<p>both at starting and mid-career averages.</p>
<p>Top</a> US Colleges ? Graduate Salary Statistics</p>
<p>Now many will say "hey this is skewed because a lot of engineers from VT get high starting salaries." I retort by saying we have A LOT of majors of equal numbers that could skew the stats down. Not that it's a big deal, I am just saying college rankings aren't everything. Think of the network you get from being a VPI alum.</p>
<p>Oh dear if GPBurdell saw this one he’d flip out.</p>
<p>Anyway, I’m not huge on self-reported statistics and we DO have a much higher percentage of engineers than UVA. I wonder how hey counted people who did undergrad somewhere and then grad school.</p>
<p>Also:
[Hokies</a> earn more than Wahoos | Richmond BizSense](<a href=“http://www.richmondbizsense.com/2009/07/23/hokies-edge-wahoos-in-graduates’-starting-salaries/]Hokies”>http://www.richmondbizsense.com/2009/07/23/hokies-edge-wahoos-in-graduates’-starting-salaries/)</p>
<p>Thanks for the article guillaume. However, this article and the original one on payscale.com would hold a lot more weight and credibility if they had divulged the size of the sample group. I mean, I looked at the link to the methodology and I couldn’t find it anywhere. They could have called or received surveys from say 3 people at each school? Friends and family members they knew? If you are going to print/publish something like this, at least give it a chance to be a little credible!</p>
<p>They do say somewhere (can’t remember where and don’t have it in front of me) that the margin of error for the total survey is 5 points and for the Ivy league survey it’s 10 points.</p>
<p>In the famous words of my children…“my bad” 
I did go back and look again. (but I still would like to know how many were surveyed) This is from the [PayScale</a> - Salary Comparison, Salary Survey, Wages](<a href=“http://www.payscale.com%5DPayScale”>http://www.payscale.com) site under methodology:</p>
<p>90% Confidence Interval on the Median: For all schools, the confidence interval is +/-5%, with the following exceptions:</p>
<p>•Due to large variation in the pay of graduates from elite schools (Ivy Leagues, Stanford, Caltech, etc.) the 90% confidence interval is +/-10%.
•Due to smaller data sets, the 90% confidence interval for small liberal arts schools is also +/-10%.</p>