Re: ranging opines about the range
William B. Ware <[EMAIL PROTECTED]> wrote in sci.stat.edu: >Anyway, more to the point... the "add one" is an old argument based on the >notion of "real limits." Suppose the range of scores is 50 to 89. It was >argued that 50 really goes down to 49.5 and 89 really goes up to >89.5. Thus the range was defined as 89.5 - 49.5... thus the additional >one unit... Perhaps a better argument is that if you count the numbers you get forty of them: 50, 51, 52, ..., 59 makes ten, and similarly for the 60s, 70s, and 80s. -- Stan Brown, Oak Road Systems, Cortland County, New York, USA http://oakroadsystems.com My reply address is correct as is. The courtesy of providing a correct reply address is more important to me than time spent deleting spam. = Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =
Re: Help
Thanks for your helps :) = Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =
Please help
i haven't touch statistics materials for many years so i need someone be so kind to help me out with this simple problem: Tossing a fair coin n times. Let A denote the maximum run length, i.e. the largest number of consecutive heads we get among the n tosses. Find E(A) for the case n=10. The answer is apporximately 2.8 Could someone help me the way how to understand this question. I will write a computer simulation program but as you can see i don't know how to get E(x) generally. Thank you very much! = Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =
Re: ranging opines about the range
In article <[EMAIL PROTECTED]>, Robert J. MacG. Dawson <[EMAIL PROTECTED]> writes > > >jeff rasmussen wrote: >> >> Dear statistically-enamored, >> >> There was a question in my undergrad class concerning how to >>define the >> range, where a student pointed out that contrary to my edict, the range was >> "the difference between the maximum & minimum". I'd always believed that >> the correct answer was the "difference between the maximum & minimum plus >> one" > > One what? Any statistic that depends on the units used seems rather >arbitrary to me. If I compute the range of weights of a group of people >(in kilograms) I ought to get the same actual *weight* as an American >using pounds or a Brit using stones. On a lighter note - sorry - Brits can't use stones as however reluctantly we are now metricated. Selling things in pounds and stones is against the law - though I suppose that using the measure is not - yet! I just tell students I'm B.C. - Before Centimetres. - Jonathan Robbins > > Suppose I have three meter sticks - are you telling us that the range >of their lengths is a little over one meter? > > I'm afraid I vote with your students. > > -Robert Dawson > > >= >Instructions for joining and leaving this list and remarks about >the problem of INAPPROPRIATE MESSAGES are available at > http://jse.stat.ncsu.edu/ >= = Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =
Re: MCAS, statistics and other math problems
At 12:41 PM 10/5/01 -0500, Christopher J. Mecklin wrote: >(4) If the Massachusetts Department of Education really wants to include a >boxplot item on the test, it should either be a multiple choice question >written so that the correct answer is the same no matter which type of >boxplot one was taught, or an open-ended question where the students >actually create boxplots for 2 data sets and compare/contrast the 2 >distributions. The readers then should be aware of both types of boxplots >when assessing the question. > >That's my two cents, anyway actually, i think the above is worth at least 3 cents but, the main issue re: boxplots ... is the fact that a boxplot indicates a median in the "box", rather than a mean (say) in the "box" ... really really important ENOUGH to waste an entire question (1 in 6 about statistical things) on a test that is such high stakes? seems like iF you wanted to use a boxplot as a data reporting tool ... within the context of an item on a test like this ... that, you would focus on something important like: spread of scores, or ... what is an approximate average value, or ... whether the distribution seems to be symmetrical or skewed ... == dennis roberts, penn state university educational psychology, 8148632401 http://roberts.ed.psu.edu/users/droberts/drober~1.htm = Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =
Re: ranging opines about the range
William B. Ware said on 10/5/01 8:58 AM: >I don't think I understand your argument... Are you saying that the >"descriptive statistic" should be invariant over scale? > >Anyway, more to the point... the "add one" is an old argument based on the >notion of "real limits." Suppose the range of scores is 50 to 89. It was >argued that 50 really goes down to 49.5 and 89 really goes up to >89.5. Thus the range was defined as 89.5 - 49.5... thus the additional >one unit... > >Personally, I don't subscribe to this position... It assumes that the low >score is always toward the low end of its value and that the upper value >is always toward the high end of its value... Sort of a maximum range... I >prefer not including the additional one unit... Another problem with the add one notion based on real limits is that it does not necessarily apply to many real limits situations. The way I introduce real limits to a class is to pass around a piece of paper asking each student to write down their weight. The paper comes to the front of the room while I go through the announcements, review questions, etc. I then write all the numbers on the board and point out that nearly all the students wrote down their weight to the nearest 5th pound. A few went to the nearest single pound. We then discuss in the context of real limits how a weight of 125 pounds represents weights from 122.5 to 127.5, etc. Then we can discuss how all measurements are necessarily representing ranges of values which are beyond the precision of the measuring system. Note, if the idea of real limits necessitating the adding one to the calculation of the range were valid, then in the case of figuring the range of weights for a class, I would do well to add 5. In all cases the amount added to the range calculation depends on the precision of measurement, which becomes a problematic notion, IMO. Paul = Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =
Re: MCAS, statistics and other math problems
Dr. Gallagher and Edstat newsgroup: Here's my take on the MCAS and boxplots. (1) I agree with Eugene Gallagher and others in that the question about boxplots on the MCAS is poor, since the correct answer depends on whether you learned the "Tukey" boxplot (that indicates outliers) or the "quick" boxplot (that ignores the possibility of outlers and merely extends the whiskers to the minimum and maximum). It is typical in college-level stat texts to use the Tukey boxplot, but I believe (I may be wrong) that high-school level books tend to use the "quick" boxplot. (2) Gallagher is correct in that most standard software packages (such as SPSS, SAS, S-plus/R, Minitab?) construct the "Tukey" boxplot. However I have not seen anyone mention the fact that the TI-83 graphing calculator can actually construct either of the two types of boxplots. In the StatPlot menu, the TI-83 has a Boxplot option (for what TI-83 calls a "regular" boxplot that I refer to as a "quick" boxplot) and a ModBoxplot option (this is a "modified" or Tukey boxplot). I believe this is pertinent because I assume that many secondary math classes use TI calculators. (3) My solution in my Introduction to Statistics class, therefore, is to discuss both kinds of boxplots. I use the Moore/McCabe text, which describes the Tukey boxplot. However, since many of my students will be teaching at the middle-school or high-school level, I also point out the existence of the "quick" boxplot. I do stress that the Tukey boxplot is superior, since it indicates potential outliers. (4) If the Massachusetts Department of Education really wants to include a boxplot item on the test, it should either be a multiple choice question written so that the correct answer is the same no matter which type of boxplot one was taught, or an open-ended question where the students actually create boxplots for 2 data sets and compare/contrast the 2 distributions. The readers then should be aware of both types of boxplots when assessing the question. That's my two cents, anyway Chris Mecklin At 02:33 AM 10/05/2001 +, EugeneGall wrote: >During the last week in August, there was a lengthy thread on sci.stat.edu >about problems with the probability and statistics questions in MCAS, the high >stakes test required for graduating from a MA public high school. > >Shortly after participating in that thread, I wrote up my analyses of 6 of the >41 questions on the 2001 exam and 4 of the 42 questions on the 2000 exam. I >mentioned this group and several people who posted on that thread in my >commentary. Four of the 2000 & 2001 questions were in the area of statistics >and probability. The most severe problems appear to be testing on concepts >intended only for 11th & 12th graders - a violation of the basic principle of >MCAS. My commentary includes cross-references to these learning standards. > >I sent my critique to the Dept. of Education in Aug. so that they could delete >the flawed questions from the scores on which failure decisions are based. As >described in the newspaper article linked below, there are no appeals now >possible in MCAS for failing because of invalid questions. Students must pass >this MCAS math test, or one of 4 retakes, to graduate in 2003. 45-50% of MA >10th graders failed the tests offered from 1998 through 2000. > >The MA Dept of Education's Press spokesman, Heidi Perlman, is quoted in a >Berkshire Eagle story that DOE stands behind all of the questions I discussed: > "But the Department of Education dismisses the professor's analysis > of the >test and stands by all its questions. In fact, the department changed its >scoring policy on the 10th-grade tests this year to safeguard against errors, >officials said. .. "Some of the questions could've been slightly better >worded, >but in total none of them are invalid questions," said department spokeswoman >Heidi Perlman. She said it was reviewed by department staff, but >officials did >not agree with Gallagher's analysis. "We don't believe his criticisms are >valid," Perlman said. > >Ms Perlman's comments can can be read in the following news article from the >Berkshire Eagle, by Jennifer Fenn: >http://search.newschoice.com/ArchiveDisplay.asp?story=d:\index\newsarchive >s\ne\nebe\fpg\20011002\1122674_mcaserrors.txt&source=www%2Eberkshireeagle% >2Ecom&puid=2269&paper=Berkshire+Eagle+Online > >One reporter told me that he wasn't sure how to handle my analysis of these >questions because DOE says the questions are all valid, and I say that they >aren't. He said that he's not a mathematician and can't judge who is >correct. >I said publish the questions, and let the mathematically literate readers >respond. > >I would appreciate what the members of this group think about the questions, >especially about the statistics and probability questions. I realize that my >28-p commentary is a bit much, but the issue is very important to the Class of >2003 and other citiz
Re: MCAS, statistics and other math problems
Thanks, and moral support is appreciated. MCAS is very controversial in MA. None of the major papers have yet called into question the test itself. Now, the DOE apparently is saying that they stand behind every question. I believe it might help if the MA DOE MCAS group, headed by Jeff Nellhaus hears from concerned mathematicians about problems in the test (if you truly think there are problems). There is a feedback page at the bottom of the DOE MCAS page. One reporter told me, "I don't understand this. This is mathematics. There are clear-cut right and wrong answers aren't there?" I told him I thought there were. I truly hope that DOE will call for an outside review. Perhaps the problems I flagged were caused by a failure by the testing company to remove flawed questions. Who knows? An outside review of the questions is needed. This test is scaled with hidden "anchor" questions offered on every test. They make up about 20% of the questions asked. I was flagging about 1/10 to 1/8 of the open questions as being flawed. A few flawed "anchor" questions used to scale one year's test could pose real problems. If you want to comment directly to DOE, here is the link: http://www.doe.mass.edu/mcas/ = Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =
Job Posting - Director of Institutional Effectiveness
Statisticians certainly have many of the skills needed to direct a college's institutional effectiveness efforts. Perhaps some of you are interested in the following: LYNCHBURG COLLEGE IN VIRGINIA Lynchburg College is searching for an outstanding candidate to serve as Director of Institutional Effectiveness, working with academic and administrative units to oversee the College's Institutional Effectiveness activities. Skills and Competencies- Excellent English-language oral and written communication skills. Good mathematical skills for data presentation and statistical analyses. Computer skills and competency with spreadsheet, graphics, database, and statistical analysis software packages. Minimum Experience- Three years of directly related experience in academic field or experience in institutional effectiveness. Minimum Education- Master's Degree in appropriate field, Doctorate preferred. Salary- Competitive salary commensurate with experience. Starting Date- No later than June 30, 2002. Application Materials- Letter of application, copy of transcript, current vita, and three letters of recommendation. Please address correspondence to: Dr. Delores M. Wolfe Associate Dean of the College Lynchburg College 1501 Lakeside Drive Lynchburg, VA 24501-3199 Phone: 434-544-8695 E-mail: [EMAIL PROTECTED] For complete information on this position visit http://www.lynchburg.edu/jobpostings/ie.htm Lynchburg College is an Equal Opportunity Employer. __ = Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =
Re: ranging opines about the range
i think that the +1 is reasonable IF, we have a potentially continuous variable that, for convenience, we put tick marks at arbitrary points ... such as a 50 item test ... we let scores be 23, or 24, or 25, etc. IF the assumption is that knowledge is continuous ... then i don't see anything amiss if we assume that the limits are set at 1/2 units below and above the arbitrary values we use ... since (as dividing points between 2 adjacent values), i don't see anything necessarily that would argue that our "observed" scores (23, or 24, etc.) would be biased one way or the other the difficulty in using the 1 for finding the range is primarily when we have scales that clearly are not in units of 1 ... either real or made so arbitrarily ... if