Hi! I'm a senior student going to apply for graduate school in operations research. My major in undergraduate school is statistics. While writing my statement of purpose, I think that I have to say something about the relationship between operations research and statistics and then state why I'm qualified for this program. So I have to state my research and courses in a way that have relation to operations research.

Bt the way, I'm a Chinese. I'm sorry if there are some mistakes in my expression. Thanks~

asked 22 Nov '13, 21:44

xuranw's gravatar image

xuranw
111
accept rate: 0%


I'm chinese, and applying to graduate programs in OR too! your writing's fine! (:

Not that I want to be a prick -- but it smells more like a homework question: "help me write the connection between operations research (OR) and stats for me to paste (with modifications) into my Statement of Purpose (SoP), so that I can move on to talk about myself". In practice, the aspect of OR that interests you will help guide/hint at the ways in which your background statistics comes in handy. Being more specific in your queries - eg.

I'd taken classes in sampling methods - MCMC/SIR/whatever, and was fascinated by applications of it in stochastic optimization in [insert paper name]. Were there other instances in which you saw important sampling methods being applied in nonobvious ways?"

or

I've seen algorithms [1] that utilises optimisation routines as a mechanism for statistical inference, and was curious if there are instances where the converse was true: when statistical inferences were essential to optimization?

Edit: I just stumbled across the paper "Statistical Inference of stochastic optimization problems" by xxx, however, I lack a background in yyy, and the math was a little dense for me. Is there a manner of explaining it for an audience with a background in mathematical statistics at the level of [insert textbook], without a background in yyy? [2]

It doesn't even need to be about optimization (I was mainly drawing from my own interests in framing this answer) It could be about process monitoring/control-charting, reliability/quality engineering, queuing theory, project management, or anything that strikes your fancy. Nor does it have to be this deep/technical - but it has to hint at some quality of 'earnestness', of having done your 'due diligence'.

Have you thought about what it was about OR that interests you? Have you looked at past/recent work done by the departments/faculty you're applying to? It might not only help (i) frame a more fruitful discussion here, but also (ii) improve the way you write your SoP. All the best with your applications!

[1]: ranging from the "very simple" gradient descent, or Nelder-Mead for the laplacian approximation to a posterior density in Bayesian statistics, to fairly complex schemes such as dual decomposition for MAP inference in markov random fields.

[2]: Or you could ask: are there (i) other equally motivating examples, (ii) applications of this approach to an industrial problem, or (iii) extensions of this work using other approximation schemes that demonstrated better convergence/worked-better in practice?

link

answered 23 Nov '13, 00:04

yeesian's gravatar image

yeesian
846210
accept rate: 3%

edited 23 Nov '13, 00:11

Your answer
toggle preview

Follow this question

By Email:

Once you sign in you will be able to subscribe for any updates here

By RSS:

Answers

Answers and Comments

Markdown Basics

  • *italic* or _italic_
  • **bold** or __bold__
  • link:[text](http://url.com/ "Title")
  • image?![alt text](/path/img.jpg "Title")
  • numbered list: 1. Foo 2. Bar
  • to add a line break simply add two spaces to where you would like the new line to be.
  • basic HTML tags are also supported

Tags:

×8
×1

Asked: 22 Nov '13, 21:44

Seen: 5,675 times

Last updated: 23 Nov '13, 00:11

OR-Exchange! Your site for questions, answers, and announcements about operations research.