Log-likelihood of zero-truncated Poisson











up vote
1
down vote

favorite
1












Question:



Edwards and Eberhardt (1967) conducted a live-trapping study on a confined population of known size. In their study, wild cottontail
rabbits were penned in a 4-acre rabbit-proof enclosure. Live trapping was conducted for 18 consecutive
nights. Recorded capture frequencies were as follows: 43 rabbits were caught at exactly 1 night, 16
rabbits at 2 nights, 8 at 3 nights, 6 at four nights, 2 at 6 nights and 1 rabbit was caught at 7 nights. In
other words, we have observations from $X_1, · · · X_m$ count variables of m = 76 different, caught rabbits.
So, in this sample, 43 of the $x_1, · · · , x_m$ were ones, 16 twos, etc. Every count can take a maximum of
T = 18 captures. The number of of zero counts, i.e. the number of rabbits that were not caught, is
unobserved. We denote this additional sample as $X_{m+1}, · · · , X_n$. Assuming independence of trapping
occasions and homogeneity of capture probability θ at each occasion each $X_i$ would follow a binomial distribution. We assume here that a Poisson approximation is justified. That is:



$P(X_i = x) = frac{exp(−θT)(θt)^x}{x!}$ where i = 1, · · · , n.



Note that the observed sample is zero-truncated so that the observed sample can be considered as arising from the zero-truncated Poisson density:



$$exp(−θT)(θT)^x over (1 − exp(−θT))x!$$ for $i = 1, · · · , m$, $;θ ∈ (0, 1)$ and $x ∈ {0, 1, · · · , T}$.



Determine the log-likelihood function for the observed sample.



My solution:



I have already attempted this and got:
$sum_{i=1}^m n_ilogfrac{exp(−θT)(θT)^x}{x!}frac{1}{1 − exp(−θT)}$



Is this correct? If not, what should I have got? What have I done wrong?










share|cite|improve this question






















  • Someone's been doing the Dankmar's coursework here :P I think the context is not relevant anyway, you can just ask for the log-likelihood function of a zero-truncated Poisson distribution and its first and second order derivative
    – Euler_Salter
    Nov 21 at 22:42












  • @Euler_Salter haha yes! I thought context was good. Does it look right to you?
    – Vicky
    Nov 21 at 22:49










  • Yes but it could scare off lazy fellow stackexchangers, so it's nice to keep it short! Not sure now, I'm a bit tired, but I just found this: math.stackexchange.com/a/1857529/348937
    – Euler_Salter
    Nov 21 at 22:51










  • @Euler_Salter thanks! Will take a look.
    – Vicky
    Nov 21 at 22:53















up vote
1
down vote

favorite
1












Question:



Edwards and Eberhardt (1967) conducted a live-trapping study on a confined population of known size. In their study, wild cottontail
rabbits were penned in a 4-acre rabbit-proof enclosure. Live trapping was conducted for 18 consecutive
nights. Recorded capture frequencies were as follows: 43 rabbits were caught at exactly 1 night, 16
rabbits at 2 nights, 8 at 3 nights, 6 at four nights, 2 at 6 nights and 1 rabbit was caught at 7 nights. In
other words, we have observations from $X_1, · · · X_m$ count variables of m = 76 different, caught rabbits.
So, in this sample, 43 of the $x_1, · · · , x_m$ were ones, 16 twos, etc. Every count can take a maximum of
T = 18 captures. The number of of zero counts, i.e. the number of rabbits that were not caught, is
unobserved. We denote this additional sample as $X_{m+1}, · · · , X_n$. Assuming independence of trapping
occasions and homogeneity of capture probability θ at each occasion each $X_i$ would follow a binomial distribution. We assume here that a Poisson approximation is justified. That is:



$P(X_i = x) = frac{exp(−θT)(θt)^x}{x!}$ where i = 1, · · · , n.



Note that the observed sample is zero-truncated so that the observed sample can be considered as arising from the zero-truncated Poisson density:



$$exp(−θT)(θT)^x over (1 − exp(−θT))x!$$ for $i = 1, · · · , m$, $;θ ∈ (0, 1)$ and $x ∈ {0, 1, · · · , T}$.



Determine the log-likelihood function for the observed sample.



