Skip to content

Commit dda4d96

Browse files
authored
Merge pull request #67 from StatProofBook/master
update to master
2 parents 10d5d4b + 0dca886 commit dda4d96

9 files changed

Lines changed: 30 additions & 41 deletions

File tree

D/exc.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -27,13 +27,13 @@ username: "JoramSoch"
2727
---
2828

2929

30-
**Definition:** Generally speaking, [random events](/D/reve) are mutually exclusive, if the [probability](/D/prob) of their disjunction can be expressed in terms of their [marginal probabilities](/D/prob-marg).
30+
**Definition:** Generally speaking, [random events](/D/reve) are mutually exclusive, if they cannot occur together, such that their intersection is equal to the [empty set](/P/prob-emp).
3131

3232
<br>
3333
More precisely, a set of statements $A_1, \ldots, A_n$ is called mutually exclusive, if
3434

3535
$$ \label{eq:exc}
36-
p(A_1 \vee \ldots \vee A_n) = \sum_{i=1}^n p(A_i)
36+
p(A_1, \ldots, A_n) = 0
3737
$$
3838

39-
where $p(A_1, \ldots, A_n)$ is the [probability](/D/prob) of the disjunction of $A_1, \ldots, A_n$ and $p(A_i)$ is the [marginal probability](/D/prob-marg) of $A_i$, for all $i = 1, \ldots, n$.
39+
where $p(A_1, \ldots, A_n)$ is the [joint probability](/D/prob-joint) of the statements $A_1, \ldots, A_n$.

D/prob-marg.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -35,13 +35,13 @@ username: "JoramSoch"
3535

3636
**Definition:** (law of marginal probability, also called "sum rule") Let $A$ and $X$ be two arbitrary statements about [random variables](/D/rvar), such as statements about the presence or absence of an event or about the value of a scalar, vector or matrix. Furthermore, assume a [joint probability](/D/prob-joint) distribution $p(A,X)$. Then, $p(A)$ is called the marginal probability of $A$ and,
3737

38-
1) if $X$ is a discrete [random variable](/D/rvar) with domain $\mathcal{X}$, is given by
38+
1) if $X$ is a [discrete](/D/rvar-disc) [random variable](/D/rvar) with domain $\mathcal{X}$, is given by
3939

4040
$$ \label{eq:prob-marg-disc}
4141
p(A) = \sum_{x \in \mathcal{X}} p(A,x) \; ;
4242
$$
4343

44-
2) if $X$ is a continuous [random variable](/D/rvar) with domain $\mathcal{X}$, is given by
44+
2) if $X$ is a [continuous](/D/rvar-disc) [random variable](/D/rvar) with domain $\mathcal{X}$, is given by
4545

4646
$$ \label{eq:prob-marg-cont}
4747
p(A) = \int_{\mathcal{X}} p(A,x) \, \mathrm{d}x \; .

I/Proof_by_Author.md

Lines changed: 3 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@ title: "Proof by Author"
44
---
55

66

7-
### JoramSoch (252 proofs)
7+
### JoramSoch (254 proofs)
88

99
- [(Non-)Multiplicativity of the expected value](/P/mean-mult)
1010
- [Accuracy and complexity for the univariate Gaussian](/P/ug-anc)
@@ -186,6 +186,7 @@ title: "Proof by Author"
186186
- [Probability density function of a sum of independent discrete random variables](/P/pdf-sumind)
187187
- [Probability density function of an invertible function of a continuous random vector](/P/pdf-invfct)
188188
- [Probability density function of the Dirichlet distribution](/P/dir-pdf)
189+
- [Probability density function of the F-distribution](/P/f-pdf)
189190
- [Probability density function of the beta distribution](/P/beta-pdf)
190191
- [Probability density function of the chi-squared distribution](/P/chi2-pdf)
191192
- [Probability density function of the continuous uniform distribution](/P/cuni-pdf)
@@ -195,6 +196,7 @@ title: "Proof by Author"
195196
- [Probability density function of the multivariate normal distribution](/P/mvn-pdf)
196197
- [Probability density function of the normal distribution](/P/norm-pdf)
197198
- [Probability density function of the normal-gamma distribution](/P/ng-pdf)
199+
- [Probability density function of the t-distribution](/P/t-pdf)
198200
- [Probability integral transform using cumulative distribution function](/P/cdf-pit)
199201
- [Probability mass function of a strictly decreasing function of a discrete random variable](/P/pmf-sdfct)
200202
- [Probability mass function of a strictly increasing function of a discrete random variable](/P/pmf-sifct)

I/Proof_by_Number.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -268,3 +268,5 @@ title: "Proof by Number"
268268
| P260 | mgf-fct | [Moment-generating function of a function of a random variable](/P/mgf-fct) | JoramSoch | 2021-09-22 |
269269
| P261 | dent-addvec | [Addition of the differential entropy upon multiplication with invertible matrix](/P/dent-addvec) | JoramSoch | 2021-10-07 |
270270
| P262 | dent-noninv | [Non-invariance of the differential entropy under change of variables](/P/dent-noninv) | JoramSoch | 2021-10-07 |
271+
| P263 | t-pdf | [Probability density function of the t-distribution](/P/t-pdf) | JoramSoch | 2021-10-12 |
272+
| P264 | f-pdf | [Probability density function of the F-distribution](/P/f-pdf) | JoramSoch | 2021-10-12 |

I/Proof_by_Topic.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -236,6 +236,7 @@ title: "Proof by Topic"
236236
- [Probability density function of a sum of independent discrete random variables](/P/pdf-sumind)
237237
- [Probability density function of an invertible function of a continuous random vector](/P/pdf-invfct)
238238
- [Probability density function of the Dirichlet distribution](/P/dir-pdf)
239+
- [Probability density function of the F-distribution](/P/f-pdf)
239240
- [Probability density function of the Wald distribution](/P/wald-pdf)
240241
- [Probability density function of the beta distribution](/P/beta-pdf)
241242
- [Probability density function of the chi-squared distribution](/P/chi2-pdf)
@@ -246,6 +247,7 @@ title: "Proof by Topic"
246247
- [Probability density function of the multivariate normal distribution](/P/mvn-pdf)
247248
- [Probability density function of the normal distribution](/P/norm-pdf)
248249
- [Probability density function of the normal-gamma distribution](/P/ng-pdf)
250+
- [Probability density function of the t-distribution](/P/t-pdf)
249251
- [Probability integral transform using cumulative distribution function](/P/cdf-pit)
250252
- [Probability mass function of a strictly decreasing function of a discrete random variable](/P/pmf-sdfct)
251253
- [Probability mass function of a strictly increasing function of a discrete random variable](/P/pmf-sifct)

P/f-pdf.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@ mathjax: true
55
author: "Joram Soch"
66
affiliation: "BCCN Berlin"
77
e_mail: "joram.soch@bccn-berlin.de"
8-
date: 2021-10-12 09:00
8+
date: 2021-10-12 09:00:00
99

1010
title: "Probability density function of the F-distribution"
1111
chapter: "Probability Distributions"
@@ -43,7 +43,7 @@ $$
4343
**Proof:** An [F-distributed random variable](/D/f) is defined as the ratio of two [chi-squared random variables](/D/chi2), divided by their [degrees of freedom](/D/dof)
4444

4545
$$ \label{eq:f-def}
46-
X \sim \chi^2(u), \; Y \sim \chi^2(v) \quad \Rightarrow \quad F = \frac{X/u}{\sqrt{Y/v}} \sim F(u,v)
46+
X \sim \chi^2(u), \; Y \sim \chi^2(v) \quad \Rightarrow \quad F = \frac{X/u}{Y/v} \sim F(u,v)
4747
$$
4848

4949
where $X$ and $Y$ are [independent of each other](/D/ind).
@@ -110,7 +110,7 @@ f_{F,W}(f,w) &= f_X\left( \frac{u}{v} f w \right) \cdot f_Y(w) \cdot \lvert J \r
110110
\end{split}
111111
$$
112112

113-
The [marginal density](/D/dist-marg) of $F$ can now be [obtained by integrating out](/D/dist-marg) $W$:
113+
The [marginal density](/D/dist-marg) of $F$ can now be [obtained by integrating out](/D/prob-marg) $W$:
114114

115115
$$ \label{eq:f-F-s1}
116116
\begin{split}

P/prob-emp.md

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -25,7 +25,8 @@ sources:
2525
title: "Probability and Statistical Inference"
2626
in: "Kendall's Advanced Theory of Statistics, Vol. 1: Distribution Theory"
2727
pages: "ch. 8.6, p. 288, eq. (b)"
28-
url: "https://www.wiley.com/en-us/Kendall%27s+Advanced+Theory+of+Statistics%2C+3+Volumes%2C+Set%2C+6th+Edition-p-9780470669549" - authors: "Wikipedia"
28+
url: "https://www.wiley.com/en-us/Kendall%27s+Advanced+Theory+of+Statistics%2C+3+Volumes%2C+Set%2C+6th+Edition-p-9780470669549"
29+
- authors: "Wikipedia"
2930
year: 2021
3031
title: "Probability axioms"
3132
in: "Wikipedia, the free encyclopedia"

P/prob-exc.md

Lines changed: 12 additions & 30 deletions
Original file line numberDiff line numberDiff line change
@@ -27,51 +27,33 @@ username: "JoramSoch"
2727
---
2828

