distribution according to random measures
Is a random probability measure a probability measure, i.e. if $X_i$ is random variable on some probability space $(Omega,mathcal F,mathbb P)$ could its induced distribution be a random probability measure $mu$, say $X_isim mu$?
Then, as $mu$ is itself random, it has an own probability distribution, $musim Q$.
For example let's take the empirical measure $P_n(A)=frac{1}{n}sum_{i=1}^n delta_{X_i}(A)$. Then the empirical distribution function $F_n(x):=frac{1}{n}sum_{i=1}^n 1{X_ile x}$ is a random probability measure as it is an empirical measure indexed by the class $mathcal C={(-infty,x]: xin mathbb R}$? Can one say $X_isim P_n$?
probability probability-theory measure-theory random-variables random
add a comment |
Is a random probability measure a probability measure, i.e. if $X_i$ is random variable on some probability space $(Omega,mathcal F,mathbb P)$ could its induced distribution be a random probability measure $mu$, say $X_isim mu$?
Then, as $mu$ is itself random, it has an own probability distribution, $musim Q$.
For example let's take the empirical measure $P_n(A)=frac{1}{n}sum_{i=1}^n delta_{X_i}(A)$. Then the empirical distribution function $F_n(x):=frac{1}{n}sum_{i=1}^n 1{X_ile x}$ is a random probability measure as it is an empirical measure indexed by the class $mathcal C={(-infty,x]: xin mathbb R}$? Can one say $X_isim P_n$?
probability probability-theory measure-theory random-variables random
add a comment |
Is a random probability measure a probability measure, i.e. if $X_i$ is random variable on some probability space $(Omega,mathcal F,mathbb P)$ could its induced distribution be a random probability measure $mu$, say $X_isim mu$?
Then, as $mu$ is itself random, it has an own probability distribution, $musim Q$.
For example let's take the empirical measure $P_n(A)=frac{1}{n}sum_{i=1}^n delta_{X_i}(A)$. Then the empirical distribution function $F_n(x):=frac{1}{n}sum_{i=1}^n 1{X_ile x}$ is a random probability measure as it is an empirical measure indexed by the class $mathcal C={(-infty,x]: xin mathbb R}$? Can one say $X_isim P_n$?
probability probability-theory measure-theory random-variables random
Is a random probability measure a probability measure, i.e. if $X_i$ is random variable on some probability space $(Omega,mathcal F,mathbb P)$ could its induced distribution be a random probability measure $mu$, say $X_isim mu$?
Then, as $mu$ is itself random, it has an own probability distribution, $musim Q$.
For example let's take the empirical measure $P_n(A)=frac{1}{n}sum_{i=1}^n delta_{X_i}(A)$. Then the empirical distribution function $F_n(x):=frac{1}{n}sum_{i=1}^n 1{X_ile x}$ is a random probability measure as it is an empirical measure indexed by the class $mathcal C={(-infty,x]: xin mathbb R}$? Can one say $X_isim P_n$?
probability probability-theory measure-theory random-variables random
probability probability-theory measure-theory random-variables random
asked 2 days ago
lemontree
1588
1588
add a comment |
add a comment |
1 Answer
1
active
oldest
votes
For a random measure, it is just the case that $Omega = mathcal{P}$ the set of all probability measures on space. For example $P_n$ in your definition.
The empirical measure is a random variable on the space of functions. This measure is obtained via taking the push forward measure of the mapping $pi: mathcal{P}(mathbb{R}) mapsto mathcal{S}$, where $mathcal{S}$ is the collection of step functions in $mathbb{R}$.
$Xsim mu$ is for a fixed measure $mu$. In your example, you cannot say $X_i sim P_n$ because the distribution $X_i$'s is something from which you have drawn the random variables $X_i$'s to construct the measure in the first place ($P_n$ is just a function of $X_i$'s). But, if you wanted mean that $X$ is a "sample" from the empirical measure, then you have to keep in mind that there are two steps of randomness. The first step to construct the measure, and the second is taking a sample from $P_n$ conditionally on the $X_i$'s in the first step. So one needs to write the distribution of $X$ using a conditional distribution.
New contributor
Consider you have a sample $X=(X_1,dots, X_n).$ Now assume $X_imid mu sim mu$ and $musim Q$, where $mu$ is a random probability measure and $Q$ is the Distribution of the random probability measure. I think that is an example for the "two steps of randomness" you talked about. Can you explain what $X_imid mu sim mu$ means and why we can't use/ what's the difference to $X_isim mu$? Many thanks!
– lemontree
2 days ago
The conditional distribution will be a discrete measure. Suppose you toss a coin 6 times and you get TTHTTH. So your empirical measure $P_n$ will give mass 1/3 on head and 2/3 on tail. But $X_1$ is Bernoulli$(1/2)$. What you can do is take a new coin with respect to the observed empirical measure. The outcome $Y$ will be Bernoulli $(1/3)$ conditional on the event that there are exactly $2$ heads among $(X_1,dots,X_6)$.