My solution:



I have already attempted this and got:
$sum_{i=1}^m n_ilogfrac{exp(−θT)(θT)^x}{x!}frac{1}{1 − exp(−θT)}$



Is this correct? If not, what should I have got? What have I done wrong?










share|cite|improve this question






















  • Someone's been doing the Dankmar's coursework here :P I think the context is not relevant anyway, you can just ask for the log-likelihood function of a zero-truncated Poisson distribution and its first and second order derivative
    – Euler_Salter
    Nov 21 at 22:42












  • @Euler_Salter haha yes! I thought context was good. Does it look right to you?
    – Vicky
    Nov 21 at 22:49










  • Yes but it could scare off lazy fellow stackexchangers, so it's nice to keep it short! Not sure now, I'm a bit tired, but I just found this: math.stackexchange.com/a/1857529/348937
    – Euler_Salter
    Nov 21 at 22:51










  • @Euler_Salter thanks! Will take a look.
    – Vicky
    Nov 21 at 22:53













up vote
1
down vote

favorite
1









up vote
1
down vote

favorite
1






1





Question:



Edwards and Eberhardt (1967) conducted a live-trapping study on a confined population of known size. In their study, wild cottontail
rabbits were penned in a 4-acre rabbit-proof enclosure. Live trapping was conducted for 18 consecutive
nights. Recorded capture frequencies were as follows: 43 rabbits were caught at exactly 1 night, 16
rabbits at 2 nights, 8 at 3 nights, 6 at four nights, 2 at 6 nights and 1 rabbit was caught at 7 nights. In
other words, we have observations from $X_1, · · · X_m$ count variables of m = 76 different, caught rabbits.
So, in this sample, 43 of the $x_1, · · · , x_m$ were ones, 16 twos, etc. Every count can take a maximum of
T = 18 captures. The number of of zero counts, i.e. the number of rabbits that were not caught, is
unobserved. We denote this additional sample as $X_{m+1}, · · · , X_n$. Assuming independence of trapping
occasions and homogeneity of capture probability θ at each occasion each $X_i$ would follow a binomial distribution. We assume here that a Poisson approximation is justified. That is:



$P(X_i = x) = frac{exp(−θT)(θt)^x}{x!}$ where i = 1, · · · , n.



Note that the observed sample is zero-truncated so that the observed sample can be considered as arising from the zero-truncated Poisson density:



$$exp(−θT)(θT)^x over (1 − exp(−θT))x!$$ for $i = 1, · · · , m$, $;θ ∈ (0, 1)$ and $x ∈ {0, 1, · · · , T}$.



Determine the log-likelihood function for the observed sample.



My solution:



I have already attempted this and got:
$sum_{i=1}^m n_ilogfrac{exp(−θT)(θT)^x}{x!}frac{1}{1 − exp(−θT)}$



Is this correct? If not, what should I have got? What have I done wrong?










share|cite|improve this question













Question:



Edwards and Eberhardt (1967) conducted a live-trapping study on a confined population of known size. In their study, wild cottontail
rabbits were penned in a 4-acre rabbit-proof enclosure. Live trapping was conducted for 18 consecutive
nights. Recorded capture frequencies were as follows: 43 rabbits were caught at exactly 1 night, 16
rabbits at 2 nights, 8 at 3 nights, 6 at four nights, 2 at 6 nights and 1 rabbit was caught at 7 nights. In
other words, we have observations from $X_1, · · · X_m$ count variables of m = 76 different, caught rabbits.
So, in this sample, 43 of the $x_1, · · · , x_m$ were ones, 16 twos, etc. Every count can take a maximum of
T = 18 captures. The number of of zero counts, i.e. the number of rabbits that were not caught, is
unobserved. We denote this additional sample as $X_{m+1}, · · · , X_n$. Assuming independence of trapping
occasions and homogeneity of capture probability θ at each occasion each $X_i$ would follow a binomial distribution. We assume here that a Poisson approximation is justified. That is:



$P(X_i = x) = frac{exp(−θT)(θt)^x}{x!}$ where i = 1, · · · , n.



Note that the observed sample is zero-truncated so that the observed sample can be considered as arising from the zero-truncated Poisson density:



$$exp(−θT)(θT)^x over (1 − exp(−θT))x!$$ for $i = 1, · · · , m$, $;θ ∈ (0, 1)$ and $x ∈ {0, 1, · · · , T}$.



