Monday, September 5, 2011

the sock experiment: ranking system

For good measure, I am posting my ranking system for the sock experiment. With the exception of the variables and weighting schema, this is identical to the ranking system used for the cereal experiment

I realize that some of you may, at some point, want to participate in an experiment of your own and would weight variables differently than I have here. If this is the case, I am more than happy to share my spreadsheet with you (pending you keep me posted on your results!), which calculates these ranks, so you can play around with your own personal preferences. If anyone is interested, just comment or e-mail: Now, go get your nerd on.


Each variable (e.g., overall feel, price) was standardized to that variable's mean by calculating Z-scores (i.e., a common metric with a mean of 0 and a standard deviation of 1). In this way, the Z-scores are relative to the socks in the experiment, not to an absolute standard. To do this, an average and standard deviation was then calculated for each variable. The Z-score was calculated as follows:

Z = (variable value) - (average of variable values for all socks) /
(standard deviation of variable values for all socks)

I assumed a higher Z-score indicated 'worse' sock characteristics. Those variables that didn't follow this trend (i.e., where higher values indicated 'better' characteristics) (i.e., overall feel, cushion, moisture) were reverse coded by multiplying their Z-score by negative one (-1). 


Each Z-score was then multiplied by its appropriate weight as determined, albeit subjectively, below (adding up to 100%). I emphasized price in this weighting scheme. As you may suspect, results change drastically when other variables are emphasized based on personal preference.

Overall feel (1-5): 25%
Feet temperature (cool, normal, hot): 6.25%
Cushion (poor, average, good): 6.25%
Moisture (poor, average, good): 6.25%
Blistering (none, moderate, a lot): 6.25%
Price: 50%

Composite Score and Ranking.

All of the weighted Z-scores were then summed to create a weighted composite score for each sock. The composite scores were sorted by value, with the lowest composite score indicating the best sock. Based on this sorted list, each sock was assigned a rank.

You can see the current table with these ranks on my experiment page.

No comments:

Post a Comment