Re: [tips] The season of the deceased grandparent
When a student tells me that he or she will miss classes because of the death of X, I will often send a sympathy card home. It’s often appreciated. But I can imagine that in some cases it might raise the issue of why I think that someone has died. I figure it’s a win-win situation. Adams, Mike (1990). The Dead Grandmother/Exam Syndrome and the Potential Downfall of American Society. http://www.easternct.edu/~adams/ Enjoy! Hugh On Sep 3, 2014, at 4:39 PM, Jeffry Ricker jeff.ric...@scottsdalecc.edumailto:jeff.ric...@scottsdalecc.edu wrote: Hi all, I have required proof of the death of a family member for a long time now. I do this because, years ago, a student told me that he had missed a test in my class because his grandmother had died; and then several weeks later, in another instructor's class, he missed a test because (he told the instructor) that grandmother died! Apparently, she rose from the dead after the first funeral, only to die a short time later. The poor lady! Caron, Whitbourne, Halgin (1992) looked at fraudulent versus legitimate excuse-making, and found no difference in the frequency of these among college students. One difference they did find, however, is the greater number of fraudulent excuses claiming that there was a family emergency (p. 91). On the other hand, legitimate excuses were more likely than fraudulent ones to involve the death of a grandparent. Go figure. I seem to remember another paper, mentioned on TIPS a long time ago, showing that grandparents are more likely to die just before test days. Is this a false memory? Best, Jeff Reference Caron, M. D., Whitbourne, S. K., Halgin, R. P. (1992). Fraudulent excuse making among college students. Teaching of Psychology, 19, 90-93 On Tue, Sep 2, 2014 at 5:49 AM, Beth Benoit beth.ben...@gmail.commailto:beth.ben...@gmail.com wrote: Claudia and others, I didn't receive Nancy Melucci's initial post either, but read it at the bottom of Tim's reply. I don't recall this happening before, so hope it's just a quirk. Or maybe that's what happened to two previous posts of mine that got no replies? Beth Benoit Plymouth State University New Hampshire On Mon, Sep 1, 2014 at 11:51 PM, Claudia Stanny csta...@uwf.edumailto:csta...@uwf.edu wrote: Nancy, Given your institution's policies, you had no choice but to drop her if she did not show up. I expect she had the same experience in multiple classes if she was out of town for a funeral, which probably adds to her stress but should send her a clear message that this is what happens at this institution. Now if yours was the only class she missed and was dropped from, that raises a new set of questions, doesn't it? If she were out of town, wouldn't she have missed multiple classes? Just asking. . . . I think you were most kind and generous to offer to reinstate her. But I know how rigid the rules about attendance can be at two-year institutions. I learned recently that in Florida, students who miss more than a certain number of classes must be withdrawn by the instructor, even if the student is doing well in the class. Something about the regulations related to financial aid awards at 2-year schools. (The four-year schools don't have this policy, so it came as quite a surprise to me when this matter came up in a faculty development activity that involved multiple people from 2-year schools.) Perhaps if you had reinforced the message that this was not entirely your decision by telling her you would attempt to get her reinstated, assuming you could persuade the registrar or whoever to accept her documentation, you might have gotten a less hostile response. (And it would have saved you some additional grief if your attempts to reinstate her hit a bureaucratic wall.) But I wouldn't guarantee that! :-) Claudia BTW Anyone else on TIPS not getting all of the messages? I received Tim's response but never saw Nancy's question. I even looked in my spam filter. And no, I do not have a special filter set for Nancy! :-) _ Claudia J. Stanny, Ph.D. Director Center for University Teaching, Learning, and Assessment University of West Florida Pensacola, FL 32514 Phone: (850) 857-6355tel:%28850%29%20857-6355 (direct) or 473-7435 (CUTLA) csta...@uwf.edumailto:csta...@uwf.edu CUTLA Web Site: http://uwf.edu/offices/cutla/http://uwf.edu/cutla/ Personal Web Pages: http://uwf.edu/cstanny/website/index.htm On Mon, Sep 1, 2014 at 10:05 PM, Tim Shearon tshea...@collegeofidaho.edumailto:tshea...@collegeofidaho.edu wrote: Nancy Short version- you are doing the right thing and it’s her environmental factors and lack of self-reflection that lead to her response. (I.e., it’s her – not you) Long version: I’ve had exactly the same thing happen – even getting abuse from a parent for being “heartless in their time of need”. My syllabus stated that if you must miss you MUST notify me at