– Aragon
2 days ago
add a comment |
Your Answer
StackExchange.ifUsing("editor", function () {
return StackExchange.using("mathjaxEditing", function () {
StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix) {
StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
});
});
}, "mathjax-editing");
StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "69"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});
function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
noCode: true, onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});
}
});
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fmath.stackexchange.com%2fquestions%2f3060792%2fdistribution-according-to-random-measures%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
For a random measure, it is just the case that $Omega = mathcal{P}$ the set of all probability measures on space. For example $P_n$ in your definition.
The empirical measure is a random variable on the space of functions. This measure is obtained via taking the push forward measure of the mapping $pi: mathcal{P}(mathbb{R}) mapsto mathcal{S}$, where $mathcal{S}$ is the collection of step functions in $mathbb{R}$.
$Xsim mu$ is for a fixed measure $mu$. In your example, you cannot say $X_i sim P_n$ because the distribution $X_i$'s is something from which you have drawn the random variables $X_i$'s to construct the measure in the first place ($P_n$ is just a function of $X_i$'s). But, if you wanted mean that $X$ is a "sample" from the empirical measure, then you have to keep in mind that there are two steps of randomness. The first step to construct the measure, and the second is taking a sample from $P_n$ conditionally on the $X_i$'s in the first step. So one needs to write the distribution of $X$ using a conditional distribution.
New contributor
Consider you have a sample $X=(X_1,dots, X_n).$ Now assume $X_imid mu sim mu$ and $musim Q$, where $mu$ is a random probability measure and $Q$ is the Distribution of the random probability measure. I think that is an example for the "two steps of randomness" you talked about. Can you explain what $X_imid mu sim mu$ means and why we can't use/ what's the difference to $X_isim mu$? Many thanks!
– lemontree
2 days ago
The conditional distribution will be a discrete measure. Suppose you toss a coin 6 times and you get TTHTTH. So your empirical measure $P_n$ will give mass 1/3 on head and 2/3 on tail. But $X_1$ is Bernoulli$(1/2)$. What you can do is take a new coin with respect to the observed empirical measure. The outcome $Y$ will be Bernoulli $(1/3)$ conditional on the event that there are exactly $2$ heads among $(X_1,dots,X_6)$.
– Aragon
2 days ago
add a comment |
For a random measure, it is just the case that $Omega = mathcal{P}$ the set of all probability measures on space. For example $P_n$ in your definition.
The empirical measure is a random variable on the space of functions. This measure is obtained via taking the push forward measure of the mapping $pi: mathcal{P}(mathbb{R}) mapsto mathcal{S}$, where $mathcal{S}$ is the collection of step functions in $mathbb{R}$.
$Xsim mu$ is for a fixed measure $mu$. In your example, you cannot say $X_i sim P_n$ because the distribution $X_i$'s is something from which you have drawn the random variables $X_i$'s to construct the measure in the first place ($P_n$ is just a function of $X_i$'s). But, if you wanted mean that $X$ is a "sample" from the empirical measure, then you have to keep in mind that there are two steps of randomness. The first step to construct the measure, and the second is taking a sample from $P_n$ conditionally on the $X_i$'s in the first step. So one needs to write the distribution of $X$ using a conditional distribution.
New contributor
Consider you have a sample $X=(X_1,dots, X_n).$ Now assume $X_imid mu sim mu$ and $musim Q$, where $mu$ is a random probability measure and $Q$ is the Distribution of the random probability measure. I think that is an example for the "two steps of randomness" you talked about. Can you explain what $X_imid mu sim mu$ means and why we can't use/ what's the difference to $X_isim mu$? Many thanks!
– lemontree
2 days ago
The conditional distribution will be a discrete measure. Suppose you toss a coin 6 times and you get TTHTTH. So your empirical measure $P_n$ will give mass 1/3 on head and 2/3 on tail. But $X_1$ is Bernoulli$(1/2)$. What you can do is take a new coin with respect to the observed empirical measure. The outcome $Y$ will be Bernoulli $(1/3)$ conditional on the event that there are exactly $2$ heads among $(X_1,dots,X_6)$.
– Aragon
2 days ago
add a comment |
For a random measure, it is just the case that $Omega = mathcal{P}$ the set of all probability measures on space. For example $P_n$ in your definition.
The empirical measure is a random variable on the space of functions. This measure is obtained via taking the push forward measure of the mapping $pi: mathcal{P}(mathbb{R}) mapsto mathcal{S}$, where $mathcal{S}$ is the collection of step functions in $mathbb{R}$.
$Xsim mu$ is for a fixed measure $mu$. In your example, you cannot say $X_i sim P_n$ because the distribution $X_i$'s is something from which you have drawn the random variables $X_i$'s to construct the measure in the first place ($P_n$ is just a function of $X_i$'s). But, if you wanted mean that $X$ is a "sample" from the empirical measure, then you have to keep in mind that there are two steps of randomness. The first step to construct the measure, and the second is taking a sample from $P_n$ conditionally on the $X_i$'s in the first step. So one needs to write the distribution of $X$ using a conditional distribution.
