Preparing for PHD

[statdude13]

Hello All, 

I just wanted to gather a few opinions on pursuing a PHD in Statistics given my background. I would like to begin a PHD program in maybe 3 or 4 years so I wanted to see what type of preparation is necessary. 

I have an undergrad degree in Business and an MS in Technological Entrepreneurship. 
The only math related courses I have taken are Quantitative Analysis for Business 1 and 2 and Business Statistics. I also conducted a research paper for my honor’s thesis in which I collected data and used multivariate hypothesis testing to find correlations between 10+ variables. 

To be eligible for a PHD program I was thinking I would take a few grad courses in stats as a non matriculating student and do well on my GRE. 

Just wondering if this would be enough or do I have no shot since I do not have a purely mathematical background. 

Any and all help is greatly appreciated.

[cyberwulf]

At MINIMUM, you will need the following math classes to even be considered:

 

Calculus I, II, and III (up to multivariable)

Linear Algebra

A year of probability/mathematical statistics

 

You will also need Real Analysis to be taken seriously by anywhere halfway decent.

 

Even with those courses, you'd have pretty marginal preparation. Most applicants to stats programs were/are math majors, and so will have taken quite a bit more than the above. The graduate statistics courses you could take with your current background are likely very applied and are not going to help you much when applying to stats departments.

 

So it's a bit of a tough road, but the good news is that if you have 3-4 years, you should be able to pick up the relevant pre-requisites through a combination of in-person and online classes.

[statdude13]

At MINIMUM, you will need the following math classes to even be considered:

 

Calculus I, II, and III (up to multivariable)

Linear Algebra

A year of probability/mathematical statistics

Thanks for the response. I was just wondering if the school(s) I decide to take the courses at will have a large impact.

I’m located in Southern California in the OC area so I am considering UCLA or UC Irvine as they both offer a wide array of stat classes. However, I am curious if taking some courses at a local community college or perhaps another University of California or California State school will have a detrimental impact on my profile?

I’m trying would like to have a strong application since I am giving myself ample time to prepare and since I feel as though I am at a disadvantage since I do not come from a mathematical background. 

You will also need Real Analysis to be taken seriously by anywhere halfway decent.

 

Even with those courses, you'd have pretty marginal preparation. Most applicants to stats programs were/are math majors, and so will have taken quite a bit more than the above. The graduate statistics courses you could take with your current background are likely very applied and are not going to help you much when applying to stats departments.

 

So it's a bit of a tough road, but the good news is that if you have 3-4 years, you should be able to pick up the relevant pre-requisites through a combination of in-person and online classes.

Thanks for the response. I was just wondering if the school(s) I decide to take the courses at will have a large impact.

 

I’m located in Southern California in the OC area so I am considering UCLA or UC Irvine as they both offer a wide array of stat classes. However, I am curious if taking some courses at a local community college or perhaps another University of California or California State school will have a detrimental impact on my profile?

 

I would like to have a strong application since I am giving myself ample time to prepare and since I feel as though I am at a disadvantage because I do not come from a mathematical background. 

Edited June 18, 2013 by statdude13

[Shostakovich]

Thanks for the response. I was just wondering if the school(s) I decide to take the courses at will have a large impact.

 

I’m located in Southern California in the OC area so I am considering UCLA or UC Irvine as they both offer a wide array of stat classes. However, I am curious if taking some courses at a local community college or perhaps another University of California or California State school will have a detrimental impact on my profile?

 

I would like to have a strong application since I am giving myself ample time to prepare and since I feel as though I am at a disadvantage because I do not come from a mathematical background. 

 

Personally I'd take the Calculus series at a community college (and also the lower division linear algebra) since those are normally huge classes with similar education anywhere. But if money isn't an issue, I would take all of the upper division courses (Real Analysis, Linear Algebra, Stats/Prob Theory, other electives) at UCLA or UCI since you could meet professors who could write you good recommendation letters. I'm familiar with programs at both schools and they have multiple profs who are quite active (and well known) in the Stats/Biostats discipline. Not sure about other UC's or CSU's.

[cyberwulf]

Personally I'd take the Calculus series at a community college (and also the lower division linear algebra) since those are normally huge classes with similar education anywhere. But if money isn't an issue, I would take all of the upper division courses (Real Analysis, Linear Algebra, Stats/Prob Theory, other electives) at UCLA or UCI since you could meet professors who could write you good recommendation letters. I'm familiar with programs at both schools and they have multiple profs who are quite active (and well known) in the Stats/Biostats discipline. Not sure about other UC's or CSU's.

 

Totally agree with this advice.

[superbean]

What other electives for us non-math majors would you guys recommend?  I'm signing up for advanced calculus and real analysis next year (along with M.S. Stats core classes) but I would like to get as much math in as possible.

[Tronathan]

Have you looked into taking these classes somewhere? I think most colleges will require you to have taken the prerequisite courses that are needed to enroll in a course even if you are not seeking a degree. Can anyone confirm if this true? If you are allowed to take a masters level mathematical statistics course without the required background I still think it is a pretty bad idea and you will almost certainly fail it.

 

I think a good strategy may be to look at the prerequisites for the Masters' level mathematical statistics course at UCLA (called 200B at UCLA) or UCI and work backwards. This class will probably require theoretical linear algebra, real analysis, and undergrad math stat. To enroll in those courses you probably need Calculus 3, some type of discrete math/ logic/ intro to proofs class, and upper division intro to probability. The calculus courses are in sequence; you need calc 1 to take calc 2 to then take calc 3.

[statdude13]

Have you looked into taking these classes somewhere? I think most colleges will require you to have taken the prerequisite courses that are needed to enroll in a course even if you are not seeking a degree. Can anyone confirm if this true? If you are allowed to take a masters level mathematical statistics course without the required background I still think it is a pretty bad idea and you will almost certainly fail it.

 

I think a good strategy may be to look at the prerequisites for the Masters' level mathematical statistics course at UCLA (called 200B at UCLA) or UCI and work backwards. This class will probably require theoretical linear algebra, real analysis, and undergrad math stat. To enroll in those courses you probably need Calculus 3, some type of discrete math/ logic/ intro to proofs class, and upper division intro to probability. The calculus courses are in sequence; you need calc 1 to take calc 2 to then take calc 3.

Thanks for the response. I am going to follow Shostakovich’s advice and take the math courses at a local community college and take the statistics undergraduate courses at both UC Irvine and UCLA so I can meet faculty at both.

This will probably take a few years if I take only one course per semester, however, time is not a big deal (I hope) since I am giving myself 3 to 4 years. 

[Shostakovich]

Thanks for the response. I am going to follow Shostakovich’s advice and take the math courses at a local community college and take the statistics undergraduate courses at both UC Irvine and UCLA so I can meet faculty at both.

This will probably take a few years if I take only one course per semester, however, time is not a big deal (I hope) since I am giving myself 3 to 4 years. 

 

I think it might be a good idea to focus on math courses even at UCLA and UCI, and make sure that you have multiple courses in Linear Alg and Real Analysis completed before you go for other courses. One other thing to remember might be that you only really need three good letters of recommendation, so it could be advantageous to take multiple courses with one prof (and build a good relationship with them).

 

UCI has a small Stats department in their Informatics/CS department (although with some faculty quite active in Stats/Biostats research) and taking their Stats 120 series (upper div intro probability/stat theory) could be a great way to meet some of them. The problem might be that they don't offer too many upper div Stats courses and you'd have to either go up to the the graduate courses or take related courses in the Math department. From what I understand, UCLA Stat is way bigger and even offer a Statistics major so you'd probably have a more diverse experience there.

 

Good luck!