• Learn before you hack
• Make it pretty
• Document everything

These three hints apply to lots of life’s endeavors,
but let’s talk about how they apply to Excel.

Learn before you hack

Excel is built so anyone can use it. Work-arounds do exist, which makes it tempting to hack and kludge your way to inelegant solutions. Avoid this!

Learn keyboard shortcuts. My Tao of shortcuts applies here, too. Invest in getting lightning-fast with keyboard shortcuts. Yes, you can point and click, but in the end all that clicking will take hours out of your life! (also on that note… go ahead and stop hiding from Excel 2007!)

Learn pivot tables. Pivot tables are the most valuable tool in Excel. If you can’t use them, you’re missing out. I won’t explain them in this post because many others already have, but learn them one way or another. Pivot tables let you perform cuts, filters, and sums on huge amounts of data with speed and grace. It’s the best way to get familiar with a dataset and do many analyses.

Learn functions. You know it’s time to learn a new function when you find yourself struggling to link lots of “if” statements together or manually re-typing data to get the format right. A function probably exits to solve your exact problem. Use Google, built-in help, or your friends to find the answer, but DO NOT do things the slow, hacky way. The elegant solution will solve the problem better and save you hours down the road when you have to do the same thing again!

Make it pretty

Spending time on the aesthetics has several benefits. Pretty Excel models inspire confidence in clients and coworkers and are easier to use and build.

Understand the ins and outs. Take time to identify key inputs and outputs. Ensure these are easy to find when you lay out the model. Next, list other inputs and outputs and sketch a plan for linking the two before starting. A planned model looks cleaner than an haphazard one and is easier to build!

Organize your tabs. Keep inputs, outputs, and data on separate tabs to help people find what they’re looking for. Also try organizing tabs into groups and color-coding them to reinforce the structure.

Use consistent colors. Settle on a single, non-hideous color scheme. This makes models easy to read and nice to look at! Plan the colors you’ll use in advance and stick to your plan.

Document everything

An elegant, beautiful model is no good if people can’t use it. Plus, you’ll never know your model as well as the day you build it. For those reasons, document! Your boss will think you’re a superhero, and you’ll significantly reduce the number of emails asking for explanations!

Summarize and give instruction. There should be two tabs at the beginning of any Excel model. One summarizes what it’s for, why it was built, when, and by whom. The other gives instructions on key inputs and outputs, what users can change, and what they should leave alone.

Record your assumptions. Let me say that again… Record your assumptions! It’s a shame this is last on the list because it’s the most important. If you make an assumption, DOCUMENT IT. Every sheet with calculations or inputs should have an “assumptions” column. Total stranger should be able to explain your model… This helps catch mistakes, gets your thinking crystal clear, and gives you bulletproof answers to the age-old question “what’s happening in this cell?”

Epilogue

If you commit to making elegant, beautiful, well-document models, you’ll be ahead of most… Of course, there are countless other best practices I didn’t mention. What are yours?

• Part 1: Branding Yourself and Making Making a “Wow” Resume
• Part 2: Preparing for Your Case Interview to Get Bulletproof
• Part 3: Talking about Your Experience and Sounding like a Bad-ass

Leaving academia and joining consulting firms is a something many PhD students (myself included) are getting interested in. Firms like McKinsey & Company, Boston Consulting Group (BCG), and Bain & Associates once hired mostly MBAs but are now branching out to hire MDs, lawyers, and PhDs.

I wanted to make a big impact with the skill I learned during my PhD. I got excited when I heard about consulting because it promises just that. In the next three parts, I’ll take you through the big lessons I learned while preparing and interviewing: How to get an interview, how to nail the case, and how to dazzle them with your experience.

Part 1: Branding Yourself and Making Making a “Wow” Resume gives you pointers to polish that scruffy science look off your C.V. and generally control your “personal brand” so that interviewers are impressed with you long before you walk in the door.

Part 2: Preparing for Your Case Interview to Get Bulletproof talks about how to approach the case and how to practice so that you can shine while others look dull. I’ll give you some simple exercises that will improve the structure and creativity of the “case” portion of your interview.

Part 3: Talking about Your Experience and Sounding like a Bad-ass covers an important and often overlooked portion of a consulting interview… talking about yourself! I know you have some amazing stories to tell. This sections shows how to make your stories say the right things about you.

Please enjoy!

Disclaimer: I recently went through the application and interview process with a top firm, came out with an offer, and signed it! In this series, I share my experience and give some ideas for people on a similar path. However, at the time of writing (July 2009), I do not have any inside information on how any company conducts their hiring. These are just my thoughts!

Fast Level Sets Demo

The links below point to the technical report and a demo written in C++/MEX that can be run directly in MATLAB. The demo implements the Chan-Vese segmentation energy, but many energies can be minimized using the provided framework.

Sparse Field Method – Technical Report [pdf]
Sparse Field Method – Matlab Demo [zip]

To run the MATLAB demo, simply unzip the file and run:
>>sfm_chanvese_demo
at the command line. On the first run, this will compile the MEX code on your machine and then run the demo. If the MEX compile fails, please check your MEX setup. The demo is for a 2D image, but the codes work for 3D images as well.

My hope is that other researchers wishing to quickly implement Whitaker’s method can use this information to easily understand the intricacies of the algorithm which, in my opinion, were not presented clearly in Whitaker’s original paper. Personally, these codes have SUBSTANTIALLY sped up my segmentations, and are allowing me to make much faster progress towards completing my PhD!

Thanks to Ernst Schwartz and Andy for helping to find small bugs in the codes and documentation. (they’re fixed now!)

For more information regarding active contour, segmentation, and computer vision, check here: Computer Vision Posts

Here is a download-able Matlab demo, which should work on any pre-aligned stereo image pairs:

stereo_modefilt.zip

The entire code is written in Matlab/C++/MEX. The stereo matching is all in Matlab, and the selective mode filter is coded in C++ and callable from Matlab (meaning it must be compiled before it can run). Currently, the correspondence is the major bottleneck, so anyone who can improve this, please let me know! Enjoy.