Must read:Is there a real future in data analysis for self-learners without a math degree?

# 4 Months into Data Analysis: let’s get real!

After filling the statistics gap and getting familiar with R over the past four months, it is now time to set a SMART goal. First, let us have a short look back on our learning experience as Not an Engineer before defining the ultimate goal of our journey, which strangely resembles a hiking tour in the mountains.

### The discovery phase: the promises of data analysis

From down in the valley, you catch sight of the summit. You are full of energy and in admiration of what lies ahead of you. Then, you start your tour, walking through the forest, thinking about how great hiking is and wondering why you have not done it more often in the past. You already reflect on which other mountain areas to discover next. This is how the journey starts, the discovery phase.

During my first steps with R – scraping, cleaning and exploring data – I became aware of the great power of data analysis. “If only I knew how to process data in such speed and scale back when I was a communications consultant, I could have provided insights much faster.” What I painfully achieved, or tried to build, with Excel and slow if-loops in VBA or PHP, I could now accomplish with the right R package and included functions in no time.

### On your way up: the power of statistics

A few hours into climbing the steep hiking path, your thoughts are swept away by the physical experience. You get a real, and more realistic sense of climbing in the mountains.

After fooling around with R, I had to make up for my gap in statistics. Back to the good old learning techniques, books, flashcards and exercises. Unless you feel a natural attraction towards statistics and alike, this is where I needed the most discipline and motivation. The more I made headway, the more I understood that I had been merely scratching at the surface of R’s immense potential. In order to make good use of it, you need to understand at least the basic principles of inferential statistics, regression and machine learning.

### Half-way up: losing sight of the summit

Under increasingly rude weather conditions, you keep climbing. There is less conversation among hikers and, instead of admiring the landscape around you, you focus increasingly on the way itself. Somewhere between the valley floor and the mountain top, you have lost sight of the summit.

A few months into following statistics classes, my memories of the first, almost childlike moments with data analysis simply faded away. I started to feel the lack of a clear-set goal. So, I started randomly screening job offers for “data analysts” and “data scientists“.

I came across essentially two profile types hired by companies today, described in slightly hyperbolical terms as follows:

• The math-degree, post-doc data genius
• The data clerk, “unafraid of using Excel”

Neither one nor the other matched my skills and ambitions. How many more statistical concepts and methods would I have to learn to live up to standards of true data science? Unless I enrolled into a one- or two-year Master’s programme, I would never reach the level of understanding of a data scientist recognized as such in the professional sphere, right?

As for the “fake data analyst”, why settle for data operations clearly below the level of my coding skills, while disregarding my relational and communications skills, team and project management experience, not to mention diverse linguistic proficiency? I had to think it all over again.

### Setting out for the top: applied data analytics

Back to our mountain hike: you are exhausted, unsure of reaching the summit after all. You need a break. Chewing on your sandwich and reminiscing over your journey, you wonder about what brought you here in the first place. Thinking for yourself then chatting with your fellow hikers, this is when you find courage again to set out for the top.

At one point, I started to rush through my video lectures and homework, as if I was more interested in finishing the course than the subject matter itself. This could not be.

The practical aspects of the data science and the Statistics specializations on Coursera always cheered me up and gave me courage to pursue the learning process. So, I went back to playing around with data just for fun.

And this is where it all started to make sense again. My initial aim was primarily to move out of the danger zone (located between “substantive expertise” and “hacking skills” on the Conway venn diagram below) towards actual data science, combining the coding, statistics and a specific field of expertise.

Now, the next big goal is to apply the acquired analytical skills in my field of expertise: public relations. This includes the digital fields of communications such as social media management and SEO. Will there be a need for advanced data analysis? We might see it better from the top of the mountain.