cyberwulf
-
Posts
839 -
Joined
-
Last visited
-
Days Won
9
Posts posted by cyberwulf
-
-
On 9/5/2020 at 4:43 AM, Statmaniac said:
I think @DanielWarlock has a point. MIT has a great list of faculties; one could research in statistics. Let me share my perspective here.
Many statistics programs are getting a lot of attention because of the big data, machine learning, etc. However, one should note that there are so many programs that offer outdated curriculums. Honestly, who uses UMVUE, complete statistics? I haven't seen any of these in any papers I have read in top statistics journals published within 20 years. What's worse is that these programs still teach courses like survey sampling, generalized linear models(GLM), which had little impact on the data science's current emerge. I am not looking down on these two subjects, but one should note that these courses have almost nothing to do with the current data boom. In machine learning, you spend at most one lecture on GLM, but these outdated curricula still insist students take a full semester-length of GLM/survey sampling and other outdated topics. Now that I am working on so-called hot or emerging statistics fields, I feel my past education from statistics program was completely useless. Courses like Information Theory, Optimization, Graphical models that were not the core curriculum in the statistics program have become essential in modern statistics research. These are somehow more often taught in EECS/CS/Math departments.
Aligned with what I said, I think if one wants to have a better edge in applications in the IT industry or new methodological works in statistics journals, it would be better to choose EECS/applied math/ORFE programs like MIT or Princeton. Please take a look at the new Stanford/Berkeley faculties profiles, many of them were not trained in the Statistics PhD program. I think those on the level to get admitted to Stanford/Berkeley stats are on the level to gain admittance on MIT EECS/Princeton applied math. If not, programs like Georgia Tech IE/Upenn Applied Math have successfully yielded top students who acquired tenure track positions in top statistics programs. As far as I know, oftentimes, these programs require applicants to contact potential supervisor first, so with your background, I think it is worth considering. That being said, compared to the IT industry, biomedical applications are somewhat slowly accepting these new machine learning methods. I think this is why top biostatistics departments are still teaching outdated methodologies. In terms of the recent statistical methodological work, EECS departments like MIT have far more contributed than many other statistics programs, which cannot get out of their old fame. Also even at MIT, there are a lot of people working on computational biology.
Therefore, as @cyberwulf said, you would have to decide between traditional stat programs(many biostat programs and some stats) vs. data-sciency programs(stat programs like Stanford, Berkeley, CMU, Yale, Columbia, and CS/OR/applied math programs). Fields like genetics are highly computational, so even if you go to the latter program, the chance to work in biomedical fields is quite high. However, given the current training offered by biostat or traditional stat programs, I think the other way would be quite challenging. One way to distinguish these two types of programs would be to ask if the collaborations between departments(CS/applied math/OR) are frequent or have a lot of faculties with joint appointments. Having a separate Data Science institute or Initiative is also a sign of more data-sciency program. Lastly look into the curriculum they offer.
I'm sorry, I just can't let this stand unchallenged. It is complete nonsense to say that GLMs have had little impact on data science. Talk to any practicing data scientist and they'll tell you that a lot of the models actually being used in practice are relatively simple regression models. And survey sampling? That's a special case of weighting, which is heavily used in machine learning in the case of rare events (and also to increase algorithmic fairness).
If all you're interested in doing is creating algorithms that do something faster or more accurately, sure, maybe you don't need a ton of statistical training. But, if that's all you're interested in doing, you're not really interested in being a statistician! Statisticians seek to develop tools for better data analysis, which includes quantifying uncertainty, carrying out inference, and improving model interpretability. It's impossible to do that without a solid grounding in the kind of old-fashioned statistics you look down your nose at.
Lastly, your conclusion that it is better to attend EECS/ORFE programs like MIT/Princeton because graduates from these programs have obtained positions in top stat departments is flawed. Top departments are often looking to find the smartest people they can hire, on the logic that they'd rather have a rock star who does something a little bit outside the norm than an "excellent-but-not-exceptional" faculty member who fits easily within the field. Sometimes, those brilliant people are in non-stat programs, but they're being hired because of their brains not because of their training. Indeed, if they were equally brilliant but had been trained in a stat department, they might be even more attractive candidates! Most people in EECS/ORFE programs will end up in those disciplines; entering such a program with the goal of entering a different field upon graduating is taking a huge gamble that you'll be so exceptional that hiring committees will overlook the fact that your research and training is unorthodox.
