Jump to content

spunky

Members
  • Posts

    433
  • Joined

  • Last visited

  • Days Won

    6

Everything posted by spunky

  1. Well, if I don’t get crazy excited about my field… who’s gonna do it?! XD Statistics, data analysis and research methodology engages in that perfect dialectic dance where applied problems give rise to interesting theoretical questions and interesting theoretical questions provide solutions to problems that have not arisen yet… or that have appeared in other areas but haven’t quite made it into Psychology. John Tukey (that’s right, the Tukey from that ANOVA post-hoc test) invented the boxplot while analyzing the distribution of call frequencies at the Bell Lab. Harold Hotelling invented (actually more like re-discovered) Principal Components Analysis while answering a problem related to educational test scores. It is difficult (but not impossible) to find a good statistician who has never dealt with real data or who has never been inspired by it. I consider my students/clients some of my greatest sources of inspirations because seemingly innocent, simple questions can be extended into complex statistical problems if you know enough about them. Which is the main reason of why I am and will always be a champion of giving emphasis to theory before applications whenever Statistics are being taught. Well… yeah. Lemme quote from this appropriately-titled article, The expanding role of quantitative methodologists in advancing psychology: “A major contributor to the lack of statistical literacy in psychology researchers is the disciplinary attitude that “anyone can teach stats” (Wilcox, 2002). When psychologists without a strong quantitative methodology background teach statistics, they often lack the enthusiasm for, and knowledge of, modern statistical approaches.” (p. 85) Your advisor is probably completely unaware of initiatives and grants like the $10 million dollar grant given to the Center for Open Science who are demanding Quant Psych grads, methodologists and statisticians in order to keep up with the demand for properly-trained data analysts who can oversee this new avalanche of replicability studies that are becoming so in-vogue nowadays. I could rant on and on about this stuff (and I’d love to!) but since you’ve already acknowledged that he’s biased, I’ll just let it be
  2. i still feel this has more to do with an issue of practicality and not necessarily with accuracy of performance. psych undergrads score pretty high up on both the verbal and the subject GRE. from a test-developing perspective these scores are not very discriminating because the majority of people do well. the quant GRE score is the one where you actually have bigger chunks of variability (unfortunately towards the lower end) and i guess that's why AdComms focus so much on it. the problem is, of course, with the jump in the logic that goes from "they did well on the quant section THERFORE they will do well in graduate school" which is not necessarily warranted. i do believe, however, that the bigger issue is how can universities develop a common standard along which they can compare their students. like how do you know that a 4.0 GPA from university A is equivalent to a 4.0 GPA from university B? there is no easy way to go about this from a standardization perspective unless you're willing to step on a lot of peoples toes and get yourself in situations like, i dunno, someone claiming "how can it be that a 4.0 from some crappy state school translates into a 2.0 from Standford U!?!" i truly do think that the GRE is the best the education establishment has been able to come up with to address this issue. it is incredibly limited, as we have discussed, but the other alternative that i have heard people champion (holistic evaluations) would simply cost too much. and now that we live in the "for-profit" model of education i don't really see it happening any time soon. at least not in my lifetime.
