But the plans were on display . . .”
“On display? I eventually had to go down to the cellar to find them.”
“That’s the display department.”
“With a torch.”
“Ah, well the lights had probably gone.”
“So had the stairs.”
“But look, you found the notice, didn’t you?”
“Yes,” said Arthur, “yes I did. It was on display in the bottom of a locked filing cabinet stuck in a disused lavatory with a sign on the door saying Beware of the Leopard.”
– Hitchhiker’s Guide to the Galaxy, by Douglas Adams
Last night, I was trying to find the LIBNAME statement for my course so I could upload data to be used by the class with SAS On-Demand. Here is where you find it.
Go to your sodareg (the SAS On-Demand for Academics Registration page)
Which my Safari hates and refuses to open, by the way, so I just did it in Chrome. When you log in, next to the course name you will see a link that says info and above that link is a note that this is where you get information about your course setup, including instructions for storing data on the server.
You might think that is perfectly obvious and you would read it. Actually, given that 7,500 people on April Fools Day clicked on a user contract that gave GameStation the right to their immortal soul, including agreeing that GameStation could serve notice to hand over one’s immortal soul in six (6) foot high letters of fire, I think it is safe to conclude that most people completely ignore user agreements and don’t read instructions.
So, am I going to change my behavior in this regard? Well, since most “info” from manufacturers includes information like that I should not iron my clothes while wearing them or that I agree not to sue them even if the box contains a clan of badgers instead of the software I ordered and said badger clan leaps out of the box and chews off my fingers because, well, I should have been prepared for such contingency with badger repellent handy and it’s all my own fault, really – so, no –
– unless it comes from SAS On-Demand, in which case, I might.
Oh, by the way on another random note, if you are looking for your site number, which I don’t think you really need for SAS On-Demand but the tech support form requires it, in SAS Enterprise Guide, go into the help menu and select About SAS Enterprise Guide and a menu will pop up with your site number.
If you had SAS On-Demand for Academics installed last year and you want to continue using it in the new academic year, you need to uninstall your previous version and install the new version.
You can find more details here – http://support.sas.com/ondemand/SAS93.html
Okay, so I uninstalled the previous version of Enterprise Guide no problem. The SAS Enterprise Miner uninstall seemed to have a glitch but since I am not using that for this class I am ignoring it for now and moving on.
to this page http://support.sas.com/ondemand/eg93.html
which tells me that the new version is available
I clicked on this link http://support.sas.com/ondemand/manuals/enterprise_guide_instructor.pdf
and followed the instructions, starting with registering a course, since I already had a SAS profile. Your same email and password that you had before still works, if you had previously used SAS On-Demand.
I have three computers in my office – a Mac desktop that runs boot camp, a Mac laptop and a Windows desktop. After I had registered the course and downloaded the software on one computer, I could just go back to log in here
and download it on the other two. It does ask you to log in twice, which is a little weird. Don’t worry that you are stuck in a loop when it asks you to log in the second time. Just do it and you should be taken to a page where you can click on the download button and start your download
I didn’t have any real problems except for this, which SAS tells you on the website might happen. It even has the font in red in the vain hope (in my case, anyway) that you will notice it before you start cursing them.
Note: If Microsoft .NET Framework must be installed, it might appear as if no progress is being made or that your system has stopped processing. Please be patient while the installation progresses.
The only little glitch that occurred was as sometimes happens with SAS, the pop-up window actually popped down and it was behind my browser. If nothing seems to be happening for a while, try minimizing your browser and seeing if there is a window behind there asking if you want to install SAS.
Also, Windows will almost certainly pop up after that with a window asking you to enter your password since something is trying to mess with your system. After that, it should be a simple matter of clicking next on the bottom right of each screen to accept the defaults and there you are.
I ran it through its paces a bit. The SASHELP files I use during the first class were still there. I made this 3-D graph for no reason.
I was suspicious they might have done something with the ability to analyze data you upload to the server yourself. Nope.
Only instructors can upload data to the class directory and here is how to do it.
I used Filezilla. Feel free to use whatever you want.
Your host should be sascloudftp.sas.com You enter your username and password
Here is where I ran into my first problem. The upload seemed to work fine. My ftp program showed the file in the saslib directory. Unfortunately, the saslib directory never showed up in my project. I tried logging on and off, tried different computers. Nope. The documentation shows a LIBNAME example with two blank spaces. The first one is easy enough. When you ftp with your credentials you will see the directory c_#### and that is what goes in the second blank space. What the HELL goes in the first blank space is beyond me. I guessed it was the university name and tried all sorts of variations. I checked my university email and even my company email to see if I was emailed the super-secret password. Nope.