OK, rant over.
-
I would definitely prioritize taking analysis and probability (in that order of priority) over differential equations.
-
I think your list is being too heavily influenced by program deadlines and what they have told you they'll do with updated transcripts (e.g., applying to Chicago stat makes very little sense if you want to do biostat). Most programs will consider updated transcripts if you send them in mid-December. What matters more than the published deadline is when your application gets evaluated, and even programs with Nov/Dec deadlines generally review applicants in January/February.
Also, I would suggest applying to some of the bigger, higher-ranked PhD programs like Michigan, UNC, Minnesota, and NC State (stat; but they have a lot of folks doing stat gen stuff). It's not entirely unreasonable to apply to top 3 PhD programs; JHU might be a particularly good option because of your math prep and research experience in stat gen & neuroscience.
-
You probably need to start by figuring out if you want to do a PhD in stat/biostat or math. While there are some differences between stat and biostat programs, they are tiny compared to the gulf between stat and math programs. From your background (coursework & research experience), you seem like a much better fit for (bio)stat than math, and would likely be competitive for a lot of very good stat PhD programs.
-
On 8/27/2020 at 8:41 PM, cctvwp said:
@cyberwulf any advice on what range of schools I should be applying to if I'm looking to apply for PhD Bios programs?
I agree with the above advice. You should take a shot at a couple of top 10 PhD programs (which will almost surely admit you for a Masters if you don't get into the PhD) and probably focus your apps on programs in the 10-20 ranking range.
-
I think you need to add some more "reach" schools. It's not unreasonable for you to apply to a couple of schools within the top 10, like Michigan, Penn, UNC, etc., particularly if you're willing to wait a year and re-apply.
-
Yeah, that list is way too bottom-heavy. With non-disastrous letters, you're almost certain to get into most biostats programs ranked #4 and below. With strong letters, you have a very good shot at one of the top 3 places.
-
What I wrote in 2013 is still relevant today...
-
I think the top 5 stat programs are reaches for you, but it's definitely worth applying to a couple of them. I suspect you'll find more success in the 10-25 range. Your math background is solid, though McMaster is probably perceived by most as a little less prestigious than UBC/UofT/McGill/Waterloo. Great research experience, but unfortunately that can be a little hard for admissions committees to evaluate. The primary value of those experiences is that it hopefully allowed you to build strong connections with faculty who will write you glowing letters.
If you're set on going to a top-shelf PhD program, one approach might be to do a Masters at a top Canadian university, then re-apply.
-
5 hours ago, StatsG0d said:
I agree you could apply to pretty much anywhere, but I think the top-5 might be a bit of a stretch. Not because you're not a strong applicant, but the pool for biostats has been getting a lot more competitive over the last few years, to the point where I'd say it's on par with stats programs.
Top 5 biostat is not a stretch for this applicant, given the strength of their school, GPA, and test scores. In fact, while there are no guarantees, I wouldn't bet against them getting into all the top programs they applied to.
-
On 7/29/2020 at 6:01 PM, DanielWarlock said:
Normally I would be tempted to say that you will have no trouble at top programs as you listed. But I have seen too many competitive people here and elsewhere this year to say that you are a shoe-in (several published at places like anal of stats/prob, jmlr, jams etc).
Give me one example of someone from this year who has published in Annals (Stats or Prob) before applying for a PhD.
-
Your list of targets is confusing, since neither Wharton nor Cornell are biostatistics programs and the social stats specialists at UCLA are in the stat department. Are you looking at stat, biostat, or both?
-
It's also important to remember the role that applicant self-selection plays in the process. Most applicants won't apply to every top 10 program, so each admissions committee only ranks a subset of the applicant pool. This actually helps a lot; there would indeed be significant noise if every admissions committee had to rank the top 100 applicants to statistics programs, but things become a lot more stable when programs only have to decide who to admit from among a smaller group. Consider, for example, a school that is ranked between #5 and #10 in the country. It might attract ~20 of the top 100 applicants (some don't apply below top 5 and others just aren't interested in that program for various reasons). Assuming it accepts ~30 students per year, it's likely that most of these top 100 applicants will be admitted, because they are being compared to applicants that aren't among the top 100. Even for top programs like Stanford, the same logic applies, except perhaps replacing "top 100" by "top 50" (since Stanford might perceive a meaningful difference between a top 50 and non-top 50 applicant).
-
I think it’s likely we’re going to see a lot of international deferrals due to the visa situation.
