Testing Methodology I.a- Google vs. Yahoo! revisited

After their original post, there was apparently some controversy about the methodology Matthew Chenay & Mike Perry used to compare the relative index sizes of Google & Yahoo! (original article at http://vburton.ncsa.uiuc.edu/indexsize.html, update at http://vburton.ncsa.uiuc.edu/indexsizepage.html.)

After some modification of their search algorithm, they came to a similar conclusion: Google DOES have a bigger index than Yahoo! Previously, the difference was almost 3-to-1 (37.4%), but now it’s more like 3-to-2 (65%). Still, that’s pretty significant when Yahoo! is claiming their index is twice as big as Google’s!

Another interesting fact is neither search engine had an actual total number of results that was anywhere near the estimated total number of results. Even including duplicate results, Google’s actual return was only about 54.5% of the estimated total, while Yahoo!’s actual return was only about 22.6% of the estimated total. If you take out the duplicate results, the discrepancy between actual and estimated is even worse!

Leave a Reply

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

WordPress.com Logo

You are commenting using your WordPress.com 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