  3. I’ve both TAed and taught undergraduate statistics/methods courses (and a couple of graduate-level courses) and have tried to experiment with every possible method (even early-childhood education ones) to convey the material in the most efficient way. There are two things that, for better or worse, I have concluded: (a) there has to be an exam component to it and (b ) the exam component has to carry enough weight on the student’s grades that will motivate them to study and review the material. When I started my MA and began taking the same courses as everybody else I was 100% against exams and complained to the instructor (in a friendly manner, of course) about this. My reasoning was that if you had made it this far in your education, you were willing to study and learn the material because you knew it was important. What the prof said was that you always had to assume students will try to get away with doing as little as possible in classes like this because they tend to not like the material. Fast-forward a few years when I started teaching and I did start finding out that students had a harder time mastering the actual concepts behind statistics if they felt they were not going to be tested. It was like they did not need to put on the effort as much to struggle with the concepts and learn the material… and that is an extremely critical thing that needs to happen if you are seeing this stuff for the first time. When I attempted assignment-only courses, my students became incredibly skilled SPSS-button-pushers and that’s about it. Then they would show up at my door a few months down the line when they had to work on their theses/dissertations/manuscripts and I would get very frustrated because they couldn’t even work out the simplest things by themselves. Like I would tell them “we saw this in class, is in your notes, it’s in X or Y chapter of the book”. One of my students actually gave me a very good hint as for why they were unable to apply this stuff: he said that he always worked in a group with other two people or compared his answers with other students to make sure everything was right before handing it in. So the end result was a class where everybody got an A but only 3 or 4 people knew how things worked. Ever since then I decided exams are the only way I had to ensure that people are actually going to try things at home, practice them, struggle with them and, one way or another, learn them. I have changed the focus into making the classes more interactive though… like I use R to code interactive animations of regression or ANOVA (because the entire linear model has a geometric analogue so you can actually show it in pictures), we have class discussions, we have group activities, etc… but I always keep an exam component in my courses now…lurking…waiting. I wholeheartedly agree with this. The prof who taught me linear algebra had this famous (paraphrased) quote saying: "every self-respecting mathematician should, at some point in his or her life, have to find the inverse of a non-trivial matrix BY HAND". And if you have ever had to found the inverse of a matrix by hand then you know the process is both terribly boring and incredibly illuminating. As someone who both teaches and consults statistics I feel the greatest problem that we face is not so much in how we evaluate the material but how we deliver it. I feel a lot of people in Psych and other social scientists can become really good at following “ready-made” numerical recipes and feed them into SPSS but when it comes to actually understanding where these numerical recipes come from and, more importantly, how to adapt them to new types of data or designs well… then all hell breaks loose.
  4. the GRE is really only "a thing" in North America... and i would go as far as say it's mostly "a thing" in the U.S. because even some Canadian universities (like McGill) have peculiar policies where you don't have to submit your GRE scores depending on where you studied. NEVERTHELESS i kind of have to agree on this one. if you want to do graduate school in English or in a North American setting you just have to suck it up and jump through the hoops like everybody else. yes, we do have to do twice the work (i was born in Mexico so i know what i'm talking about here), yes we have to study twice as hard and yes, we need to struggle twice as much. but that is life and it can be done if you're willing to make the sacrifice.
  5. i don't know why i'm not surprised by this (<----LOL)
  6. well, i had to memorize a few hundred obscure English words to make sure i could get a decent mark on the verbal section of the GRE. ask me what any of those words mean now and i'm clueless.. so i do empathize with people's pain when it comes to cramming stuff for the sake of the GRE
  7. my husband and i own a home in Santa Barbara, CA Canadians as well. the rules are quite different than how things were before the great crisis of 2008 in terms of foreign nationals owning property. two things: obtaining a mortgage (as TakeruK correctly said) is (a) NOT easy. your down payment will be significantly higher than what's expected from a U.S. national. and (b ) it really depends on whether or not you hold the right passport (where "right" implies the banks may not be as willing to lend you any money depending on where are you from).
  8. well, i got into my program coming from a BSc in Mathematics with just a hint of scattered psych courses here and there. i'm not sure how similar our situations are though because my field (Quantitative Psychology) looks a lot more like Statistics than Psychology itself... so my major actually helped my application. nevertheless i got a pretty awesome score in the Psych GRE so i think that's probably what helped me seal the deal (which is more or less what VulpesZerda said).