It is 10:30 pm so I don’t suppose there is anyone I can call and find out.
My tip then is that overall SAS On-demand downloads easily, works fine, imports Excel files, is a little slow for in-class demos but not terrible BUT if you are planning on uploading data to use for class, I would not leave it until the night before your class.
UPDATE: Here is where to find your LIBNAME statement, and also your site number if for some random reason (like filling out a tech support form) you want that. And also a picture of a badger.
Propensity score matching has had a huge rise in popularity over the past few years. That isn’t a terrible thing, but in my not so humble opinion, many people are jumping on the bandwagon without thinking through if this is what they really need to do.
The idea is quite simple – you have two groups which are non-equivalent, say, people who attend a support group to quit being douchebags and people who don’t. At the end of the group term, you want to test for a decline in douchebaggery.
However, you believe that that people who don’t attend the groups are likely different from those who do in the first place, bigger douchebags, younger, and, it goes without saying, more likely to be male.
The very, very important key phrase in that sentence is YOU BELIEVE.
Before you ever do a propensity score matching program you should test that belief and see if your groups really ARE different. If not, you can stop right now. You’d think doing a few ANOVAs, t-tests or cross-tabs in advance would be common sense. Let me tell you something, common sense suffers from false advertising. It’s not common at all.
Even if there are differences between the groups, it may not matter unless it is related to your dependent variable, in this case, the Unreliable Measure of Douchebaggedness.
Say, for example, that you find that your subjects in the support group are more likely to eat grapefruits for breakfast, live on even-numbered streets and own a parrot. Even though I’d be a little suspicious of anyone who gets up early enough to eat breakfast, if it turns out that none of those variables are related to how big of douchebag you are, there is no point in doing a propensity score match.
Finally, and perhaps most obvious and most frequently overlooked, if your dependent variable is not measured reliably, no amount of statistical hocus-pocus is going to make anything predict it. (Short explanation – an unreliable measure is one that has a large proportion of error variance. Error variance is, by definition, random. Random error is not going to be related to anything. Imagine that every student just colored in the bubbles in the test at random. Now imagine trying to predict the test scores with any variable. Not happening. I think all students SHOULD color in the test sheets at random. I did once. The school psychologist told me I was mentally retarded. She was wrong.)
and AFTER you do propensity score matching (or anything else) …
Even after all of this, sometimes it still doesn’t work. A few years ago, I had a client who had a really logical theory, well-designed study and when we ran the analyses every which way, none of the data supported their hypotheses.
At the end of it all, the client asked me what else we could do, and I said
“There isn’t anything else we can do that I would recommend. You know, sometimes the theory is just wrong.”
It reminds me of the title of a good presentation I went to at the Joint Statistical Meetings earlier this month,
“Bayesian statistics are powerful but they’re not magical”
I think that could be applied to just about any kind of statistical technique. I wish I had said it first.
As statisticians, we like to say that statistics is everywhere. Here is an example. Regular readers of this blog might know that my darling daughter number three is the world champion in mixed martial arts. There is a very wide gap in the general discourse at mixed martial arts events and, say, the Joint Statistical Meetings, or SAS Global Forum.
A few days before her fight, a fighter from the UFC was arrested for vandalizing a church while naked. Do not ask me why. This is not a why question.
Some people have been put off by my daughter’s very forthright manner of speaking and compared her to some of the fighters in the UFC. So, what was my daughter doing during that week?
Actually, she was making weight running up to her defense of her world title, and, as she did the last time, running a contest to raise money for the World Food Programme. There is a site called freerice.com where for every correct answer you get the sponsor donates 10 grains of rice to WFP. Ronda asked her fans to play as a group. So far, they have donated over 30,000,000 grains of rice which at 3,400 grains per bowl is enough to feed over 8,800 people.
People who donated over 1,000,000 grains all got a prize. The top two donors got personalized TOPPS trading cards with Ronda’s signature. Since there are a total of two of those cards in existence they should be worth some money.
What about all of the other people, though? How do you keep people who only have time to play the game a little motivated while rewarding those who play a lot?
Enter PROC SURVEYSELECT and the SIZE statement.
Here is how you select a sample proportional to size.