-
Agree with the above. Depending on your letters, you could have a real shot at a top 10 biostat PhD program. I wouldn't bother with a Masters first; a substantial minority of biostat PhD students come straight from undergrad without a math/stat degree.
-
On 5/21/2020 at 4:59 PM, harry_stats said:
Would people be willing to comment on what they have heard from their respective universities (if anything) with regards to COVID, funding and possible reductions in cohort sizes? It is early in the process, but I wanted to get a sense of how admissions may be affected for next fall.
Nobody knows anything yet. Even in normal times, discussions on available funding and cohort size typically start in mid-fall, a month or two before admissions deadlines.
-
I think you are going to see another "post-doc pileup" similar to what happened in 2008-2010. Before that time, most PhD grads in stat & biostat seeking academic positions didn't do postdocs; then, for a couple of years, a ton of grads were pushed into postdocs by the lack of faculty positions and when hiring started again they had much better CVs than the fresh grads they were competing against. So, for the past 10 years, it's been pretty tough for PhD grads without a postdoc to land a tenure-track position.
I expect things to trend even further in this direction over the next several years: it may become virtually impossible for new grads to get academic positions without a postdoc, and multiple postdocs may become much more common. We may start looking increasingly like the lab sciences, where it's rare for new Assistant Professors to be hired without 3+ years of postdoc experience.
However, there is one countervailing factor that may work in (bio)stat's favor. Interest in data science was already high pre-pandemic, and I expect that even more people will become interested in statistical modeling and data analysis due to this experience. As a result, funding for stat/biostat hiring may be one of the first to return to pre-COVID levels simply to respond to increased demand for both data-oriented teaching and research.
-
Yes, I would expect that there will be fewer funded (mostly Ph.D.) positions available for Fall 2021, but there may not be a major impact on the availability of unfunded (mostly Masters) spots. Indeed, programs might try to expand their Masters programs to try to make up some of the financial shortfall.
The folks who are likely to suffer the most are current graduate students approaching graduation; the job market over the next 1-2 years could look pretty bleak.
- trynagetby and shuggie
-
2
-
Yes, we're quite aware that COVID-19 is a thing, and a lot of institutions are doing some form of optional or mandatory Pass/Fail grading. I would anticipate that we'll essentially just ignore Spring 2020 grades when evaluating applicants.
-
Just include extracurriculars and don't worry about it. At worst they'll have no impact, and at best they might catch an admissions committee member's eye as a slight positive.
- Jasmine Ng and Bayequentist
-
1
-
1
-
Disciplinary boundaries only matter insofar as they influence what you are likely to work on and where you are likely to publish, hence how much your profile will appeal to potential postdoc supervisors.
-
4 years is fairly standard for someone with a Masters in the same field. And if you're almost but not quite done in your fifth year and making good progress, then most programs will happily find something for you even if they didn't "guarantee" it up front.
-
Unfortunately, the middle of the admissions & recruiting season is probably the worst time to make an "unofficial" campus visit. Faculty and staff are already occupied with admitted students (who have highest priority) and may not be particularly keen on making additional arrangements for someone who is unlikely to be admitted. They would (rightly) also be concerned about precedent; if you were to visit and then ultimately be accepted, this would potentially create a big incentive for future non-admitted students to try to arrange such unofficial visits. Things could quickly get out of hand.
-
Here's the thing: It's much easier for programs to make "no decision" on applicants who aren't admitted in the first round and aren't obvious rejections than to come up with an official waitlist of people who are first in line to be admitted if first round offers decline. So, many schools keep a bunch of applicants hanging, even though most of these aren't really in the running for admission (editorial comment: I think this is unfair to students, but it's the reality). If you haven't heard from a school, offers don't seem to be trickling out gradually, and you haven't been notified that you're on an official waitlist, then you should probably be prepping yourself for bad news.
Before you start agonizing over your personal/research statement for stat or biostat, read this.
in Mathematics and Statistics
Posted
There's a lot more stuff that I would call "research lite", for example REUs, summer internships with professors, senior research projects, etc. However, since many applicants now have this, and the fact that it's almost impossible to gauge how much a student has really contributed to any research outputs they list, it doesn't really move the needle that much. Also, these opportunities are much more readily available to students at larger and more elite institutions, and it doesn't make sense to penalize those at smaller colleges who might have excelled if given these "research" opportunities but weren't able to access them.