  9. as long as you end up with an awkward laugh at the end, everything will be fine. remember, the more awkward the better. natalie portman's a is a good one to start practicing: https://www.youtube.com/watch?v=nlbsvC_1GsY
  10. well, for Texas A&M you can do this one: http://online.stat.tamu.edu/content_link.php?page=Certificates#schedule that seems to be more general-statistics based or this one: http://epsy.tamu.edu/degrees-and-programs/graduate-degree-programs/online-masters-research-measurement-and-statistics that has a more 'social sciency' feel to it. although just by looking at the titles of the courses on the education-based one it doesn't seem like you'll be doing a lot of statistics-related stuff. the first one seems like a better option (which is, i guess, the one you were referring to initially). from looking at the syllabuses of the courses i can see there's a lot of emphasis on SAS and R. i'd really recommend you practicing both before you begin. and if they offer some type of SAS certification, TAKE IT. it looks really good on the CV the Texas A&M and Iowa State are the only two ones i know that are both online and do not require a solid mathematical foundation. if you come across any more it would be nice if you could share them. i know lots of people who would also wanna improve their stats knowledge
  11. yeah, a full-on Master's degree on Statistics is not recommended for anyone who doesn't have a solid math base. i'd say the BARE minimum that you'd need is the basic calculus sequence (differential, integral and multivariate), linear algebra and at least a course on mathematical statistics or a 3rd-year level probability course (something that focuses on the method of proof). i only know one person who was on a similar situation to yours and he vouched for the online MSc program in Iowa State. you can circumvent all theory courses and just focus on the applied ones so it is more manageable if you don't have a solid math foundation. i think i asked you about whether your (physical) presence was required or not because there are many applied statistics programs housed under Faculties/Departments of Education that cater to people with limited math backgrounds but who want to become better data analysts. there are 2 in Texas (Texas A&M and University of Texas) if you go on here: http://www.apa.org/research/tools/quantitative/ and click on "Educational psychology programs in quantitative methodology" you should get all the info you need. many offer an MEd route so that you just do the courses and graduate.
  12. does it *have* to be online or are you open to applying to programs where you have to be physically present and do the coursework?
  13. actually, i added wrong lol... it's more like 80% (yes, that's EIGHTY percent) of applicants with a Psych major score just barely above the 50th percentile. the breakdown of the table (which is on page 30, not 29) to focus on is: 20% - 140-144 (10th - 18th) 27.1% - 145-149 (21th - 37th) 24.8% - 150-154 (40th - 56th) so 20% of psych majors score between the 10th - 18th percentile of the quant section (that's really, low), 27.1% score between the 21th and 37th percentile and 24.8% are in the 40th-56th percentile range. if you add those three big groups to people who score below the 10th percentile (i.e. people for who numbers are really, really not their friends) then you get that around 80% of grad school applicants with a psych major score either at the 56th percentile or below on the quantitative portion of the GRE. i think i'm starting to get now why my field of Quant Psych is so unpopular...LOL.
  14. About a couple of years ago or so I took an internship on ETS and was particularly interested in working in the department that handles the GRE (& all the other post-grad tests like the PRAXIS and whatnot). Here are some of the things I took home from them: - Every single study where the ETS claims you shouldn’t use a cut-off score is merely a formality that they use to prevent getting sued. Think about it… they want to sell you a product and then they’re gonna bash it? Of course not! Heck, if they were not sued they’d probably trumpet them as the secret oracle of success in graduate school. There are lists of results that are available to the public and there are lists of results that are only privy to ‘clients’ (e.g. universities). It’s mostly technical stuff and I never saw one but I knew from the people who worked on them that they were mostly devoted to come up with “diagnostic scores” which is the euphemism ETS uses for cut-scores. Funding agencies, AdComms, everybody is always asking you for the cut-score because they all need to make quick, easy decisions. Whether the decision is accurately reflected by the score or not is mostly irrelevant. That is one of the many dirty little secrets out there that you get to learn about if you hang around ETS. - If a uni says the GRE is not required but ‘recommended’ you can bet your brownies they will use it against you. - Psych (& other social sciences programs) relies on the quantitative score on the GRE for a very simple reason: it’s the one where psych majors tend to score the lowest. Just look at the table on p. 29 (http://www.ets.org/s/gre/pdf/gre_guide.pdf). You can see that around 60% of people with a major in Psych just meeerely scratched above the 50 th percentile. The fact of the matter is that the number of GRE test takers is increasing exponentially and, with that, the number of applications that Psych (and other grad) departments receive every year. This is especially true after the 2008 crisis and the loss of value in a college degree. Anyone who has glanced at the sheer number of apps that departments receive every year knows that no prof is gonna take the time to look through 100s upon 100s of applications, especially if the POI is well-known and the program is prestigious. For clinical in my uni, for example, we got WAY over 300 applications for like… maybe 7-8 positions? No department is interested in spending the resources to evaluate applications holistically so unless there is something that REALLY makes you stand out (funding, publications in prestigious journals, your POI knows you, etc.) people are probably gonna default back to the GRE. I dunno but I really don’t see this situation improving in any way in the short term, especially as the love affair between the U.S. and standardized testing just becomes deeper and deeper.