New contributor
For a random measure, it is just the case that $Omega = mathcal{P}$ the set of all probability measures on space. For example $P_n$ in your definition.
The empirical measure is a random variable on the space of functions. This measure is obtained via taking the push forward measure of the mapping $pi: mathcal{P}(mathbb{R}) mapsto mathcal{S}$, where $mathcal{S}$ is the collection of step functions in $mathbb{R}$.
$Xsim mu$ is for a fixed measure $mu$. In your example, you cannot say $X_i sim P_n$ because the distribution $X_i$'s is something from which you have drawn the random variables $X_i$'s to construct the measure in the first place ($P_n$ is just a function of $X_i$'s). But, if you wanted mean that $X$ is a "sample" from the empirical measure, then you have to keep in mind that there are two steps of randomness. The first step to construct the measure, and the second is taking a sample from $P_n$ conditionally on the $X_i$'s in the first step. So one needs to write the distribution of $X$ using a conditional distribution.
New contributor
New contributor
answered 2 days ago
Aragon
213
213
New contributor
New contributor
Consider you have a sample $X=(X_1,dots, X_n).$ Now assume $X_imid mu sim mu$ and $musim Q$, where $mu$ is a random probability measure and $Q$ is the Distribution of the random probability measure. I think that is an example for the "two steps of randomness" you talked about. Can you explain what $X_imid mu sim mu$ means and why we can't use/ what's the difference to $X_isim mu$? Many thanks!
– lemontree
2 days ago
The conditional distribution will be a discrete measure. Suppose you toss a coin 6 times and you get TTHTTH. So your empirical measure $P_n$ will give mass 1/3 on head and 2/3 on tail. But $X_1$ is Bernoulli$(1/2)$. What you can do is take a new coin with respect to the observed empirical measure. The outcome $Y$ will be Bernoulli $(1/3)$ conditional on the event that there are exactly $2$ heads among $(X_1,dots,X_6)$.
– Aragon
2 days ago
add a comment |
Consider you have a sample $X=(X_1,dots, X_n).$ Now assume $X_imid mu sim mu$ and $musim Q$, where $mu$ is a random probability measure and $Q$ is the Distribution of the random probability measure. I think that is an example for the "two steps of randomness" you talked about. Can you explain what $X_imid mu sim mu$ means and why we can't use/ what's the difference to $X_isim mu$? Many thanks!
– lemontree
2 days ago
The conditional distribution will be a discrete measure. Suppose you toss a coin 6 times and you get TTHTTH. So your empirical measure $P_n$ will give mass 1/3 on head and 2/3 on tail. But $X_1$ is Bernoulli$(1/2)$. What you can do is take a new coin with respect to the observed empirical measure. The outcome $Y$ will be Bernoulli $(1/3)$ conditional on the event that there are exactly $2$ heads among $(X_1,dots,X_6)$.
– Aragon
2 days ago
Consider you have a sample $X=(X_1,dots, X_n).$ Now assume $X_imid mu sim mu$ and $musim Q$, where $mu$ is a random probability measure and $Q$ is the Distribution of the random probability measure. I think that is an example for the "two steps of randomness" you talked about. Can you explain what $X_imid mu sim mu$ means and why we can't use/ what's the difference to $X_isim mu$? Many thanks!
– lemontree
2 days ago
Consider you have a sample $X=(X_1,dots, X_n).$ Now assume $X_imid mu sim mu$ and $musim Q$, where $mu$ is a random probability measure and $Q$ is the Distribution of the random probability measure. I think that is an example for the "two steps of randomness" you talked about. Can you explain what $X_imid mu sim mu$ means and why we can't use/ what's the difference to $X_isim mu$? Many thanks!
– lemontree
2 days ago
The conditional distribution will be a discrete measure. Suppose you toss a coin 6 times and you get TTHTTH. So your empirical measure $P_n$ will give mass 1/3 on head and 2/3 on tail. But $X_1$ is Bernoulli$(1/2)$. What you can do is take a new coin with respect to the observed empirical measure. The outcome $Y$ will be Bernoulli $(1/3)$ conditional on the event that there are exactly $2$ heads among $(X_1,dots,X_6)$.
– Aragon
2 days ago
The conditional distribution will be a discrete measure. Suppose you toss a coin 6 times and you get TTHTTH. So your empirical measure $P_n$ will give mass 1/3 on head and 2/3 on tail. But $X_1$ is Bernoulli$(1/2)$. What you can do is take a new coin with respect to the observed empirical measure. The outcome $Y$ will be Bernoulli $(1/3)$ conditional on the event that there are exactly $2$ heads among $(X_1,dots,X_6)$.
– Aragon
2 days ago
add a comment |
Thanks for contributing an answer to Mathematics Stack Exchange!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
Use MathJax to format equations. MathJax reference.
To learn more, see our tips on writing great answers.
Some of your past answers have not been well-received, and you're in danger of being blocked from answering.
Please pay close attention to the following guidance:
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fmath.stackexchange.com%2fquestions%2f3060792%2fdistribution-according-to-random-measures%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown