Monday, October 27, 2008

The economics of stable marriages

I've been studying matching models, a branch of game theory that explores what happens when groups have to figure out how to pair off. These kinds of dynamics in job markets for freshly minted professionals, post-season bowl games, and most famously, marriage.

Here's the abstract from Bergstrom and Bagnoli, "Courtship as a Waiting Game." It cracks me up.
In most times and places, women on average marry older men. We propose a partial explanation for this difference and for why it is diminishing. In a society in which the economic roles of males are more varied than the roles of females, the relative desirability of females as marriage partners may become evident at an earlier age than is the case for males. We study an equilibrium model in which the males who regard their prospects as unusually good choose to wait until their economic success is revealed before choosing a bride. In equilibrium, the most desirable young females choose successful older males. Young males who believe that time will not treat them kindly will offer to marry at a young age. Although they are aware that young males available for marriage are no bargain, the less desirable young females will be offered no better option than the lottery presented by marrying a young male. We show the existence of equilibrium for models of this type and explore the properties of equilibrium.
For a guy who's been happily married since 22, it's an unflattering picture. Of course, five years later I'm still making close to $0 annually, so maybe that's time not "treating me kindly."

Tuesday, October 7, 2008

It's like the SAT for Supreme Court justices...

Here's a nifty data thing.  Check out the Martin-Quinn scores for Supreme Court justice at http://mqscores.wustl.edu/.   This is a nifty application of a branch of statistics called item-response theory, which is most often used for designing standardized tests.  Just like the SAT designers peg students' "aptitude" from high to low based on their responses to questions, Martin and Quinn have pegged each justice on an ideological scale using their votes on various cases.

The Martin -Quinn site has a nice little graph showing all the justices and their ideological points over time.  (You can't miss it.  It animates over and over and over.)  Bonus points if you can name the Nixon appointee who trends way liberal in the 60's and 70's!

Data is downloadable, just in case you wanted 80 years of data about Supreme Court ideology.

Thursday, October 2, 2008

Hiatus

So the semester has started up again, bringing ~400 pages of polisci reading a week. We're three weeks in, with 10 to go before the break. Here's my strategy for keeping an interesting blog up and running for the duration:

First, I've added a widget that lets me share items of interest from my RSS reader. (It's down on the right.) (In garish green.) These posts will be the creme de la creme of the dozens of feeds I try to keep an eye on. Anything in here is, IMHO worth a look.

Second, I'm going to loosen the topical boundaries of this blog past education policy. For the time being, that probably means a political science take on American government, since that's what I'm immersed in. I will continue to lean quantitative, so look for lots of data, game theory, and nifty statistics.

Finally, this is the end of editing. Most of these posts will be dashed off, spellchecked once (not twice) and sent.

yoroshiku

Wednesday, August 20, 2008

Does exposure to lead cause crime?

While driving to change the oil in my car yesterday, I listened to Philip and Alice Shabecoff discuss their book Poisoned Profits: The Toxic Assault on Our Children on the Diane Rehm show.

I haven't read it (don't plan to), but if the title and the interview are any indication, the book is polemic. The Shabecoffs have concluded, based on some vague anecdotal and correlational research, that a whole bunch of chemicals are toxic and should be banned.

Don't get me wrong -- I'm not a big fan of dumping/consuming random chemicals. But I'm also wary of beating up corporations just because they're easy political targets. And the evidence here is ... shaky. The problem is a statistical classic: correlation does not imply causation.

Case in point: a recent study on the effect of childhood lead exposure on adult criminal activity. The researchers targeted pregnant mothers in high-lead areas, took detailed readings of lead levels for the mothers and (later) their children, and then looked at the criminal histories of those children once they reached adulthood. They concluded that a little lead as a child makes a person much more likely to be arrested later in life.

The problem: which children are most likely to grow up in the homes with the worst lead problems? Those with the most impoverished, disadvantaged (and least health-conscious) parents. So when the researchers look at the correlation between lead exposure and arrests, it's impossible to tell whether lead or poverty is the real cause of crime.

So the study, like so many others is inconclusive. What do you think the standard of evidence for concluding that a chemical is harmful should be?

Monday, August 18, 2008

Michelle Rhee's merit pay plan: Out of control

Until recently, merit pay for teachers was a debate about control. Those in favor (often business/economics types) argued that merit pay motivates teachers and improves achievement by "aligning incentives." Those opposed (including, notably, the teachers unions) argued that merit pay debases teachers by subjecting them further to uncaring administrators and biased tests.

Now there's a new wrinkle in the debate: Michelle Rhee, Teach for America alum and current chancellor of D.C. public schools, is proposing a voluntary merit pay system.

(Check out blog reactions at The Quick and the Ed and DC Teacher Chic. These, and most of the reactions I've seen online have been positive.) (Don't be surprised -- think about who blogs.)

I haven't sorted through the pros and cons of Rhee's proposal, so I can't tell you if it's good policy. But politically speaking, voluntary merit pay is a real innovation, because it breaks the status quo perception of merit pay as a power grab by district administrators. It's pretty hard to argue that a plan is about control when entry is voluntary.

Thursday, August 14, 2008

Rindskopf’s Rules for Statistical Consulting

(I stole this post wholesale from this site, mostly because I want to be able to find this text if I ever look for it again.)

Some of these rules are universal, while others apply only in particular situations: Informal academic consulting, formal academic consulting, or professional consulting. Hopefully the context will be apparent for each rule.

Communication with the Client:

(1) In the beginning, mostly (i) listen and (ii) ask questions that guide the discussion.

(2) Your biggest task is to get the client to discuss the research aims clearly; next is design, then measurement, and finally statistical analysis.

(3) Don’t give recommendations until you know what the problem is. Premature evaluation of a consulting situation is a nasty disease with unpleasant consequences.

(4) Don’t believe the client about what the problem is. Example: If the client starts by asking “How do I do a Hotelling’s T?” (or any other procedure), never believe (without strong evidence) that he/she really needs to do a Hotelling’s T.

Exception: If a person stops you in the hall and says “Have you got a minute?” and asks how to do Hotelling’s T, tell them and hope they’ll go away quickly and not be able to find you later. (I’ve had this happen, and if I ask enough questions I inevitably find that it’s the wrong test, answers the wrong question, and is for the wrong type of data.)

Adapting to the Client and His/Her Field

(5) Assess the client’s level of knowledge of measurement, research design, and statistics, and talk at an appropriate level. Make adjustments as you gain more information about your client.

(6) Sometimes the “best” or “right” statistical procedure isn’t really the best for a particular situation. The client may not be able to do a complicated analysis, or understand and write up the results correctly. Journals may reject papers with newer methods (I know it’s hard to believe, but it happens in many substantive journals). In these cases you have to be prepared to do more “traditional” analyses, or use methods that closely approximate the “right” ones. (Turning lemons into lemonade: Use this as an opportunity to write a tutorial for the best journal in their field. The next study can then use this method.) A similar perspective is represented in the report of the APA Task Force on Statistical Significance; see their report: Wilkinson, L., & APA Task Force on Statistical Inference. (1999). Statistical methods in psychology journals: Guidelines and explanations. American Psychologist, 54, 594-604.

Professionalism (and self-protection)

(7) If you MUST do the right (complicated) analysis, be prepared to do it, write a few tutorial paragraphs on it for the journal (and the client), and write up the results section.

(8) Your goal is to solve your client’s problems, not to criticize. You can gently note issues that might prevent you from giving as complete a solution as desired. Corollary: Your purpose is NOT to show how brilliant you are; keep your ego in check.

Time Estimation, Charging for Your Time, etc.

(9) If a person stops you in the hall and asks if you have a minute, make him/her stand on one leg while asking the question and listening to your answer. If they ask for five minutes, it’s really a half-hour they need (or more).

(10) Corollary: Don’t charge by the job unless you really know what you’re doing or are really desperate. Not only do people (including you) underestimate how long it will take, but (a la Parkinson’s Law) the job will expand to include everything that comes into the client’s mind as the job progresses. If you think you know enough, write down all of the tasks, estimate how much time each will take, and double it. Also let the client know that if they make changes they’ll pay extra (Examples: “Whoops, I left out some data; can you redo the analyses?”, or “Let’s try a crosstab by astrological sign, and favorite lotto number, and...”)

(11) Charge annoying people a higher hourly rate. If you don’t want to work for them at all, charge them twice your usual rate to discourage them from hiring you (at least if they do hire you, you’ll be rewarded well.)

Resources
http://www.amstat.org/sections/cnsl/index.html ASA section on consulting
http://www.amstat.org/sections/cnsl/BooksJournals.html Their guide to books and journals on statistics
Boen, J.R. and Zahn, D.A. (1982) The Human Side of Statistical Consulting, Lifetime Learning Publications.
Javier Cabrera and Andrew McDougall. (2002). Statistical Consulting. Springer-Verlag.
Janice Derr. (2000). Statistical Consulting: A Guide to Effective Communication.. Pacific Grove CA: Duxbury Press, 200 pages, ISBN:0-534-36228-1.
Christopher Chatfield (1988). Problem solving: A statistician's guide, Chapman & Hall.
Taplin R.H. (2003). Teaching statistical consulting before statistical methodology. Australian & New Zealand Journal of Statistics, Volume 45, Number 2, June 2003, 141-152. Contains a good reference list on statistical consulting.

Monday, August 11, 2008

50 Things New Teachers Need to Know...

This blog post is best slice-of-life I've seen into the world of teaching in a long time. The anonymous author strikes me as a pretty good teacher. His advice is practical, and also a little disillusioning. Did my teachers see themselves as mentors cum bureaucrats cum parole officers this way?

PS: I found this link here, at Joanne Jacobs' blog. For anyone interested in education, this is a blog worth keeping an eye on.

Thursday, August 7, 2008

Looking for a flashlight in the dark

Today, we bring you a true story...

Two years of looking for a flashlight in the dark: An astounding case study in government decision making

In 2006, the Michigan legislature passed the Michigan Merit Curriculum (MMC), a tough new set of high school graduation standards. Among other things, the standards called for every student to graduate with four years of math. Previously, students needed about three years to graduate.

Unintended consequence: in one blow, the MMC increased statewide demand for math teachers by a third. More math classes means more math teachers. Since math teachers were already in short supply and teacher accreditation (going through ed school, student teaching, etc.) usually takes years, this created a huge pipeline problem for Michigan's school systems. Apparently, nobody -- not the legislature, the Michigan Department of Education (MDE), or any of the research groups urging the curriculum change -- had thought through this part of implementation. MDE worried about it, but didn't have the capacity to really come to grips with the problem.

So after the legislation passed, MDE commissioned a study of "teacher supply and demand" from a group of policy students at U of M. I was one of the students, and -- I can say this now -- we never really understood what our task was. The research question was very broad and vague, so we did the study that seemed most interesting: an investigation of the distribution of "high quality" teachers across the state. We based our work on the registry of education personnel (REP), a statewide database that tracks all Michigan teachers. Our statistics were decent, but didn't speak directly to the question MDE needed answered. This turned out to be the first in a long sequence of research projects trying to figure out where the extra teachers would come from.

The next year, another U of M student group picked up where we had left off. They had somewhat better data and a clearer understanding of their goal, but were still overwhelmed. They arrived at one major conclusion: the REP doesn't contain the information necessary to answer the real questions about teacher supply and demand. The REP can only tell us about teachers currently teaching, not the pool of potential teachers. The team's recommendation was a statewide survey of building administrators to assess real needs.

At the same time, a research team at MSU was working on getting deeper into the REP to see what it *could* tell us. They came up with a set of three reports, gradually decoding the data structures of the REP. Major conclusion: Michigan has almost no reserve pool of practicing math teachers. Four out of five teachers currently teaching and certified to teach math are already teaching math. Again, the conclusion was that Michigan would need to bring in more math teachers from outside the pool of currently practicing teachers.

Bear in mind that all of this analysis so far has been based on the REP -- data that the state has collected routinely for years. Two years and five report later, MDE still doesn't know anything about potential teachers *not* captured in the REP.

By now it's 2008. The Merit Curriculum has been in place for two years and the first cohort of high school freshmen have gone through their first year of math. Newspapers are starting to run articles about failure rates. The most extreme claim that over 20% of high school freshman failed algebra I, the first class in the sequence. Editorial pages are running apocalyptic predictions about drop-out rates and missed graduations. The legislature is starting to discuss repealing MMC.

MDE is desperate to increase the number of competent certified math teachers, but still doesn't know where to look. The next school year starts within a month. The clock is ticking...

Moral of the story?
Beats me. "Reform is messy." / "Reform is hard." / "Reform takes time." "Unintended consequences dominate good intentions." ?

Tuesday, August 5, 2008

Externalities dominate...


Check out this NYTimes Freakonomics blogpost on the recent NBER paper "Externalities in the Classroom: How Children Exposed to Domestic Violence Affect Everyone's Kids." I love the paper, hate the title.

The paper... is a rare quantitative glimpse into the impact that home life has on schools. I skimmed it; it isn't perfect, but it's credible. The basic conclusion:
we estimate that adding one more troubled boy peer to a classroom of 20 students reduces boys’ student test scores by nearly two percentile points (one-fifteenth of a standard deviation) and increases the probability that boys commit a disciplinary infraction by 17 percent (4.4 percentage points).
The title... makes me xenophobic. ("Are there kids like that in my brother's classes? How could we get rid of them?") It turns abused kids into damaged goods. It's a fair characterization of the evidence presented in the paper, but it's not the angle I would have taken.

In my mind, the real story is about the cost of broken relationships. It's more sad than surprising to see that really bad parenting can influence not just their own kids, but all the kids around them enough to show up on test scores and administrative records.

Key takeaway: People are remarkably interconnected. Externalities dominate any place where people are learning.

A PS -- I found the comments on the blog funny in a dark way. It's a mixed bag of snarky, offensive, shallow, and pompous. A few are insightful. I suppose we're all better for this kind of discussion, but the process is pretty messy.

Monday, August 4, 2008

Postracial indeed -- Obama's take on affirmative action


Debates about affirmative action have always made me uncomfortable. I believe in fairness, mainly in the form of meritocracy -- equality of opportunity, not outcome. However, it's also obvious that opportunities are not equal in our society, and a lot of those inequalities are racially distributed. Our massive achievement gaps are proof of that.

My (limited) experience suggests that in most parts of America, soft discrimination is a much bigger problem that overt KKK-style bigotry. I've always worried that racial affirmative action perpetuates the stereotypes it is meant to compensate for. Also, many black kids are born into well-educated, affluent families and it seems unfair to give them a bonus intended for the disadvantaged. So in the big pro/con debate of affirmative action, I've leaned con.

Of course, as a half-white, half-Asian child of upper-middle class parents with advanced degrees, it's simply not PC for me to speak against affirmative action. What do I know about race and discrimination?

So three cheers to Barack Obama for saying what I couldn't, as reported in Sunday's NY Times.

During a presidential debate in April, Mr. Obama said his two daughters, Malia, 10, and Sasha, 7, “who have had a pretty good deal” in life, should not benefit from affirmative action when they apply to college, particularly if they were competing for admission with poor white students.

Read the whole article for details; the main idea is that Obama is on record as saying that affirmative action should be based on socioeconomic status instead of race. His daughters have grown up privileged; they don't need or deserve affirmative action.

This take on affirmative action sits a lot better with my conscience. It shares opportunity fairly and broadly, but doesn't reinforce racial stereotypes. I don't know the details, but I like it.

I don't know how this idea will play out in public opinion, but I'm hopeful. Two years ago, Michigan went through a similar debate on Proposal 2, a constitutional initiative to make "preferential treament on the basis of race, sex, color, ethnicity, or national origin" illegal in the state. Campaigns on both sides fought angry and dirty. I quietly supported the Prop 2 for the reasons above. Liberal newspapers around the state castigated moderates making essentially the same argument that Obama is making. Affirmative action played out as a divisive polarizing issue.

This time, the combination of messenger and message seems to have some resonance. (See the same NY Times article for some details.) If Obama pushes, he may have the reach and credibility to reshape take the affirmative action debate beyond race -- a real milestone for American politics.

We'll see how it goes, but so far on this issue I think Obama is living up to his potential for running a truly post-racial campaign.

PS - The picture in this post is borrowed from http://lib.colostate.edu/research/divandarea/bif/archive/bif03/affirm.jpg. I have no idea what their content is like. Go Google images!

Friday, July 25, 2008

The New Balance philosophy of testing


Before interviews of all types, I've found it valuable to try to match the dress code of the people I'm visiting. Bear with me here, this is policy-relevant.

When I go up to the state government offices in Lansing, I wear my brown Oxford-style Dockers. Around the poli sci department, I usually wear a beat-up pair of New Balance, or maybe sandals in the summer. When I'm in the policy school, I often go back to khakis and Dockers because it's a professional school and that's just the way people dress.

Key insight: picking shoes is not about blending in -- it's about shared perspective. By dressing the way others dress, I try to indicate that I see the world the way they see it. Picking the right shoes for an interview is a kind of attiristic* code-switching.

Testing is a lot like checking to see if people are wearing the "right" shoes. As Vihao suggests in his comment, the goal is to make sure that students can make decisions more or less the way that we would make decisions. When they demonstrate the "right" kind of thinking, we know that we can trust their judgment and turn them loose on the world.

In the best case, we know that our decisions are fallible and so we don't try to force too much conformity -- just enough to have a common language for approaching problems. As with shoes, we don't usually demand complete conformity, just an appreciation of the symbolic significance of their actions. In good tests, the real goal is to demonstrate fluency, not correctness.

Examples include: recitals, portfolio evaluations, essays, debates, "show your work" math problems, and discussions, including (I can't resist) the cultural awareness test that Calvin fails in this strip. None of these tests has a right answer, but there are still implicit standards for what constitutes good work.

The subjects with right and wrong answers are exceptions that prove the rule. For elementary math, grammar, and the boring kind of history ("What year was the battle of Waterloo?") correctness is easy to judge because everyone agrees on what the right answers are. But the goal is still to make sure that students are speaking the same language that everyone else is.

Launch point: I've made some big claims about what testing should and shouldn't be. What do you think? Have you seen examples of this kind of testing at work, school, etc.? Or am I all wrong this time?

* Attiristic: adj. An invented word meaning, "pertaining to dress and clothing." (Does anyone know a real word that means what I want to say here?)

I know, I know...

It's been too long since I've posted. I've been trying to figure out how to bring together Karen's comment about testing non-content-related standards, Vihao's comment on how face to face interviews catch information that paper tests miss, and Sherry's comment about how what students plan to do after school should have an impact on what they're learning in schools.

I suppose I can ask another blue-sky question: how close can a test get to measuring real "education"?

Thursday, July 17, 2008

You can't improve what you can't measure

I'm still responding to the emails and comments from my last post. Thanks, all, for the good discussions.

Today I want to respond to a comment I've heard many times -- most recently from my long-lost high school buddy Vihao:
"standardized education assumes everybody is the same. i say get rid of standardized tests and make curriculum more flexible to allow students to spend more time pursuing subjects they enjoy..."

I completely agree that teaching needs to involve students and speak to the things that are relevant and interesting to them. If it were possible, I'd support an IEP for every child. Check out www.longtaillearners.com for an interesting extrapolation of this theme.

But I don't believe that embracing individualized learning means we have to reject standardized testing. Let me try an analogy.


A couple of weeks ago, my wife and I moved to a new apartment. Except for campus and Kroger, we have to get on the highway to go just about anywhere. Since there are three ways to get to the onramp (and because we are both Type A people), we timed ourselves driving to and from the highway several times and compared. The verdict? Dhu Varren to Green to 23 going south, and Barton to I-14 going north or west. (Not that you care; this is just an analogy.)

Picking the best way to get to the highway is like improving schools. There are lots of reasonable sounding ways to accomplish both tasks, but to do either intelligently, you need some metric to use as a baseline for comparison. For roads, the metric was our dashboard clock. For schools, the best available metric is standardized tests.

You can't improve what you can't measure. The paradox here is that standardized tests can give teachers more flexibility in the way they run their classrooms.

PS - A sidenote that I have to include every time I talk about tests: many of the standardized tests currently in use are bad or really bad. This isn't because we don't know how to do better; it's because many states put in slipshod assessments hoping that accountability reform would just go away. We definitely need to devote more attention to fixing these badly designed testing systems.

Friday, July 11, 2008

Calvin asks, "Why are schools boring?"

A question and a challenge for you:

First, the question. According to wikipedia, "a School is an institution designed to allow and encourage students ... to learn, under the supervision of teachers." Learning, in my experience, is not usually boring.


(Click to enlarge.)

So why is it that schools are so boring? According to my friend Calvin, they're not just sometimes dull -- boredom is the dominant emotion associated with school. Why is the one setting designed specifically for intellectual stimulation the setting most strongly associated with flat-out mind-numbingness?

And next, my challenge: what would it take to run a school without boredom?

PS: This C&H strip is linked from www.s-anand.net/calvinandhobbes.html#19870517, a site worth having bookmarked. (Is it legal? I have no idea.)
This strip is also instructive.

Reintroducing myself...

My name is Abe Gong. My goal is to learn how to make better schools.

I'm a first-year public policy and political science PhD student at the University of Michigan. I'm interested in institutional design, behavioral economics, and far-from-equilibrium dynamics in organizational change, especially as they yield practical approaches to improving K-12 education. When relatives ask, I usually say I study "school reform." Methodologically speaking, I lean quantitative, interdisciplinary, and pragmatic.

Politically, I'm a progressive moderate. I believe that accountability reform might work for the American K-12 system, but there are a lot of kinks to iron out first. The status quo is unacceptable.

Monday, March 17, 2008

Opening salvo -- Two thumbs down for Collateral Damage

I started reading Collateral Damage: How High-Stakes Testing Corrupts America's Schools on the bus on Thursday and it made me so angry I read the whole thing in a day. The book is propaganda, not research. The authors (Sharon Nichols and David Berliner) start by comparing NCLB to 9-11 and Hurricane Katrina, claim that high-stakes testing is always bad, and then find anecdotes of bad things that have happened since NCLB.

This is shoddy research, based in ideology and calculated to fire up opponents of accountability reform. Here are my responses to the book's two major claims:


  • "Campbell's Law" is bunk. Nichols and Berliner contend that "Campbell's law stipulates that the more any quantitative social indicator is used for social decision-making, the more subject it will be to corruption pressures and the more apt it will be to distort and corrupt the social processes it was intended to monitor." They elevate this "law" to the level of the Heisenberg uncertainty principle and use it throughout the book as an carte blanche excuse for not assessing school performance.

    If you search for "campbell's law" on google or google scholar, the vast majority of sites and articles you turn up will refer to Collateral Damage. Most of the rest are written by authors named Campbell. This "law" was not recognized or circulated prior before Nichols and Berliner's book.

    Don't go calling it "Berliner's law" either -- it simply isn't true. Example: grades are the sole measurement for evaluating college student performance. Do you cheat to improve your grades -- always? If Berliner's word is law, you must. Nichols and Berliner cite examples of doctors, teachers, salespeople, CEOs, politicians, auto mechanics, etc. cheating to improve their bottom lines. Do they all cheat? Of course not. Campbell's "law" is a vast overgeneralization.

    The truth is that performance metrics put pressure on those being evaluated. Organizational theorists have a good framework for looking at cheating and corruption called the "fraud triangle." In the fraud triangle, cheating happens when pressure, opportunity, and rationalization come together. In stark contrast to Nichols and Berliner's claim, pressure from testing alone isn't enough to induce teachers to cheat.


  • The authors of Collateral Damage also contend that performance evaluation is an "archaic theory of management" "commonly used to manage workers in the nineteenth century--a workforce consisting mostly of laborers whose intellects were not valuable and who were completely replaceable (pieceworkers in shirt factories, fruit pickers, nonunion laborers)." Nichols and Berliner try to argue that modern businesses don't attachthreats and incentives to the performance of knowledge workers. Read this section again and you'll notice the lack of any citations for this ludicrous idea.

    The truth is that most professionals are paid largely for performance. Most hiring, firing, and promotion decisions are made on the basis of performance evaluations. Incentives and performance pay are the rungs of the most career ladders. Managers, entrepreneurs, and increasingly, everyday employees, are compensated with stock options. Lawyers, wall street analysts, consultants, and CEOs count on annual review bonuses as a substantial portion of their income. The trend in medicine for the last 30 years has been towards performance management. And that's to say nothing about the fact that all businesses live and die by the ultimate performance evaluation -- the ability to generate revenue in a competitive environment.

    From the early experiments with incentivized performance in the 1800's, performance pay has become increasingly widespread, sophisticated, and effective. Education is one of the last industries in the modern information economy that has held out against performance evaluation. I don't know if Nichols and Berliner missed this trend because of ignorance or ideology, but it is a glaring omission and a bad foundation for a book about measuring performance.



Collateral Damage never tries to verify either of these two very large claims. It simply takes them as given and then chronicles supporting anecdotes. Itdoesn't address alternative hypotheses. It doesn't consider context. It calls for no further research -- according to its authors, Collateral Damage is the definitive end to the debate about accountability.

To my mind, this is an unproductive path for policy discussion. It starts from ideology, not reality, and leaves no room for discovery and discussion. There are plenty of legitimate criticisms and questions about accountability policy: What are rational ways to choose proficiency levels? Could we improve testing by using different formats? How can we prevent cheating by teachers and students? These need to be resolved or high-stakes testing might end up hurting a lot of kids.

Unfortunately, Nichols and Berliner ignore the real criticisms in favor of false generalizations, made-up "laws," and extreme anecdotes. It's writing like this that makes reform such a combatative and political process. Two thumbs down for the closed-mindedness and lack of real analysis that produced Collateral Damage.

Declaration of intent

Good social science happens when three things get together:

  • good questions

  • good methods

  • good data

  • You can learn about good methods and data in grad school, but you have to find good questions for yourself. This blog is about opening a dialogue to find good questions -- especially about American education policy.

    My goal is to get in touch with people and talk through important policy questions, starting from a variety of ideas, experiences, and perspectives. That includes friends, students, teachers, principals, parents, politicians, policymakers, and anyone who's ever been to a school and wondered why education is what it is.

    I expect this conversation to be a quest for places where reasonable people can reasonably disagree about the right way to do things in society. Conversely, it will be a conversation about finding the common ground that people share regardless of the policies they favor. Hopefully, this map of consensus and honestly held disagreement will lay out a route toward better discussion, better research, and eventually better policy.

    Looking forward to your replies
    - Abe

Hello world...

This is a test to make sure blogger is being nice.