  15. i chose a thesis topic during my master's that i LOVED and now i can't even be in the same room with that topic without feeling resentful and angry. and i used to LOVE it so much! so maybe this is a blessing in disguise? (i.e. you won't end up hating something that you initially loved?)
  16. well.. you posted during the SUPER BOWL WEEKEND... what did you expect?! kiddin'... why don't you consider moving this thread to the Psychology sub-forum? we have conversations like this almost every month or so (and February just started so you could kickstart the next one! ). i feel you'd probably benefit more from people who are in the same situation like yours in a program similar to yours
  17. Oh, tell me about *THAT*. For my MA's thesis I worked on extending and testing some of the developments published in this article. At some point it had one of those "after finding the first, second and third derivatives of the likelihood function it easily follows that..." but finding the first, second and third derivatives took me like a week!
  18. What do you mean by MIGHT actually be fun? It IS fun! It’s like the funniest thing ever! We have graphs! Lotsa them! With shiny colours! XD
  19. Aw… you clicked on it? Thank you! Well… we are and we are not. I am definitely heavy on the math because that’s the tradition I come from. As I mentioned to you, I did an undergrad degree in Math and tried to incorporate as many Statistics courses as I could. I studied in a very, very small rural university and they didn’t have a separate Statistics department so I improvised a “Statistics” degree the best I could. But it does not have to be. There are more people on the “applied side” who have a good intuition for data analysis and can do some basic matrix algebra/college calculus and that is enough for them. For you (and basically anyone interested in Quant Psych) this is my take on why it is much more beneficial to be a “statistician/mathematician interested in Psychology” rather than “a psychologist interested in Statistics”): - The preeminent journal in our field is Psychometrika (http://link.springer.com/journal/11336). It contains probably some of the most famous papers on theory and methods that later became standard in Psychology and the behavioural sciences. The journal is VERY mathematical. You need quite a bit of a math/stats background to go through all the theorems, proofs and applications. Because of that, of course, it’s a tough journal to get published in. So if you are a rising scholar and manage to get a manuscript published there, people will be fighting for you. I know that because it happened exactly to a friend of mine. This person recently accepted a position at Michigan State U (another VERY prestigious program) and once this person had gone through the necessary formalities, they told him/her that what stood out over everything was his/her article in Psychometrika, which no other candidate had. - Where the talents of Quant Psych people really shine is when you see a new and complex method published somewhere and you know you can apply it to your data (as opposed to doing things to the data so it fits some more basic, not-as-interesting method). That usually implies you can read math, you can transform math into computer code (hence the importance of having programming skills) and you can execute this code in a way that you and, hopefully, other people can understand. If you can’t read and understand math then you can’t really use many of these methods until someone who can read and understand math publishes a watered-down version of it in some other journal and now you’re stuck citing this person over and over again while he or she sees his/her citation H-index move up. That’s actually a trick a lot of Quant Psych people use to get easy pubs out. They act as “knowledge translators” and publish complicated stuff in simple words and then everybody goes and cites their stuff - Think about this from a very pragmatic, hiring-a-new-person perspective. You have Candidate A and Candidate B applying for the same tenure-track Quant Psych position. The publications and research experience of Candidate A tells you that he or she is a very skilled data analyst but that’s about it. Candidate B, on the other hand, not only is a skilled data analyst but can also read and publish theoretical papers, knows how to program and develop software, is ‘fluent’ in many programming languages, etc. Which candidate gives you the more bang for your buck? Theory is (in my opinion) VERY important because if someone understands theory they can apply it in practical data analysis problems regardless of which setting they are in. But if you only know how to analyze data and don’t understand the theory behind it, you can easily get stuck with problems that sorta-kinda-almost look as if they could be solved by some analysis method that you learnt but the data doesn’t quite fit. You’ll need to go ask someone who knows theory to guide you. And theory is usually the realm of Statistics/Mathematics departments.