First, I downloaded the file that had all of the donors. It is a csv file. Then, I just from the SAS FILE menu selected IMPORT DATA, dragged down to select csv as the type and opened my file.
Here is the program
*** This deletes people who did not donate any rice, and also
*** Those who donated > 1,000,000 grains, since those people already are guaranteed a prize
*** It also breaks them into 3 groups - High N=7, Middle N = 12 and low N=188 ;
data winners ;
set rice ;
if grains_in_group > 1000000 or grains_in_group = 0 then delete ;
else if grains_in_group > 100000 then donate = "high" ;
else if grains_in_group > 20000 then donate = "mid" ;
else donate = "low" ;
*** This just does the frequency by group to check all is well *** ;
proc freq data = winners ;
tables donate ;
*** The documentation says you need to sort by the strata variable **
*** Although I tried it without sorting, too, because I am just like that
*** And it still works. Maybe SAS loves me ;
proc sort data = winners ;
by donate ;
*** The method = PPS requests sample with probability proportional to size
*** and without replacement. N = (2 1 3) will select 2 from high, 3 from mid and 1 from low.
proc surveyselect data = winners method = pps n=(2 1 3) out = selected;
size grains_in_group ;
strata donate ;
Two things to note
1. When you do the N=( 2 1 3) — the numbers are assigned in order of how they are sorted, so it is not high, middle, low. In alphabetical order, it is sorted high, low, middle. So the 7 people who donated between 100,000 and 999,999 grains of rice had a 1 in 3.5 chance of being selected. The people who donated 20,000 to 99,999 had a 1 in 4 chance of being selected and the people who donated less than 20,000 had a 1 in 188 chance.
2. I could have left off the SIZE statement and done a simple random sample stratified by donate. If I did that, the people who were in the highest donor group would have more chance of winning than in the middle donor or low donor group but within group, the person who donated 10,000 grains would have no more chance than the person who donated 10. I didn’t think that was fair. In fact, when I compared the two methods, pps and srs with strata by group, by running the program several times after I had already selected the winners, just to see what would happen, on the average there was a difference of 30,000 – 50,000 grains in the amount donated using the proportional to size method with the stratified random sample.
So, thanks to all the people who donated. Hurray for Ronda for doing something good while she’s starving to make weight.
And hurray to SAS for making it so easy to select people fairly.
As for the fight, Ronda won it in 54 seconds. She keeps the belt (and yes that is REAL gold). The only one who has been able to take the belt from her so far has been her 4-year-old niece, but she cheated. She used cuteness.
Also, even though the fight is over, you can still join the group and donate. It’s a good cause, because, to quote Ronda, “It sucks to be hungry.”
I’m not really swearing in the title of this post because I am not so much angry as sad. I have been reviewing grant proposals recently. Generally, I hate reviewing proposals because the pay is minimal relative to the time you put in, there are usually a lot to be read in a short time, and it adds up to a couple thousand pages. I do it anyway, kind of like having to be the Brownie Troop Leader at least once if you have four daughters. If you write a lot of grants, it’s kind of obligatory to review them.
So … I am reading this grant and it is all about a wonderful program to teach students science, technology, engineering and mathematics (STEM). There are going to be all sorts of resources, they are going to offer these amazing courses, it is based on the latest educational research, students will be doing cutting edge science. I am getting all excited and proud of my country just reading it. What a great program! What terrific curriculum! What fabulous technology.
and then, I realize ….
This isn’t a new program.
This is a renewal application.
I have BEEN to this program.
And it is nothing like that.
The sites each have maybe one relatively new computer that works. If they have any other computers at all, they are ancient. The staff turns over every six months or so. Every time I go there it is new people. Very little of the training stated in the proposal occurs.
I was a speaker at one of the training sessions they did have, many years ago. One of the staff members fell asleep. Afterwards, one of the other employees said to me,
“Your training was interesting. It’s not you. She’s just on drugs. She falls asleep at work all of the time.”
The students who are supposedly learning programming and taking courses in advanced science and mathematics are, on the average, reading and doing mathematics two to four years below their grade level. Not only are they not taking the courses described in the proposal, I didn’t even know they were supposed to be learning anything like that until I read the proposal.
Basically, the students get help with their homework sometimes and do some social activities. That is not terrible, but it is NOTHING like what was described. So much so that I did not even realize it was the same program at first. I thought it was just another program with the same name.
