Take the 2-minute tour ×
Mathematics Stack Exchange is a question and answer site for people studying math at any level and professionals in related fields. It's 100% free, no registration required.

I am fitting a model's parameters to grouped data by maximizing the likelihood equation:

$L(\theta)=N!\prod_{i=1}^{G}\frac{p_i(\theta)^{n_i}}{n_i!}$

$\theta$ is the vector of parameters. $n_i$ is the number of observations in group i. That is, $n_i=x_i-x_{i-1}$ where $x_i$ is an individual observation. $N$ is the total number of observations ($N=\sum_{i}n_i$). $G$ is the number of groups.

And $p_i(\theta)=F(x_i;\theta)-F(x_{i-1};\theta)$, where $F(x_i;\theta)$ is the distribution function I am trying to fit to the data.

My problem is that the observations are normalized (they are percentiles). So $0<n_i<1$, when I need integers for the factorials. Multiplying $N$ and $n_i$ by 100 and rounding allows me to run the equation in matlab, but then I am not sure what to do with the output in order to convert it back to 1/100 scale. Appreciate some advice. Thanks.

share|improve this question
add comment

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Browse other questions tagged or ask your own question.