Determine the log-likelihood function for the observed sample.



My solution:



I have already attempted this and got:
$sum_{i=1}^m n_ilogfrac{exp(−θT)(θT)^x}{x!}frac{1}{1 − exp(−θT)}$



Is this correct? If not, what should I have got? What have I done wrong?







poisson-distribution log-likelihood






share|cite|improve this question













share|cite|improve this question











share|cite|improve this question




share|cite|improve this question










asked Nov 21 at 22:34









Vicky

597




597












  • Someone's been doing the Dankmar's coursework here :P I think the context is not relevant anyway, you can just ask for the log-likelihood function of a zero-truncated Poisson distribution and its first and second order derivative
    – Euler_Salter
    Nov 21 at 22:42












  • @Euler_Salter haha yes! I thought context was good. Does it look right to you?
    – Vicky
    Nov 21 at 22:49










  • Yes but it could scare off lazy fellow stackexchangers, so it's nice to keep it short! Not sure now, I'm a bit tired, but I just found this: math.stackexchange.com/a/1857529/348937
    – Euler_Salter
    Nov 21 at 22:51










  • @Euler_Salter thanks! Will take a look.
    – Vicky
    Nov 21 at 22:53


















  • Someone's been doing the Dankmar's coursework here :P I think the context is not relevant anyway, you can just ask for the log-likelihood function of a zero-truncated Poisson distribution and its first and second order derivative
    – Euler_Salter
    Nov 21 at 22:42












  • @Euler_Salter haha yes! I thought context was good. Does it look right to you?
    – Vicky
    Nov 21 at 22:49










  • Yes but it could scare off lazy fellow stackexchangers, so it's nice to keep it short! Not sure now, I'm a bit tired, but I just found this: math.stackexchange.com/a/1857529/348937
    – Euler_Salter
    Nov 21 at 22:51










  • @Euler_Salter thanks! Will take a look.
    – Vicky
    Nov 21 at 22:53
















Someone's been doing the Dankmar's coursework here :P I think the context is not relevant anyway, you can just ask for the log-likelihood function of a zero-truncated Poisson distribution and its first and second order derivative
– Euler_Salter
Nov 21 at 22:42






Someone's been doing the Dankmar's coursework here :P I think the context is not relevant anyway, you can just ask for the log-likelihood function of a zero-truncated Poisson distribution and its first and second order derivative
– Euler_Salter
Nov 21 at 22:42














@Euler_Salter haha yes! I thought context was good. Does it look right to you?
– Vicky
Nov 21 at 22:49




@Euler_Salter haha yes! I thought context was good. Does it look right to you?
– Vicky
Nov 21 at 22:49












Yes but it could scare off lazy fellow stackexchangers, so it's nice to keep it short! Not sure now, I'm a bit tired, but I just found this: math.stackexchange.com/a/1857529/348937
– Euler_Salter
Nov 21 at 22:51




Yes but it could scare off lazy fellow stackexchangers, so it's nice to keep it short! Not sure now, I'm a bit tired, but I just found this: math.stackexchange.com/a/1857529/348937
– Euler_Salter
Nov 21 at 22:51












@Euler_Salter thanks! Will take a look.
– Vicky
Nov 21 at 22:53




@Euler_Salter thanks! Will take a look.
– Vicky
Nov 21 at 22:53















active

oldest

votes











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',
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
});


}
});














 

draft saved


draft discarded


















StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fmath.stackexchange.com%2fquestions%2f3008478%2flog-likelihood-of-zero-truncated-poisson%23new-answer', 'question_page');
}
);

Post as a guest















Required, but never shown






























active

oldest

votes













active

oldest

votes









active

oldest

votes






active

oldest

votes
















 

draft saved


draft discarded



















































 


draft saved


draft discarded














StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fmath.stackexchange.com%2fquestions%2f3008478%2flog-likelihood-of-zero-truncated-poisson%23new-answer', 'question_page');
}
);

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







Popular posts from this blog

Berounka

Sphinx de Gizeh

Different font size/position of beamer's navigation symbols template's content depending on regular/plain...