So …. did I say something in the review panel? No, because the proposal was pulled from our panel due to a conflict of interest – one of the other reviewers had been an employee or consultant of theirs – so it went to some other group who will review this fictitious program and probably give it funding. I would have – if it really existed.
As I said, I’m not angry so much as disappointed.
The Rocket Scientist and I just had our first martini in days. Actually, one of us (cough * me * cough) is not a big drinker, but still … Alcohol is against tribal law and I do believe in respecting the customs anywhere I am visiting. If I can’t respect your customs, I won’t go there.
After being up until the not-so-wee hours of the morning fixing every last bug we could find and adding every last feature we could think of, we did our live demo for the teachers at Tate Topa Tribal School today (thank you!!!) and headed the 25 mile round trip into the nearest town where we could buy a drink to celebrate.
Then there is the fact that different browsers recognize different video formats making it necessary to upload three different versions of each video clip.
Every time we got something fixed, we just got further along in the game until it quit working. This is called progress.
After we met with two of our cultural experts (thank you to Dr. Erich Longie and Lorraine Greybear !!) we made a bunch of changes. Then, we took down pages of suggestions from the teachers today that will take up the next two months.
Different colors to make the path stand out. Different background to make instructions easier to read. Better graphics when the students get answers right. More, new and different music. More sounds.
I am tired just thinking about it. We will put up a link to some samples in a week or two once we have made some more progress.
Hurray for us. We got it working. And it didn’t suck.
Yesterday, I posted how to get SPSS Integration Technologies with Python working on the Mac.
Today, I received this certificate of appreciation from one of my blog readers.
I’m including this in my performance review. Oh wait, I don’t get performance reviews, I’m the president.
Now that I have my certificate in getting the damn thing working, next I am going for my undergraduate degree in Getting the Damn Thing Working, eventually progressing to my Ph.D. in Getting the Damn Thing Working Studies.
Anyway, I just think this is the type of appreciation readers of this blog ought to be showing. So, thank you, Ernie.
So, I did it. I finally got the SPSS Python Integration modules to work on the Mac. There should be angels singing and certificates of achievement handed to me personally by at least four of the twelve apostles.
At the very least, I should get a prize.
Almost six months ago, I wrote a post on 1,000 ways not to get SPSS FUZZY to work.
Okay, let’s back up here a few steps … SPSS for some time now has not really been developing the syntax very much and instead offering the capability for free (not counting the $1,699 cost of SPSS) to extend SPSS with Python or R.
Actually, if you are at a university, you can usually get an SPSS license for almost every product for $250 a year or less (sometimes much, much less depending on the deal your campus has). So you have the pointy-clicky interface and you can extend it with other programming languages as well.
Also, SPSS runs native on the Mac which not everything (cough – SAS – cough) does.
Most times, doing something on the Mac is quite a bit simpler than doing things on Windows. This is not one of those times.
Here is how to get it to work:
1. Install SPSS – I happen to be using SPSS 20
2. Download the Python plugin
3. Install the plugin. It should be pretty obvious. You double-click on the file you downloaded, which is a disk image. It opens up, you double-click on the icon that says IBM Statistics Essentials for Python, click through a few windows – it assumes your SPSS is installed in the default location
and so is Python27
If you have a Mac, Python was probably installed when you got it and in that location.
4. Now, you try SPSS and go to UTILITIES > EXTENSION BUNDLES > VIEW INSTALLED EXTENSION BUNDLES and it shows you have the modules installed but when you try running a program you get an error message that says there is no such module.
Your problem is that your modules are installed in the wrong place. Even worse, because they are installed in a hidden directory, searching won’t even find them.
Here is how to find out if this is your problem and how to fix it.
5. Go to where you have SPSS installed, hold down the control key and click. You should see a drop down menu like this. Select SHOW PACKAGE CONTENTS
When you open the Contents folder, you’ll see a bunch of other folders. One of them is named Extensions. When you look at this, you can see right away what the problem is. That extensions folder is empty. That is where your modules are supposed to be. So, where are they?
To find them, click on your hard drive – mine is named Alice because I like Alice in Wonderland. You should see folders that say Application, Library, Users and maybe a few others. Click on the Library folder.
Open the Application Support Folder
Open the folder IBM
Open the folder SPSS
Open the folder Statistics
Open the folder 20
NOW …. you see Extensions
Open that folder. Copy everything in it.
Go back to the empty Extensions folder in the SPSS Contents folder
Paste everything into it.