Re: [tips] statistics teaching: SPSS vs R
I probably didn’t describe well what I experienced in using R, so I’ll do so here…in detail that will have little interest for most TIPsters. So, unless you’re really interested in R, you won’t want to read further. ;-) I’m using a Mac, so you can get a sense of the extent to which people encounter problems with R by subscribing to the R-sig-mac list: To subscribe or unsubscribe via the World Wide Web, visit https://stat.ethz.ch/mailman/listinfo/r-sig-mac Trust me…people encounter lots of problems just trying to get R up and flying on the Mac. Admittedly, I don’t always understand what they’re trying to do, nor why they’re having problems, but it seems fairly common. My experiences were with R 3.1 (Spring Dance) and the latest version is 3.1.1 (Warm Puppy), which was released in July. And, as I’d mentioned, I was using Field’s text as a guide. Moreover, Field suggested starting with RCommander, though he proposed that in the long run readers would become comfortable with the command lines and move beyond RCommander. I also did most of my work within the RStudio environment, which made it easy to get “help” files, etc. I understand RCommander to be fairly ubiquitous. It’s also going to provide most of the statistical analyses that a beginning student would likely need. However, I don’t think that it can handle more complex designs. OTOH, Field’s text provides command lines for a number of complex designs. So that’s where I started. At the outset, one needs to install a bunch of packages. The one that appeared to be broken enables comparisons (multcomp). Below is an email that lays out the problem and the proposed fix. In so doing, I hope that I’m clarifying what I meant by “stuff” breaking with updates to R. And it’s really a nice community (like TIPS, but not as much fun), with very responsive members of the community. That said…and consistent with earlier comments…the R experience surely requires more support than is necessary for SPSS Hugh P.S. I have copies of short handouts for R available, if anyone is interested. - Hi John, [Russ responding to John Fox] Well, I wasn't really aware of the problem, though I do remember looking at the package-checking results for my package, lsmeans, maybe a month or two ago and seeing there was an error in the OS X Mavericks test because multcomp wasn't found. Since multcomp is such an important package, I assumed that was a totally spurious result and didn't follow-up on it. I also looked at the checking results for multcomp, and what I see for Mavericks, there is a message that an Rd file links to lsmeans documentation but can't find it. I also note that lsmeans is not mentioned in any of the Depends, Suggests, Imports, Enhances fields, and I wonder if that's a problem. It appears that there is another package, SimComp, that is in Suggests for multcomp, but is not available for Mavericks, and one of the examples in multcomp requires it. So that is part of this picture as well... For Hugh, I think this approach might work for you: 1. Make sure all the packages required by multcomp are installed:they are stats, graphics, mvtnorm, survival, TH.data, and sandwich. 2. Install the multcomp tarball: download.file(http://cran.r-project.org/src/contrib/multcomp_1.3-2.tar.gz,multcomp_1.3-2.tar.gz;) install.packages(url(multcomp_1.3-2.tar.gz), repos=NULL, type=source) 3. If you want lsmeans (and of course you do!), install it the same way: download.file(http://cran.r-project.org/src/contrib/lsmeans_2.00-5.tar.gz;http://cran.r-project.org/src/contrib/lsmeans_2.00-5.tar.gz,lsmeans_2.00-5.tar.gz) install.packages(url(lsmeans_2.00-5.tar.gz), repos=NULL, type=source) Hope this helps, Russ Russell V. Lenth - Professor Emeritus Department of Statistics and Actuarial Science The University of Iowa - Iowa City, IA 52242 USA Voice (319)335-0712 (Dept. office) - FAX (319)335-3017 On 4/21/2014 11:18 AM, John Fox wrote: Hi Hugh, -Original Message- From: Hugh Foley [mailto:hfo...