  20. good! so you know some R, some Python and some UNIX Shell. that's a good thing because that means you've been exposed to programming before and you're not starting from 0. i've found that people in cognitive programs tend to have more technical skills so that is an advantage. i think you're fine as far as your math goes. a lot of succesful applicants to Quant Psych programs only have their intro and advanced research methods courses as a math background. as you can imagine, the less "sophisticated" your math background is the more time you'll need to spend catching up by taking classes and not doing research. i know many prestigious programs in Quant Psych partner themselves up with Statistics Departments and require their students to take classes in the Statistics Department. if you plan to apply to any of those, then you REALLY need those linear algebra/regression courses. especially if they have an emphasis on theory and how to build proofs/mathematical arguments. if i were you and still had a year(ish) to apply i would take an introductory course to Linear Algebra (Multivariate Statistics is essentially linear algebra for statisticians) and a course solely devoted to Regression Analysis. if you see ANYTHING regression, take it. you can thank me later. yes.... but i'd need to charge you for that ok, no, LOL. i'll need more info about this because this could be tackled in a variety of different ways from a variety of different models. like if this is an analogies test, then item response theory is the way to go. if this is has more to do with the actual content of the words, then something along the lines of text analytics/multidimensional scaling. if this is a stimulus/response kind of thing then it falls within DoE (Design of Experiments)/ANOVA framework. spunky cannot compute with the information provided! more information is needed! i say it's a great, great, GREAT idea. i was actually doing my MSc in Statistics (which I left unfinished) when i got my letter of acceptance to my program. the more R/Stats/technical skills you can muster, the better prepared you will be.
  21. Anyhoo, yes! I have my MA and I am now finishing the first year of my PhD in Quant Psych. I LUV IT LUV IT LUV IT LUV IT and will address your questions in a sequential and orderly fashion This type of program is AWESOME and here’s why you think should think it’s awesome as well . First and foremost, our job prospects in academia and tenure-track positions are FAR better than those in any other area of Psychology as you can see on here http://www.apa.org/research/tools/quantitative/. I know a common (and valid) criticism is that this data is from 1996. But no need to worry, if you look at this blurb I prepped for other gradforum thread: you will see I linked the sources of the original data from the National Science Foundation so you can see for yourself where Quant Psych stands. I haven’t finished crunching the numbers but I will post an updated “study” on employment trends within Psych on my blog . Still things are more or less what you would expect them to be: everybody is worse off after the 2008 crisis… but we’re still the only program where the number of tenure-track positions outnumber PhD graduates. It’s just a game of numbers, you see. Quantitative programs we’re not that popular (as you can see from some of the responses to this very thread). You wanna dabble somewhere outside academia? No worries! I have done work for hospitals, market research firms, private and public research institutions, StatsCanada (like the Census Bureau of Canada), the government and, my favourite, testing companies (like ETS, the proud owners of the GRE). The fact of the matter is that there is more data out there than people capable of making sense of it and coming from a social science program gives you that cool edge that you can always make it relatable to other people. As a Quant Psych you are one of the few people who will be capable of working on any lab, regardless of which area within psychology it is because everybody gathers data and you know how to make sense of data. If you don’t feel like doing applied work, you can always take safe haven in the cold beauty of abstraction and do statistics for the sake of doing statistics (which I do often . But still I have been able to learn quite a bit of things from my fMRI data/ biopsych friends, my social networks / social psych friends, my I/O friends… it’s basically a pick-and-choose which lab you want to be a member of. Trust me; ANY lab out