Everything now works.
I hate Buffy the Vampire Slayer and the entire Twilight Series. This came about over the course of a week when my daughter had strep throat and was watching approximately 4,789,362 episodes of vampire shows in the living room, which is just down the hall from my office. Thus, when Brenda Osuna from USC asked me to be a discussant on a panel of researchers involved in statistical analysis comparing viewers of Buffy the Vampire Slayer and Twilight, my first thought, and this is verbatim, was
“That has got to be the dumbest idea I have ever heard.”
However, I want to inform you of two things. First, as much as we statisticians love to quote the Washington Post article that said statistics is the next sexy profession, my older daughters mocked that greatly. Here they are trying to emphasize the lack of sexiness of the statistics profession.
And even though I truly do hate Buffy, Bella and anything else vampire-related, when I told my youngest daughter there I was going to be gone to a statistics conference, she groaned “Boring!” but then when I told her that I was going to be on a panel on Buffy the Vampire Slayer and Twilight, she immediately perked up and said, “What did they find out?”
This is relevant because the middle child in front of the blue M & M has been in every advanced math class since the age they started offering advanced classes in middle school, tested a year above average in math and just received a scholarship to a top prep school. The one showing her pierced navel in the top photo attended a science magnet and whipped through all of her high school math problems like someone doing speed reading. These are the kind of people we want in statistics. They are prime candidates.
Throughout this week at the conference we have heard repeatedly about the need to stoke the pipeline that there is an unmet need for statisticians, particularly domestic statisticians. We are filling our graduate programs with international students and that is going to cause a severe shortage down the line. Some areas, for example anything with a high security clearance, require citizenship.
For crying out loud, STUDENT isn’t an occupation we should be out-sourcing in this country!! What the hell is wrong with people who don’t get this??
Most of the “solutions” I hear for the inability to fill graduate – and even undergraduate – programs with our own students push the problem down the road.
We need to start in high school to get kids interested in statistics so they major in math and then go on into our graduate programs. BUT …. If they are going to major in math, they need to do better in high school, so let’s intervene in middle school, no, elementary school, heck, let’s go back to birth!
We’ll all be old(er) and retired by the time these “solutions” work – or more likely, don’t work, since they have not worked in the past 25 years that I have been hearing them, and as all good statisticians know, the best predictor of future behavior is past behavior (apologies to Taleb aside) .
I recommend we just stop fooling ourselves. Stop the bullshit. The only thing we really have control over are the graduate and sometimes undergraduate students that we teach. I get really tired of solutions that address every part of producing future statisticians except for the part that we ourselves control.
I was unpleasantly unsurprised when I spoke to some employers at JSM about students I knew were soon graduating who had 12-20 credit hours in statistics but did NOT have degrees in mathematics or statistics. The response I got was,
“We-ell. We might consider them if they don’t have a mathematics degree, but I don’t know.”
What. The. Fuck? Are you really that fucking stupid?
Why on earth are we writing them off? If you want to get good people, do it the American way – steal them from other people! When a company needs new engineers, managers or computer programmers they don’t wait for someone to give birth to them, they go out and hire them away from other people. When there was a shortage of computer programmers in the 1970s we hired away anyone who could program a computer without waiting for them to finish graduate school or sometimes even their undergrad degree.
So, let me get this straight — instead of taking someone who already has a bachelors or masters degree, who obviously has some motivation and academic ability, who has all of the core courses completed and more statistics courses than many majors, who has programming experience with real data, who has published papers and presented at conferences quantitative research – your plan is to encourage kids in high school to major in statistics? That’s what you’ve got? Seriously?
How many people, when they were little said,
“When I grow up, I want to be a statistician?”
“Was this your Plan A?”
Why on earth, then, do we demand that of our students?
Cynthia, the first speaker on the panel, originally began with a qualitative study of vampire media. One quote from her paper stood out.
“Clearly, combining good looks, rebellious power, and elusive sexuality can be a path to success in reaching a young adult audience” (Robillard, 2009).
I confess, on reading it, my thought was
“Ick. I hate this crap. How is this academic?”
And yet ….. when we teach statistics there are tons of examples on baseball statistics, yards run in football, and I have ZERO interest in that.
(So much so that last night when we were sitting at the UFC fights in the front row and the very nice man next to me, when I asked if he was a fighter said with some surprise,
No, I played football for 15 years. I retired after my team won the Superbowl and went into television.