@skidmore.edu] Sent: April-21-14 11:09 AM To: j...@mcmaster.camailto:j...@mcmaster.ca Subject: multcomp Hi John! I'm so sorry to bother you. I've tried all sorts of web searches to no avail (looking at FAQs, etc.). I'm just starting to use R on a Mac and apparently multcomp is no longer available. Is that true? So, when trying to install RCommander, I get the message about multcomp. I can't figure out what's going on (broken with new versions of R?), but everything else seems to work.I just can't compute post hoc comparisons. I'm assuming that this problem is well known, so if you could just point me to some relevant info, I'd appreciate it. I was aware of this issue on the Mac and assumed that it would be fixed by now, but it isn't. A quick look suggests that there is a circularity issue in building the multcomp and lsmeans packages; see their check summaries on the Mac: http://www.r-project.org/nosvn
Re: [tips] statistics teaching: SPSS vs R
Last year, some students from my adv stats course (taught with SPSS) asked me to teach them R in the spring. I knew nothing about R, but I’d enjoyed using Field’s SPSS text to supplement Keppel Wickens and knew that he had a version with R: http://www.amazon.com/Discovering-Statistics-Using-Andy-Field/dp/1446200469/ref=sr_1_1?ie=UTF8qid=1408732248sr=8-1keywords=andy+field+r I’m sure that Field is not to everyone’s liking, but I enjoy his irreverent examples and his stats knowledge seems solid. Here’s my take on my R adventure… It’s admirable that people are actively working on R. It may well survive for a long time. That’s the good news. The bad news is that people are actively working on R. That means that stuff breaks with new versions. (As in the many pieces of software incompatible with new versions of an OS.) For example, I think that some of the programs that Field developed for R (in a 2012 text) won't work with the newest versions of R for Mac. And a nice package for post hoc analyses wouldn’t work with the latest Mac version (for Mavericks compatibility…and Yosemite is on the horizon…EEK). That said, I could get all the “big” analyses to work by using examples from Field’s text within RStudio. (It may all be easier on a PC.) I would argue that with sufficient investment of time (but see David below), learning R with a supporting text (such as Field’s) could lead to mastery of a package that would be even more powerful than SPSS in lots of ways. People seem to be developing statistical software for R all the time, while SPSS seems fairly stagnant for software that isn’t business related. I’ll be teaching adv stats again this fall (for the last time). I will surely use SPSS, but I may accompany each example in SPSS with R code. Hugh On Aug 22, 2014, at 10:13 AM, David Epstein da...@neverdave.commailto:da...@neverdave.com wrote: In discussions of R, I tend to think of what programmer Jamie Zawinski once said about Linux: that it's only free if your time has no value. :) --David Epstein da...@neverdave.commailto:da...@neverdave.com --- You are currently subscribed to tips as: hfo...@skidmore.edumailto:hfo...@skidmore.edu. To unsubscribe click here: http://fsulist.frostburg.edu/u?id=13238.0e762b65028402721e10bbc97ede52b7n=Tl=tipso=38043 or send a blank email to leave-38043-13238.0e762b65028402721e10bbc97ede5...@fsulist.frostburg.edumailto:leave-38043-13238.0e762b65028402721e10bbc97ede5...@fsulist.frostburg.edu -- Hugh J. Foley Department of Psychology Skidmore College Saratoga Springs, NY 12866 518-580-5308 http://www.skidmore.edu/~hfoley -- And I still don't know if I'm a falcon, a storm, or an unfinished song. Rilke -- --- You are currently subscribed to tips as: arch...@jab.org. To unsubscribe click here: http://fsulist.frostburg.edu/u?id=13090.68da6e6e5325aa33287ff385b70df5d5n=Tl=tipso=38050 or send a blank email to leave-38050-13090.68da6e6e5325aa33287ff385b70df...@fsulist.frostburg.edu
Re: [tips] student question - terror
