<p>Average salary $45,425. </p>
<p>pretty sure that they don't include graduate students in their salary average. That's actually a very good salary considering the amount of humanities majors at Harvard.</p>
<p>
</p>
<p>I wonder if the usual objection noted in my FAQ about voluntary response surveys applies here: </p>
<p>VOLUNTARY RESPONSE POLLS </p>
<p>One professor of statistics, who is a co-author of a highly regarded AP statistics textbook, has tried to popularize the phrase that "voluntary response data are worthless" to go along with the phrase "correlation does not imply causation." Other statistics teachers are gradually picking up this phrase.</p>
<p>
<p>-----Original Message----- From: Paul Velleman [<a href="mailto:SMTPfv2@cornell.edu">SMTPfv2@cornell.edu</a>] Sent: Wednesday, January 14, 1998 5:10 PM To: <a href="mailto:apstat-l@etc.bc.ca">apstat-l@etc.bc.ca</a>; Kim Robinson Cc: <a href="mailto:mmbalach@mtu.edu">mmbalach@mtu.edu</a> Subject: Re: qualtiative study</p>
<p>Sorry Kim, but it just aint so. Voluntary response data are <em>worthless</em>. One excellent example is the books by Shere Hite. She collected many responses from biased lists with voluntary response and drew conclusions that are roundly contradicted by all responsible studies. She claimed to be doing only qualitative work, but what she got was just plain garbage. Another famous example is the Literary Digest "poll". All you learn from voluntary response is what is said by those who choose to respond. Unless the respondents are a substantially large fraction of the population, they are very likely to be a biased -- possibly a very biased -- subset. Anecdotes tell you nothing at all about the state of the world. They can't be "used only as a description" because they describe nothing but themselves.
</p>
<p>Math</a> Forum Discussions</p>
<p>in conducting surveys/polls and so on, the key to the reliability include at least a few important elements; 1) respondents must truly represent the universe. 2) respondents must be systematically selected at random i.e. that is all are given equal chance/probability of being selected and included in the survey. 3) the methodology/questionnaire so on and so forth must be scientifically done.</p>
<p>don't think voluntary response is in line with the procedure needed to conduct a proper survey. most of the polls on cc cannot be called proper survey either; however beneficial and informative the survey results can be to the ccers, they cannot be said to represent the universe (all ccers).</p>
<p>In conclusion, where you go to college does not matter.</p>
<p>Thoughts?</p>
<p>no. if you look at placement into grad schools you will see the differences.</p>
<p>
[quote]
One professor of statistics, who is a co-author of a highly regarded AP statistics textbook, has tried to popularize the phrase that "voluntary response data are worthless"
[/quote]
</p>
<p>That's a rather extreme viewpoint, don't you think? After all, how else are you actually going to obtain graduation salary data? After all, you can't actually force anybody to tell you their salary. It's just a known problem that is endemic to most statistical studies.</p>
<p>
[quote]
After all, how else are you actually going to obtain graduation salary data?
[/quote]
</p>
<p>With the proper protocol, it could be by direct observation.</p>
<p>It's a very private matter between two parties neither of which is the school. I think the H survey is pretty good and gives a decent picture of the class.</p>
<p>
[quote]
In conclusion, where you go to college does not matter.</p>
<p>Thoughts?
[/quote]
</p>
<p>That this is a ridiculous oversimplification, albeit one that seems to be very popular to state on this board.</p>
<p>
[quote]
With the proper protocol, it could be by direct observation.
[/quote]
</p>
<p>Oh really? Exactly how? Again, you can't compel anybody to tell you what salary they're making or what job they're taking or, heck, whether they're even taking a job at all.</p>
<p>45K is really high, and consider that Harvard kids who go into certain professions have a quickly increasing earnings potential.</p>
<p>For example, IB: 1st year - 130K, 3rd year (associate) - 250K, 6th year (VP) - 500K at age 27-28</p>
<p>Or in MC: 1st year - 75K, 3rd year (associate) - 150K, 6th year (senior associate) - 350K at age ~27-28~</p>
<p>A better look would have been to gauge Harvard salaries 5 years out.</p>
<p>Considering that over 10% of the class is going into Education (Teach for America?), the $45k number is pretty impressive. But that is for only 2/3 of the class. It is likely that the students who find work later will do so at a lower average salary.</p>
<p>Those numbers were in the good days. These days for IB it's half that with many out the door. Also how many get to stay 6 years or more?</p>
<p>umm... i don't think that's necessarily true.</p>
<p>
[quote]
For example, IB: 1st year - 130K, 3rd year (associate) - 250K, 6th year (VP) - 500K at age 27-28</p>
<p>Or in MC: 1st year - 75K, 3rd year (associate) - 150K, 6th year (senior associate) - 350K at age ~27-28~
[/quote]
</p>
<p>Those are figures with bonuses<a href="especially%20for%20Ibanking">/i</a>. The article was just talking about *base salaries.</p>
<p>Good point - also, who knows who those bonuses might be this coming year (I've heard 30-40% drop).</p>
<p>Those numbers are always going to be higher than they really should be.</p>
<p>Students with a high salary are more likely to report their income, thus skewing the statistics northward.</p>
<p>On the other hand, while these statistics are of dubious absolute value, they could still be useful as a means of relative comparison, if we assume there is a similar selection bias across all schools that skews values up.</p>
<p>
[quote]
With the proper protocol, it could be by direct observation.
[/quote]
</p>
<p>Well, sure, but the "gun to the head" method of forcing responses has a perverse appeal to this researcher. Not that I could get that by our Human Subjects board.</p>
<p>More seriously, though....</p>
<p>Voluntary responses aren't "worthless." They have their limitations, but calling them "worthless" is the kind of hyperdramatic language you'd think a statistic professor would steer clear of.</p>
<p>"Those numbers were in the good days. These days for IB it's half that with many out the door. Also how many get to stay 6 years or more?"</p>
<p>It's not going to be down 50%, but easily could be down 25% for first year analysts. In my BB IB analyst class, 27% stayed on as a third-year analyst and 12% were promoted to associate.</p>