMF) and a cumulative distribution function (CDF)?

A

PMF assigns probabilities to distinct values of a discrete random variable, while CDF measures the total probability of observing a value less than or equal to a given input.

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

What are the four common population moments?

A
  • Mean
  • Variance
  • Skewness
  • Kurtosis
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What does the quantile function represent?

A

The quantile function is the inverse of the CDF and defines two moment-like measures: the median and the interquartile range.

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

How do continuous random variables differ from discrete random variables?

A

Continuous random variables produce values from an uncountable set, while discrete random variables produce distinct values.

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

What are the properties of a probability mass function (PMF)?

A
  • Must return non-negative values
  • The sum of all probabilities in the support must equal one
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What is the formula for the cumulative distribution function (CDF) in relation to PMF?

A

F_X(x) = Σ f_X(t) for all t in R(X) where t ≤ x.

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

What is the expected value of a random variable?

A

The expected value is the weighted average of all possible outcomes, where the weights are the probabilities of those outcomes.

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

How is the expected value of a Bernoulli random variable calculated?

A

E[X] = 0 × (1 - p) + 1 × p = p.

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

What is Jensen’s inequality?

A

Jensen’s inequality states that for a concave function, E[h(X)] < h(E[X]), and for a convex function, E[g(X)] > g(E[X]).

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

What is the variance of a random variable?

A

The variance measures the degree to which the values of a random variable differ from its expected value and is defined as σ² = E[(X - μ)²].

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

Define skewness in the context of random variables.

A

Skewness measures the asymmetry of a distribution, calculated as E[(X - μ)³]/σ³.

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

What does kurtosis indicate about a random variable?

A

Kurtosis measures the heaviness of the tails of a distribution, with a normal distribution benchmarked at 3.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Fill in the blank: The expected value of a function of a random variable X is defined as E[f(X)] = _______.

A

Σ f(x) × P(X = x) for x in R(X).

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

What is the relationship between the CDF and PMF for discrete random variables?

A

The PMF can be derived from the CDF as f_X(x) = F_X(x) - F_X(x - 1).

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What is the expected value of a fair die roll?

A

E[X] = (1/6) × (1 + 2 + 3 + 4 + 5 + 6) = 3.5.

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

What is the standard deviation of a random variable?

A

The standard deviation is the square root of the variance and measures the volatility of a random variable.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

True or False: The expectation operator is a nonlinear operator.

18
Q

What is the support of a discrete random variable?

A

The set of distinct values that the random variable may take.

19
Q

What is the expected value of the exponential of a Bernoulli random variable?

A

E[exp(X)] = (1 - p) + p * exp(1).

20
Q

What is the expected value of a random variable expressed in a linear combination?

A

E[cX + a] = cE[X] + a, where c and a are constants.

21
Q

What does the term ‘support’ refer to in the context of a discrete random variable?

A

The support refers to the set of values that the random variable may take.

22
Q

What is the first moment of a random variable?

A

The first moment is the expected value, denoted as μ₁ = E[X].

23
Q

Fill in the blank: The expected value of a constant is _______.

A

the constant itself.

24
Q

What is the fourth standardized moment known as?

A

Kurtosis

Kurtosis measures the tails of the distribution.

25
Q

What is the kurtosis of a normally distributed random variable?

A

3

Kurtosis greater than 3 indicates heavy-tailed distributions.

26
Q

What type of distributions are described as heavy-tailed?

A

Distributions with kurtosis greater than 3

Financial return distributions are often heavy-tailed.

27
Q

How is a standardized version of a random variable (X) constructed?

A

Using the formula ( rac{X - mu}{sigma} )

This results in a variable with mean 0 and unit variance.

28
Q

What do (a) and (b) represent in the linear transformation (Y = a + bX)?

A

Location shift (a) and scale (b)

(a) affects the mean, and (b) affects the standard deviation.

29
Q

What is the effect of the location shift (a) on the variance of (Y)?

A

It has no effect

Variance measures deviations around the mean.

30
Q

If (b > 0), how do the skewness and kurtosis of (Y) compare to those of (X)?

A

They are identical

If (b < 0), skewness changes sign, but kurtosis remains unchanged.

31
Q

What is a continuous random variable?

A

A variable with a continuous support

It uses a probability density function (PDF) instead of a probability mass function (PMF).

32
Q

What is the integral property of a probability density function (PDF)?

A

The integral of the PDF across its support equals 1

This is similar to the summation property of a PMF.

33
Q

How can the PDF be derived from the cumulative distribution function (CDF)?

A

By taking the derivative of the CDF

The relationship is ( f_X(x) = rac{dF_X}{dx} ).

34
Q

What is the expectation (mean) of a continuous random variable (X)?

A

The integral ( E[X] = int x f_X(x) dx )

This calculates the average value of the variable.

35
Q

What is the definition of the α-quantile of a random variable (X)?

A

The smallest number (q) such that (Pr(X < q) = alpha)

This quantile function is denoted by (Q_X(alpha) = F^{-1}(alpha)).

36
Q

What does the median represent in a data set?

A

The 50% quantile

It is the middle value when the data is ranked in ascending order.

37
Q

How is the median calculated when there is an even number of observations?

A

It is the average of the two middle numbers

This ensures an accurate representation of the central tendency.

38
Q

What does the interquartile range (IQR) measure?

A

The difference between the 75% and 25% quantiles

It is a measure of dispersion that is less sensitive to outliers.

39
Q

Why are quantiles significant for random variables?

A

They are always well-defined, even for heavy-tailed distributions

Unlike moments, which may not be finite for heavy-tailed variables.

40
Q

What does the mode measure in a distribution?

A

The location of the most frequently observed values

In continuous distributions, it is the highest point in the PDF.