I told him that I didn’t really watch TV or football but I had at least heard of the Superbowl so he must be very good if even I had heard of it. For some reason, both he and my daughter found that hilarious. Hmph.
Anyway, my point is that if we can use sports statistics to try to make statistics more relevant to students, why not statistics on vampire shows. If you add up the revenue from all the vampire books and TV shows, I don’t know if it rivals baseball but it sure is not a trivial market. According to Statistics Brain, the Twilight Series franchise alone is closing on $5 billion – yeah, that’s billion with a B.
So …. the first paper on the panel was the senior statistical consultant who oversaw the whole project. The second was a qualitative researcher (Cynthia) who then shifted to a quantitative study. Yes, she is a beginning quantitative researcher, and in her paper she discussed many of the mistakes she made, false starts and what she learned – the need for random sampling, better designed questions, changing data from unstructured to structured so it could be analyzed, potential bias, overlapping populations, categorical data analysis. It was a quite impressive list. Is she even a junior statistician yet? No. However, what she IS, is much more interested in statistical analysis than she was before and full of ideas for how to revise her research and extend it in the future. She certainly has far more potential to become a statistician than the average high school student or undergraduate statistics major because she already has learned a lot of very useful information for anyone who is going to work in the field.
This is really not rocket science – if you want to get a more diverse group of students, you need to study more diverse topics and recruit and train those students in diverse ways.
I think we’ve been really stupid in the U.S. in mathematics and statistics departments. According to Dr. Suresh of the National Science Foundation, in 2007, less than one-third of engineering Ph.D.’s GRANTED BY AMERICAN UNIVERSITIES went to American citizens as did less than half of Ph.D.’s in the physical sciences. He did not give specific percentages for statistics or mathematics but you don’t have to go to many conferences to see that we have been filling up our programs with international students.
Rather than changing our programs to attract and retain students from the U.S. , we’re keeping our programs the same and recruiting students from thousands of miles away. You can talk all day long about how that is a good thing because we’re so great, we’re attracting a global audience, globalization is a good thing, etc. etc. One of my colleagues told me that the answer was obvious, look at the international students coming in and how hard they work, American students are entitled.
That is COMPLETE bullshit.
I teach students who work an eight-hour day, then come take classes for six hours in the evening, in things like Advanced Quantitative Data Analysis, where they learn SAS programming along with inferential statistics. Does that sound lazy and entitled to you? I’m not saying there aren’t lazy, entitled students in the U.S. I am saying I very seldom see any in the graduate program where I teach.
What I do see is students who are challenging and questioning, who are reluctant to spend four years or eight years studying theoretical distributions and trying to create some new statistic that is a trivial improvement over the prior methods. I see students who want to study and research topics that interest them. That is not a bad thing. In fact, that is what I love about my work, is that I DO get to address fascinating problems every day. So, Brenda is right – we should recruit intelligent, articulate, hard-working graduate students from other fields into statistics as another optional path.
But I still really hate Buffy. And Ella. And any other vampire-related person or thing.
Kirk Anderson recently mentioned a new course on the American Statistical Association Statistical Education group, Statistics in the Media
“The focus will be on how statistics are reported in the media. Students will be asked to read news stories and critically evaluate the conclusions made, recognizing when assertions are and are not supported by evidence. “
Unfortunately, I couldn’t help with his request for a recommended textbook – I teach doctoral students who need to conduct their own research – but I think the concept of such a course for undergraduates is brilliant.
Statistics is everywhere and applied in every setting. In the vast majority of universities, though, we teach introductory statistics as if everyone was going to become a statistician. Imagine if instead of teaching students how to use Office or OpenOffice, every student was required to take a course that covered regular expressions, functions and local and global name space (those concepts are fundamental, right?)
Almost no one would use computers and there would be a huge shortage of people who could run anything on a spreadsheet.
My only suggestion for improvement would be that instead of “an algebra-based introductory statistics pre-requisite” that they are planning, I’d teach one course (maybe for more credits) that included the introductory statistics, rather than have it as a separate course.
So, 10 brownie points and a cookie for Grand Valley State University in Michigan for innovation in statistics education. (Admit it, now you’re hungry.)
Shameless plug: For another take on a different view on statistics education, you can go to the session, Interview with the Vampire Researcher at the Hilton Bayfront, Sapphire D from 10:30 – noon on Thursday, August 2, part of the Joint Statistical Meetings in San Diego