Calling all PhD's -Math & Stats - understanding them vs. merely using them

[statsnoviceGRRR]

Hello all,

I am prepping for Graduate school next Spring... and my eyes are focused on getting a PhD in Marketing (I don't know if the focus will be behavioral or quantitiative) I realize I have some time ahead of me to worry, but I like being as prepared as possible which is why I'd like to pose some questions for the members here.

First Question:
It seems that because of technology and programs like SPSS, many researchers can employ pretty advanced analysis without really understanding what is going on behind the scenes. I would imagine that many social scientists don't have an exhaustive math background... so what is more important- focusing on my discipline or learning statistics inside and out?

Second Question:
What kind of a general math background do you think will help someone succeed in a PhD in Marketing program (candidates usually need to take statistics up to at least multivariate - i;ve seen some places require linear algebra, bayesian models... stuff i know nothing about basically.) All I have ever taken was an applied calc class. I loved it, but it was not "proof based" I honestly never even had any exposure to 'proofs' so I don't know what I am missing or how to compensate for my math immaturity.

I do know that I thought it was cool when I learned that one SD away from the mean = the inflection point of curve = point where second derivative changes sign. How important are these kinds of connections? I would imagine there are hundreds of facts like this... and it worries me that I do not know them!

 

[jkotlerman]

I don't believe that you will need advanced mathematics, but a good set of applied statistics classes for business and marketing majors is a must. It is true that many software packages will let you do very complex analyses without deep understanding of the processes, still it is much better to understand how these functions work and why you should or should not use them.

Jenny Kotlerman
www.statisticalconsultingnetwork.com

 

[JohnM]

Actually, the stats background of PhD-level social scientists who conduct research is relatively strong, especially in psychology....and they understand the pros/cons and underlying principles of the fancy multivariate methods before they "point and click."

Unless you plan to teach quantitative methods to PhD students, I wouldn't worry about proofs or mathematical statistics (i.e., second derivatives) - no one outside of academia gives a hoot about them...

Focus first on being a really astute marketer, and if you really want to, build stats as a secondary skill. People with PhDs in Marketing really love marketing, not necessarily stats.