Interview Question: Do You Know Your ML?

Sample Question #133 (statistics)

Given a sample of N observations: X1, X2, …, XN, please write out its likelihood function.

(Comment: a really good question that tests your understanding of one of the basic concepts in statistical estimations)

Advertisements
This entry was posted in Sample Qs. Bookmark the permalink.

One Response to Interview Question: Do You Know Your ML?

  1. Brett says:

    ANSWER
     
    I really like this question. Many students only memorize how to form an MLE, but neglect to understand what this "likelihood function" is to begin with.
     
    A likelihood function simply relates the parameters of the distribution, given the observations, to the theoretical density function of the population from which the observations were supposedly drawn.
     
    For the data sample in the question, the likelihood function, in its general form, is:
     
      L(a_1, …, a_k | X_1, …, X_N) proportional to f(X_1, …, X_N | a_1, …, a_k),
     
    where the a_i’s are the k parameters of the model. Usually we can set the two sides to equal to each other. If we add the additional assumptions that the X’s are independent observations, the right-hand side becomes a product of the individual cdf’s evaulated at each X value.  MLE then proceeds by maximizing this product.
     

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s