My colleague Sheldon Solomon and his colleagues talk about terror management theory. Apparently contemplating one's demise has an impact on one's world view. ;-) Hugh On Oct 24, 2013, at 3:40 PM, Christine Grela cgr...@mchenry.edumailto:cgr...@mchenry.edu wrote: Sorry in advance for cross-posting! I had a student approach me after class today with an interesting question. He is interested in writing a horror story, but he is looking for some psychological insight on terror specifically, what makes us afraid, and how that might be different from horror more broadly. I couldn’t give him any resources off the top of my head that would apply to writing, but I thought someone on this list might have some ideas. If you have any suggestions for resources I can recommend to this student, I would really appreciate it. Christine L. Grela Instructor of Psychology McHenry County College Office: C-124; Phone: 815-479-7725 cgr...@mchenry.edumailto:cgr...@mchenry.edu --- You are currently subscribed to tips as: hfo...@skidmore.edumailto:hfo...@skidmore.edu. To unsubscribe click here: http://fsulist.frostburg.edu/u?id=13238.0e762b65028402721e10bbc97ede52b7n=Tl=tipso=29063 (It may be necessary to cut and paste the above URL if the line is broken) or send a blank email to leave-29063-13238.0e762b65028402721e10bbc97ede5...@fsulist.frostburg.edumailto:leave-29063-13238.0e762b65028402721e10bbc97ede5...@fsulist.frostburg.edu -- Hugh J. Foley Department of Psychology Skidmore College Saratoga Springs, NY 12866 518-580-5308 http://www.skidmore.edu/~hfoley -- And I still don't know if I'm a falcon, a storm, or an unfinished song. Rilke -- --- You are currently subscribed to tips as: arch...@jab.org. To unsubscribe click here: http://fsulist.frostburg.edu/u?id=13090.68da6e6e5325aa33287ff385b70df5d5n=Tl=tipso=29070 or send a blank email to leave-29070-13090.68da6e6e5325aa33287ff385b70df...@fsulist.frostburg.edu
Re: [tips] Statistical question-correlations
Rather than create an attachment, I'm providing a link to a handout for my stats class. It portrays how one could have a positive relationship in one group and a negative relationship in another group, but overall there would be a positive relationship. If you simply imagine the upper group (x values from 6-10) as having a negative relationship, you would have one way that two groups with negative relationships could combine to produce a positive relationship. In a similar fashion, you could envision how two groups with positive relationships could combine to produce a negative relationship. http://www.skidmore.edu/~hfoley/Handouts/S.Ch16-17.pdf [scroll down to the top of page 10] Hugh On Feb 27, 2012, at 11:30 AM, Helweg-Larsen, Marie wrote: I have a simple statistical question. I have a sample of 307 people. 111 are in the red group and 196 are the blue group. The correlation between variables x and y in the red group is r= .226 (n=111), p .05 and in the blue group r=.164 (n=196), p.05. However, when I run the correlation between x and y in the entire sample (red and blue combined, no missing data) I get a negative correlation, r=-.142 (n=307), p .05. Now what doesn’t make sense to me that two groups individually have positive and significant correlations but the two groups combined can have a negative and significant correlation. So you stats tipsters. Is that statistically possible? I have checked everything I possibly can in terms of errors in the data or the analyses and have found none. Some suggestions about what I ought to look at? Marie Marie Helweg-Larsen, Ph.D. Associate Professor l Department of Psychology Kaufman 168 l Dickinson College Phone 717.245.1562 l Fax 717.245.1971 Office Hours: Mondays and Tuesdays 2:00-3:30 http://users.dickinson.edu/~helwegm/index.html --- You are currently subscribed to tips as: hfo...@skidmore.edumailto:hfo...@skidmore.edu. To unsubscribe click here: http://fsulist.frostburg.edu/u?id=13238.0e762b65028402721e10bbc97ede52b7n=Tl=tipso=16294 (It may be necessary to cut and paste the above URL if the line is broken) or send a blank email to leave-16294-13238.0e762b65028402721e10bbc97ede5...@fsulist.frostburg.edumailto:leave-16294-13238.0e762b65028402721e10bbc97ede5...@fsulist.frostburg.edu -- Hugh J. Foley Department of Psychology Skidmore College Saratoga Springs, NY 12866 518-580-5308 http://www.skidmore.edu/~hfoley -- And I still don't know if I'm a falcon, a storm, or an unfinished song. Rilke -- --- You are currently subscribed to tips as: arch...@jab.org. To unsubscribe click here: http://fsulist.frostburg.edu/u?id=13090.68da6e6e5325aa33287ff385b70df5d5n=Tl=tipso=16296 or send a blank email to leave-16296-13090.68da6e6e5325aa33287ff385b70df...@fsulist.frostburg.edu
Re: [tips] Dumb question....
