Joy & peril of data analysis

(This post was meant to be written last month when I finally finished my data analysis but somehow other things caught up and I forgot about it. This forgetfulness has become quite common in my studious life lately. When the mind is filled with all kind of thoughts, I tend to forget many other things. Anyway, keep writing is good. It keeps my mind refresh and active. Hence, I’m writing this blog post today.)

I was pretty excited when I started to see survey responses flowing in during the very first week of data collection. I was rather anxious to get them analyzed then and see if the data proved to be significant in my research. Thanks to many Twitter friends, my own peers and some blog  readers, I reached my target number of responses before the month ended. Really appreciate their time and effort in helping me.

By the time I prepared my first presentation, I have collected 69 responses (not many to some but it’s adequate to be my first time – my supervisor only suggested 60). I spent hours or rather weeks (few hours a day due to work commitment) in putting the data together in nice tables and graphs. Some sections where choices are given more than one, the data table is growing too horizontally big to fit in the page, so I have to rethink a few options to represent them better. I was rather new in data analysis and I was quite silly in doing all the calculation manually. Don’t laugh! I wanted to spank myself. Being an IT geek yet I was doing it manually. Thinking my data size was not so big, it was possible but tedious and error-prone. After the presentation, I continued to collect data and the data grew to 80 responses. Doing it manually started to killing me. Checking error alone wasted my time. No other choice but to learn how to use Excel formula. It didn’t work wonder just like that though. The data needed to be arranged accordingly in order for the formula to work. At the end, everything worked fine despite it took me quite long to get everything in order.

The more I think of this, the more I feel silly. Anyway, this is part of my learning process after all. Putting numbers after numbers in tables, thinking the best way to represent them nicely so that people (or even myself) can understand and finally trying to write analysis about them are no easy task. That’s the peril part, I guess. The joy of data analysis for a researcher (I try to think of myself as one) is to find out good information from the respondents. These information are either proof of the research hypotheses or some new insights that are interesting to find out. I did find out a lot of new insights from my data analysis and they gave me good building blocks for my system development. However, whether if the system or solution will be successful is another story for another day.


Leave a Reply

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

You are commenting using your 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