there has its doors open for someone who is a capable data analyst and you can always keep a more ‘applied’ side if that’s what you like. For example, I happen to be passionate about the phenomenon of unemployment and underemployment for post-graduate students. So I gather a lot of data and look at trends and patterns on that. When I get bored with that and want to go back to my math, I just take out my computer and start writing code. I AM! I DID! I applied because of two things. First, I’m fascinated with this crazy idea that you can actually use numbers to describe people’s behaviour. And it surprises me incredibly how accurate that is! Within the various areas that you can specialize as a Quantitative Psychologist I really like Psychometrics and the ‘working horse’ of modern Psychometrics which is Item Response Theory. I remember when I was in elementary and high school I would find myself asking what would be the probability of me passing an exam if I just randomly replied to the answers in it. Little did I know that within Statistics there is a whole area devouted solely to modelling the probability of people endorsing or rejecting certain items. It was almost like magic! Second I really want to become a prof. I love research, I love teaching and I love tutoring students. Once I figured out just how hard it is to obtain a tenure-track position in a good university nowadays I thought “which program would maximize my chances of landing a job like the one I like?” Well, the one where people applied the least! And here I am This same website: http://www.apa.org/research/tools/quantitative/has a list of all the programs in North America that offer concentrations in Quantitative Psychology, Mathematical Psychology and Educational Measurement, which all overlap but are not exactly the same Now, some recommendations that some of the people in this thread have tangentially touched on: - Formal training in Mathematics or Statistics is not required but it would help you A LOT. I did my BSc in Mathematics and that enabled me to jump into research right from the very first year because I already knew a lot of the stuff that was being taught. It would be very, very helpful for you if you took the basic Calculus sequence in college (differential, integral and multivariate), linear algebra and LOTS AND LOTS of Statistics. Again, not required but HIGHLY recommended. - You need to know how to program. Computer programming is an essential skill in Quant Psych. The statistical models that you will be fitting and the type of analyses that you will be conducting are far beyond what SPSS can offer. It would be VERY useful for you to ditch SPSS if you are still using it and practice R. I mean, SAS and STATA are also recommended but Psychology is spearheading social science programs in moving exclusively to R (like most academic programs). Here in the Psych Dept, for example, no graduate course (not even the introductory ones) in methods/statistics uses SPSS. Everybody uses R. We offer two optional “R bootcamps” during the summer for new graduates so they can get up to speed with it so when the semester starts they can dive into it without any problem. - Taking a look at quantitative journals within the social sciences will give you a good insight of what Quant Psych people do. Have a look at Multivariate Behavioral Research, Psychometrika, Psychological Methods, Educational and Psychological Measurement, etc. It’s good to know what you will be getting yourself into right from the start.
  22. Sorry, Spunky was busy helping have everything ready for Monday to receive the hordes of potential new recruits!!! (Actually it’s not hordes. Just a few people… but we still want to make a good first impression. There will be ice-cream! XD)
  23. well... who knows! i mean, it's still not friday and someone told me today in class that they're taking bets to see who will be the last prof to send out invites... so apparently there are still a few. but the official recruiting stuff is gonna happen this coming week so yeah.. there's not much time left.
  24. from the few posts i read it doesn't seem like anyone applied to UBC but i feel compelled to share stuff . my friends in social/clinical said today that probably 99% of invites have already been sent out. there're still some last-minute profs but apparently friday will be the last day.
×
×
  • Create New...

Important Information

This website uses cookies to ensure you get the best experience on our website. See our Privacy Policy and Terms of Use