If I'm understanding the question, it's a fairness issue. :-) The denominator (MSWithin) is the pooled variances of samples. The numerator, OTOH, is a variance of sample means. In essence, then, the numerator is looking at a sampling distribution of means. Because the sampling distribution of the mean has a variance of (sort of) s2/n, multiplying by n turns it into s2, which gives you an F (ratio of variances). Hugh On Feb 22, 2012, at 8:57 AM, Marc Carter wrote: Hi, all -- I fear this to be a really stupid question, but... In ANOVA, why are the squared deviations in the SS between groups scaled (multiplied) by _n_? I was once told it was to weight them, but that somehow doesn't seem right. Can someone help? TIA, marc The information contained in this e-mail and any attachments thereto (e-mail) is sent by Baker University (BU) and is intended to be confidential and for the use of only the individual or entity named above. The information may be protected by federal and state privacy and disclosures acts or other legal rules. If the reader of this message is not the intended recipient, you are notified that retention, dissemination, distribution or copying of this e-mail is strictly prohibited. If you have received this e-mail in error please immediately notify Baker University by email reply and immediately and permanently delete this e-mail message and any attachments thereto. Thank you. --- You are currently subscribed to tips as: hfo...@skidmore.edu. To unsubscribe click here: http://fsulist.frostburg.edu/u?id=13238.0e762b65028402721e10bbc97ede52b7n=Tl=tipso=16204 or send a blank email to leave-16204-13238.0e762b65028402721e10bbc97ede5...@fsulist.frostburg.edu --- You are currently subscribed to tips as: arch...@jab.org. To unsubscribe click here: http://fsulist.frostburg.edu/u?id=13090.68da6e6e5325aa33287ff385b70df5d5n=Tl=tipso=16207 or send a blank email to leave-16207-13090.68da6e6e5325aa33287ff385b70df...@fsulist.frostburg.edu
Re: [tips] Finding the appropriate inferential test
Well, the range may be small (focus on ANOVA and correlation/regression), but I've got cumulative final exams on my web pages that could serve this function (at least for those tests). http://www.skidmore.edu/~hfoley/course.htm Both PS 306 (Experimental) and PS 217 (Intro Stats) would work…and then there's the PS 318 (Adv stats) course with a focus on the Keppel Wickens text…but with problems from other sources. In my stats/experimental courses, I've been trying to construct problems based on recent publications (largely from APS journals). Hugh On Dec 8, 2011, at 11:40 PM, Rick Froman wrote: Thank you, Jim. It is an Intro Stats class and those are exactly the kinds of problems they would need to practice. Rick Dr. Rick Froman, Chair Division of Humanities and Social Sciences John Brown University Siloam Springs, AR 72761 rfro...@jbu.edu From: Jim Clark [j.cl...@uwinnipeg.ca] Sent: Thursday, December 08, 2011 9:16 PM To: Teaching in the Psychological Sciences (TIPS) Subject: Re: [tips] Finding the appropriate inferential test Hi You don't mention what tests you want students to practice, but I have some small sets of review problems for intro stats (binomial / sign test, various t-tests, ANOVA, regression, chi2) at: http://ion.uwinnipeg.ca/~clark/teach/2101/ The reviews are zReview_#.pdf, where # is 1, 2, or 3. The 2nd page shows the answers, but you could post just the question parts if you preferred. There is a decision tree there as well at: http://ion.uwinnipeg.ca/~clark/teach/2101/decisiontree3.pdf If people have more sites, I too would be interested in hearing about them. Take care Jim James M. Clark Professor of Psychology 204-786-9757 204-774-4134 Fax j.cl...@uwinnipeg.ca Rick Froman rfro...@jbu.edu 08-Dec-11 8:59:24 PM Does anyone know of any sites on the web that would provide students with scenarios on which they could practice their skills in selecting an appropriate inferential test? Rick Dr. Rick Froman, Chair Division of Humanities and Social Sciences John Brown University Siloam Springs, AR 72761 rfro...@jbu.edumailto:rfro...@jbu.edu --- You are currently subscribed to tips as: j.cl...@uwinnipeg.ca. To unsubscribe click here: http://fsulist.frostburg.edu/u?id=13251.645f86b5cec4da0a56ffea7a891720c9n=Tl=tipso=14782 or send a blank email to leave-14782-13251.645f86b5cec4da0a56ffea7a89172...