2929

30-
**Theorem:** Let $A$ and $B$ be two statements about [random variables](/D/rvar). Then, if $A$ and $B$ are [mutually exclusive](/D/exc), their [joint probability](/D/prob-joint) is zero:
30+
**Theorem:** Let $A$ and $B$ be two statements about [random variables](/D/rvar). Then, if $A$ and $B$ are [mutually exclusive](/D/exc), the [probability](/D/prob) of their disjunction is equal to the sum of the [marginal probabilities](/D/prob-marg):
3131

3232
$$ \label{eq:prob-exc}
33-
p(A,B) = 0 \; .
33+
p(A \vee B) = p(A) + p(B) \; .
3434
$$
3535

3636

37-
**Proof:** If $A$ and $B$ are [mutually exclusive](/D/exc), then the [probability](/D/prob) of their disjunction is the sum of the [marginal probabilities](/D/prob-marg):
37+
**Proof:** If $A$ and $B$ are [mutually exclusive](/D/exc), then their [joint probability](/D/prob-joint) is zero:
3838

3939
$$ \label{eq:exc}
40-
p(A \vee B) = p(A) + p(B) \; .
41-
$$
42-
43-
The [law of marginal probability](/D/prob-marg) implies that
44-
45-
$$ \label{eq:prob-marg}
46-
\begin{split}
47-
p(A) &= p(A,B) + p(A,\overline{B}) \\
48-
p(B) &= p(A,B) + p(\overline{A},B)
49-
\end{split}
40+
p(A,B) = 0 \; .
5041
$$
5142

52-
where $\overline{A}$ and $\overline{B}$ are the complements of $A$ and $B$. The probability of the disjunction $p(A \vee B)$ can also be expressed as the probability of a disjunction of three mutually exclusive statements
43+
The [addition law of probability](/D/prob-marg) states that
5344

54-
$$ \label{eq:prob-exc-s1}
55-
p(A \vee B) = p\left([A \wedge \overline{B}] \vee [\overline{A} \wedge B] \vee [A \wedge B] \right) \; ,
45+
$$ \label{eq:prob-add-set}
46+
p(A \cup B) = p(A) + p(B) - p(A \cap B)
5647
$$
5748

58-
such that the definition of exclusivity can be applied to give
49+
which, in logical rather than set-theoretic expression, becomes
5950

60-
$$ \label{eq:prob-exc-s2}
61-
\begin{split}
62-
p(A \vee B) &\overset{\eqref{eq:prob-exc-s1}}{=} p\left([A \wedge \overline{B}] \vee [\overline{A} \wedge B] \vee [A \wedge B] \right) \\
63-
&\overset{\eqref{eq:exc}}{=} p(A,\overline{B}) + p(\overline{A},B) + p(A,B) \\
64-
&= [p(A,\overline{B}) + p(A,B)] + [p(\overline{A},B) + p(A,B)] - p(A,B) \\
65-
&\overset{\eqref{eq:prob-marg}}{=} p(A) + p(B) - p(A,B) \; .
66-
\end{split}
51+
$$ \label{eq:prob-add-log}
52+
p(A \vee B) = p(A) + p(B) - p(A,B) \; .
6753
$$
6854

69-
Since $A$ and $B$ are [mutually exclusive](/D/exc), we obtain:
55+
Because the [union of mutually exclusive events is the empty set](/D/exc) and the [probability of the empty set is zero](/P/prob-emp), the [joint probability](/D/prob-joint) term cancels out:
7056

7157
$$ \label{eq:prob-exc-qed}
72-
\begin{split}
73-
p(A \vee B) &\overset{\eqref{eq:prob-exc-s2}}{=} p(A) + p(B) - p(A,B) \\
74-
p(A \vee B) &\overset{\eqref{eq:exc}}{=} p(A \vee B) - p(A,B) \\
75-
p(A,B) &= 0 \; .
76-
\end{split}
58+
p(A \vee B) = p(A) + p(B) - p(A,B) \overset{\eqref{eq:exc}}{=} p(A) + p(B) \; .
7759
$$

P/t-pdf.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -116,7 +116,7 @@ f_{T,W}(t,w) &= f_X\left( t \cdot \sqrt{\frac{w}{\nu}} \right) \cdot f_Y(w) \cdo
116116
\end{split}
117117
$$
118118

119-
The [marginal density](/D/dist-marg) of $T$ can now be [obtained by integrating out](/D/dist-marg) $W$:
119+
The [marginal density](/D/dist-marg) of $T$ can now be [obtained by integrating out](/D/prob-marg) $W$:
120120

121121
$$ \label{eq:f-T-s1}
122122
\begin{split}

0 commit comments

Comments
 (0)