DAND: Udacity’s Data Analyst Nanodegree – Review of Project 1

As mentioned in my previous post I have started following the classes and projects to complete the Data Analyst Nanodegree (DAND) by Udacity. And I have great news! I have just submitted my first project.

The first project is part of the trial week received upon registration; it was labeled P0 and does not count towards the DAND. P0’s aim was to use the data provided and identify the optimal length of chopsticks for an adult. This includes identifying the dependent and independent variables, plotting the data and making observations on it. Very basic exercises which serve as a warm-up and to get acquainted with the platform. Project 0 is optional of course and can easily be completed in the first trial week which is free of charge.

Moving on to the meat of the material and project 1, the student is introduced to statistics: measures of central tendency (or simply mean, mode, median), measures of variance (variance and standard deviation), normal distributions, z-statistics, t-statistics, hypothesis testing. Although I have done stats before, I found this to be a great refresher and, without taking any notes, I feel I have a much deeper understanding of the topics. It is actually the first time I have truly absorbed the differences between z and t statistics.

One of the reasons for this, as well as the main reason for choosing Udacity’s course, is that the UI and, as a result, the learning experience gives you the feel of being tutored to. Videos are the tutor’s writings on an interactive board. Each video is very short and at the end there is a short quiz which feels like the video is paused and you write or choose the answer from the options which were just previously written for you. None of these are graded as only the completion of projects counts towards the nanodegree. This is perfect for me as there is no pressure to complete anything that you already know or feel is too simple or even if you are stuck.

What I also loved about Udacity is that not only are the courses presented in a great manner but that I do not even have to take them. You can take zero courses and complete the projects and you will “graduate”. Furthermore, you can pause the subscription at any point and then restart it when you wish. So if you are going on holiday or have lots of “real” work then you can pause and resume classes at a later date (you are given the option to pause for 7, 14 or 30 days).

Look below for a screenshot from the Udacity blog which is a video you will see while taking classes. The instructor will go through a concept and then the video is paused and you select an answer, submit it, and the video resumes.

Screen-Shot-2013-05-16-at-6.16.04-PM

 

The first project “Testing a perceptual phenomenon” provides data from a Stroop effect experiment and asks you to report several descriptive statistics, identify the independent and dependent variable, identify what test to use and create a hypothesis test and finally draw conclusions. It was nothing fancy as all you needed was a spreadsheet to complete this project but it does make you think and you need to know the material in order to be able to answer it. Submission is done via the website and a response with a review of the project will come to your email with a link to comments on each of your answers. Again this adds to the personal feel.

P0 and P1 done, another seven to go!

Michael Lazarou
Michael Lazarou

Michael Lazarou manages revenue assurance and fraud at Epic, a Cypriot telco, having joined their RA function in March 2011. His background includes a double major in Computer Science and Economics, as well as an MBA. Before being lured into the exciting world of telecoms he worked as a software developer.

Michael is interested to gain a better understanding of different aspects of RA and data analysis. He shares his insights on training courses he participates in with Commsrisk.

Related Articles

Get Our Weekly Newsletter by Email