@fsulist.frostburg.edu --- You are currently subscribed to tips as: rfro...@jbu.edu. To unsubscribe click here: http://fsulist.frostburg.edu/u?id=13039.37a56d458b5e856d05bcfb3322db5f8an=Tl=tipso=14783 or send a blank email to leave-14783-13039.37a56d458b5e856d05bcfb3322db5...@fsulist.frostburg.edu --- You are currently subscribed to tips as: hfo...@skidmore.edu. To unsubscribe click here: http://fsulist.frostburg.edu/u?id=13238.0e762b65028402721e10bbc97ede52b7n=Tl=tipso=14784 or send a blank email to leave-14784-13238.0e762b65028402721e10bbc97ede5...@fsulist.frostburg.edu -- Hugh J. Foley Department of Psychology Skidmore College Saratoga Springs, NY 12866 518-580-5308 http://www.skidmore.edu/~hfoley -- And I still don't know if I'm a falcon, a storm, or an unfinished song. Rilke -- --- You are currently subscribed to tips as: arch...@jab.org. To unsubscribe click here: http://fsulist.frostburg.edu/u?id=13090.68da6e6e5325aa33287ff385b70df5d5n=Tl=tipso=14802 or send a blank email to leave-14802-13090.68da6e6e5325aa33287ff385b70df...@fsulist.frostburg.edu
Re: [tips] Looking for new activity ideas for a course on experimental design
Hi Michelle! You may find some of the info on my Advanced Stats web page (supporting the Keppel Wickens text) to be useful…especially the lab exercises: http://www.skidmore.edu/%7Ehfoley/PS318.htm For data collection/analyses, my Experimental Psychology course would be more useful. Each semester, we have a correlation/regression study, a single factor study, and a two factor study. However, I don't keep those studies up on the web page. I can easily send you the materials for a study on biased eyewitness identification (based on materials available at Roy Malpass's site). Another fun lab was based on hindsight bias and anagram solutions, but requires SuperLab. We've also made use of the Ole Miss site: http://psychexps.olemiss.edu/ I could also send you a list of many of the studies we've used in that class over the past years. Hugh On Nov 18, 2011, at 1:00 PM, Michelle Everson wrote: Hi Everyone, I was hoping to get some new activity ideas for a course I teach on experimental design. This course tends to be on the small side (i.e., perhaps around 20 students, give or take). In the course, students learn about different kinds of designs and also about the ways they would analyze data from these designs. We focus on between-subjects designs, within-subjects designs, and mixed designs (where we use ANOVA) and we also get into multiple regression and analysis of covariance. We use SPSS as our statistical software package. Although the class is small, I like, whenever possible, to involve my students in activities where they can better understand each design. I like to be able to gather some data from the class that might work to illustrate each different design. This isn't always feasible given the small sample size I have, of course. I know there are sometimes good instructor guides that go along with different books (particularly research methods books) that might have activities that are meant to illustrate different designs. Does anyone happen to have some ideas of good class activities I might be able to use, or resources I might check out? Thanks so much for your time and help! Michelle -- Michelle Everson, Ph.D. Quantitative Methods in Education Department of Educational Psychology University of Minnesota gaddy...@umn.edumailto:gaddy...@umn.edu --- You are currently subscribed to tips as: hfo...@skidmore.edumailto:hfo...@skidmore.edu. To unsubscribe click here: http://fsulist.frostburg.edu/u?id=13238.0e762b65028402721e10bbc97ede52b7n=Tl=tipso=14260 (It may be necessary to cut and paste the above URL if the line is broken) or send a blank email to leave-14260-13238.0e762b65028402721e10bbc97ede5...@fsulist.frostburg.edumailto:leave-14260-13238.0e762b65028402721e10bbc97ede5...@fsulist.frostburg.edu -- Hugh J. Foley Department of Psychology Skidmore College Saratoga Springs, NY 12866 518-580-5308 http://www.skidmore.edu/~hfoley -- And I still don't know if I'm a falcon, a storm, or an unfinished song. Rilke -- --- You are currently subscribed to tips as: arch...@jab.org. To unsubscribe click here: http://fsulist.frostburg.edu/u?id=13090.68da6e6e5325aa33287ff385b70df5d5n=Tl=tipso=14263 or send a blank email to leave-14263-13090.68da6e6e5325aa33287ff385b70df...@fsulist.frostburg.edu