Questions tagged [multinomial-distribution]

A multivariate, discrete probability distribution used to describe the results of a random experiment where each of $n$ outcomes are placed into one of $k$ nominal categories.

Overview

The multinomial distribution is a discrete probability distribution used to describe the results of a random experiment where each of $n$ outcomes are placed into one of $k$ nominal categories. It can be thought of as the generalization of the binomial distribution. The binomial distribution is a special case of the multinomial distribution where there are only $k=2$ categories.

The probability mass function (pmf) of the distribution is parametrized by $p_i$, the probabilities of $x_i$ ($i=1,2,\ldots k$) outcomes being placed in the $i^\text{th}$ category. The pmf $P(x_i,n;p_i)$ has the following form:

$$ \left\{ \begin{array}{l l} \frac{n!}{x_1!x_2!\ldots x_n!} p_1^{x_1} p_2^{x_2} \ldots p_n^{x_n} & \quad \text{if $\sum_{n=1}^k x_i =n$ }\\ ~ \\ ~ \\ 0 & \quad \text{otherwise} \end{array} \right. $$

755 questions
53
votes
4 answers

Multinomial logistic regression vs one-vs-rest binary logistic regression

Lets say we have a dependent variable $Y$ with few categories and set of independent variables. What are the advantages of multinomial logistic regression over set of binary logistic regressions (i.e. one-vs-rest scheme)? By set of binary logistic…
Tomek Tarczynski
  • 3,854
  • 7
  • 29
  • 37
33
votes
3 answers

How to do logistic regression in R when outcome is fractional (a ratio of two counts)?

I'm reviewing a paper which has the following biological experiment. A device is used to expose cells to varying amounts of fluid shear stress. As greater shear stress is applied to the cells, more of them start to detach from the substrate. At each…
thecity2
  • 1,485
  • 2
  • 15
  • 22
29
votes
1 answer

Can a Multinomial(1/n, ..., 1/n) be characterized as a discretized Dirichlet(1, .., 1)?

So this question is slightly messy, but I'll include colourful graphs to make up for that! First the Background then the Question(s). Background Say you have a $n$-dimensional multinomial distribution with equal probailites over the $n$ categories.…
28
votes
5 answers

Getting p-values for "multinom" in R (nnet package)

How do I get p-values using the multinom function of nnet package in R? I have a dataset which consists of “Pathology scores” (Absent, Mild, Severe) as outcome variable, and two main effects: Age (two factors: twenty / thirty days) and Treatment…
Luciano
  • 587
  • 2
  • 7
  • 12
27
votes
3 answers

How can I calculate margin of error in a NPS (Net Promoter Score) result?

I'll let Wikipedia explain how NPS is calculated: The Net Promoter Score is obtained by asking customers a single question on a 0 to 10 rating scale, where 10 is "extremely likely" and 0 is "not at all likely": "How likely is it that you would…
24
votes
3 answers

How to set up and estimate a multinomial logit model in R?

I ran a multinomial logit model in JMP and got back results which included the AIC as well chi-squared p-values for each parameter estimate. The model has one categorical outcome and 7 categorical explanatory vars. I then fit what I thought would…
paul
  • 1,342
  • 3
  • 11
  • 16
20
votes
4 answers

Interpreting exp(B) in multinomial logistic regression

This is somewhat of a beginner's question, but how does one interpret an exp(B) result of 6.012 in a multinomial logistic regression model? 1) is it 6.012-1.0 = 5.012 = 5012% increase in risk? or 2) 6.012/(1+6.012) = 0.857 = 85.7% increase in…
user6911
  • 201
  • 1
  • 3
  • 3
17
votes
1 answer

What are some distributions over the probability simplex?

Let $\Delta_{K}$ be the probability simplex of dimension $K-1$, i.e. $x \in \Delta_{K}$ is such that $x_i \ge 0$ and $\sum_i x_i = 1$. What distributions which are frequently (or well-known, or defined in the past) over $\Delta_{K}$ exist? Clearly,…
17
votes
2 answers

Linear combination of two dependent multivariate normal random variables

Suppose we have two vectors of random variables, both are normal, i.e., $X \sim N(\mu_X, \Sigma_X)$ and $Y \sim N(\mu_Y, \Sigma_Y)$. We are interested in the distribution of their linear combination $Z = A X + B Y + C$, where $A$ and $B$ are…
Ivan
  • 458
  • 1
  • 4
  • 17
16
votes
2 answers

What is the normal approximation of the multinomial distribution?

If there are multiple possible approximations, I'm looking for the most basic one.
15
votes
3 answers

Why does nobody use the Bayesian multinomial Naive Bayes classifier?

So in (unsupervised) text modeling, Latent Dirichlet Allocation (LDA) is a Bayesian version of Probabilistic Latent Semantic Analysis (PLSA). Essentially, LDA = PLSA + Dirichlet prior over its parameters. My understanding is that LDA is now the…
15
votes
3 answers

Multinomial-Dirichlet model with hyperprior distribution on the concentration parameters

I will try to describe the problem at hand as general as possible. I am modeling observations as a categorical distribution with a parameter probability vector theta. Then, I assume the parameter vector theta follows a Dirichlet prior distribution…
15
votes
2 answers

Expected number of times to roll a die until each side has appeared 3 times

What is the expected number of times you must roll a die until each side has appeared 3 times? This question was asked in primary school in New Zealand and it was solved using simulations. What is the analytical solution for this problem?
14
votes
1 answer

Cost functions for contextual bandits

I'm using vowpal wabbit to solve a contextual-bandit problem. I'm showing ads to users, and I have a fair bit of information about the context in which the ad is shown (e.g. who the user is, what site they're on, etc.). This seems to be a pretty…
14
votes
2 answers

glmnet: How to make sense of multinomial parameterization?

Following problem: I want to predict a categorical response variable with one (or more) categorical variables using glmnet(). However, I cannot make sense of the output glmnet gives me. Ok, first let's generate two related categorical…
jmb
  • 645
  • 1
  • 5
  • 13
1
2 3
50 51