the unit we use is not 1, then accumulating 1/2 of a unit size of 1 at the low end of the scale + 1/2 of a unit size of 1 at the high end of the scale ... makes no sense ... fundamentally, IF you are going to posit some extension of the lowest and highest scores ... on which to make the range calculation ... you at least have to consider the UNIT SIZE you are working with FIRST ... before taking half of it alan had mentioned that on a real continuous scale ... that the range really was between the lowest and highest value ... with nothing added to either end ... and, i would agree with this IF, our measuring tool could in reality take a measurement that translates to ANY value anywhere along that scale ... if not, then one might question a wee bit about whether the lowest and highest MEASURED numbers, are actually the lowest and highest possible values (of course, alan could counter that if they can only be measured as such ... they THEY are the only admissible values) of course, all of this is rather unimportant since, the range is not a very "helpful" statistic or value to calculate on a set of data ... that is, if you are using it for indexing dispersion and, in the illustration that alan gave for how the "public" view range ... the range of prices for an item is from $1.50 to $2.50 ... they would probably laugh at you if you said that the range is REALLY from $1.495 ... to $2.505 they would say ... huh? say what? At 10:58 AM 10/5/01 -0400, William B. Ware wrote: >Robert, > >I don't think I understand your argument... Are you saying that the >"descriptive statistic" should be invariant over scale? > >Anyway, more to the point... the "add one" is an old argument based on the >notion of "real limits." Suppose the range of scores is 50 to 89. It was >argued that 50 really goes down to 49.5 and 89 really goes up to >89.5. Thus the range was defined as 89.5 - 49.5... thus the additional >one unit... > >Personally, I don't subscribe to this position... It assumes that the low >score is always toward the low end of its value and that the upper value >is always toward the high end of its value... Sort of a maximum range... I >prefer not including the additional one unit... > >Bill > >__ >William B. Ware, Professor and Chair Educational Psychology, >CB# 3500 Measurement, and Evaluation >University of North Carolina PHONE (919)-962-7848 >Chapel Hill, NC 27599-3500 FAX: (919)-962-1533 >http://www.unc.edu/~wbware/ EMAIL: [EMAIL PROTECTED] >__ > > >On Fri, 5 Oct 2001, Robert J. MacG. Dawson wrote: > > > > > > > jeff rasmussen wrote: > > > > > > Dear statistically-enamored, > > > > > > There was a question in my undergrad class concerning how to > define the > > > range, where a student pointed out that contrary to my edict, the > range was > > > "the difference between the maximum & minimum". I'd always believed that > > > the correct answer was the "difference between the maximum & minimum plus > > > one" > > > > One what? Any statistic that depends on the units used seems rather > > arbitrary to me. If I compute the range of weights of a group of people > > (in kilograms) I ought to get the same actual *weight* as an American > > using pounds or a Brit using stones. > > > > Suppose I have three meter sticks - are you telling us that the range > > of their lengths is a little over one meter? > > > > I'm afraid I vote with your students. > > > > -Robert Dawson > > > > > > = > > Instructions for joining and leaving this list and remarks about > > the problem of INAPPROPRIATE MESSAGES are available at > > http://jse.stat.ncsu.edu/ > > = > > > > > >= >Instructions for joining and leaving this list and remarks about >the problem of INAP
Job: MN, Twin Cities
Below is a posting that appeared in the local Minneapolis paper. Please direct all inquiries to Susan Mehle. No relocation expenses will be paid. Karen Scheltema, M.A., M.S. Statistician HealthEast Research and Education 1700 University Ave W St. Paul, MN 55104 (651) 232-5212 (phone) (651) 641-0683 (fax) [EMAIL PROTECTED] > -Original Message- > From: Mehle, Susan > Sent: Friday, October 05, 2001 10:05 AM > To: Scheltema, Karen > Subject: Statistician Ad > > HealthCare Administration/Research > > From the way we treat our patients and each other, to our visionary > approach to healthcare, you'll see the difference throughout the > HealthEast Care System. > > SENIOR STATISTICIAN > > Provides leadership and direction in study design and > implementation: including program evaluation, survey design, patient > satisfaction, and applied clinical and health services research studies. > Requires a Masters degree in Biostatistics, Epidemiology, Health Services > Research or a related field with coursework in research design, statistics > and technical writing; at least 3 years of related professional > experience; project management skills, strong coaching and mentoring > skills; and SPSS (or similar) and MS Office proficiency. > > We offer a competitive salary and a supportive environment in which > to pursue your goals. For consideration, please send your resume to: > HealthEast Research and Education, 1700 University Avenue West, St. Paul, > MN 55104 or email to [EMAIL PROTECTED] > == > > > Susan > _ > Susan Clay Mehle > Research and Education > HealthEast - Midway Campus > Phone: (651) 232-5021 > Pager: (651) 864-2247 > (To send a text page go to : www.airtouchpaging.com/index.asp) > = Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =
Re: ranging opines about the range
"William B. Ware" wrote: > > Robert, > > I don't think I understand your argument... Are you saying that the > "descriptive statistic" should be invariant over scale? Yes, of course. Otherwise it's a description of the process of measuring, not of what is being measured. > > Anyway, more to the point... the "add one" is an old argument based on the > notion of "real limits." Suppose the range of scores is 50 to 89. It was > argued that 50 really goes down to 49.5 and 89 really goes up to > 89.5. Thus the range was defined as 89.5 - 49.5... thus the additional > one unit... Yes, but not all data are integer test scores. *If* you are given data that have been rounded or truncated to the nearest multiple of some D (in your example, 1), then I suppose that an unbiased estimator of the original range would be max + 1 - min or something like that. -Robert Dawson = Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =
Re: ranging opines about the range
Robert, I don't think I understand your argument... Are you saying that the "descriptive statistic" should be invariant over scale? Anyway, more to the point... the "add one" is an old argument based on the notion of "real limits." Suppose the range of scores is 50 to 89. It was argued that 50 really goes down to 49.5 and 89 really goes up to 89.5. Thus the range was defined as 89.5 - 49.5... thus the additional one unit... Personally, I don't subscribe to this position... It assumes that the low score is always toward the low end of its value and that the upper value is always toward the high end of its value... Sort of a maximum range... I prefer not including the additional one unit... Bill __ William B. Ware, Professor and Chair Educational Psychology, CB# 3500 Measurement, and Evaluation University of North Carolina PHONE (919)-962-7848 Chapel Hill, NC 27599-3500 FAX: (919)-962-1533 http://www.unc.edu/~wbware/ EMAIL: [EMAIL PROTECTED] __ On Fri, 5 Oct 2001, Robert J. MacG. Dawson wrote: > > > jeff rasmussen wrote: > > > > Dear statistically-enamored, > > > > There was a question in my undergrad class concerning how to define the > > range, where a student pointed out that contrary to my edict, the range was > > "the difference between the maximum & minimum". I'd always believed that > > the correct answer was the "difference between the maximum & minimum plus > > one" > > One what? Any statistic that depends on the units used seems rather > arbitrary to me. If I compute the range of weights of a group of people > (in kilograms) I ought to get the same actual *weight* as an American > using pounds or a Brit using stones. > > Suppose I have three meter sticks - are you telling us that the range > of their lengths is a little over one meter? > > I'm afraid I vote with your students. > > -Robert Dawson > > > = > Instructions for joining and leaving this list and remarks about > the problem of INAPPROPRIATE MESSAGES are available at > http://jse.stat.ncsu.edu/ > = > = Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =
Re: MCAS, statistics and other math problems
gene ... we have been through this sort of discussion before and i, for one, totally sympathize with you in this situation ... but, it is difficult for outsiders ... outside of mass. (not being residents or parents of impacted kids) ... to really know how to respond to this and what to do about it clearly, there are serious problems with some test items and hence, there are serious problems with the SCORES examinees make ON these tests there appear to be also, clear problems with the item/test review process that has been used and, the reasons for and methods of, legitimate appeal when tests count this much, then all benefits of the doubt need to go TO the students ... not to some rigidly formulated process what LEGAL challenges have been organized and made within mass.? it seems to me that the only real way to make progress on this problem is to fight fire with fire ... and that usually means well organized legal efforts ... what can WE do, as individuals who read this list ... who are interested in this problem? probably, very little but, i think most give you our "moral" support ... and wish you well ... At 02:33 AM 10/5/01 +, EugeneGall wrote: >During the last week in August, there was a lengthy thread on sci.stat.edu >about problems with the probability and statistics questions in MCAS, the high >stakes test required for graduating from a MA public high school. _ dennis roberts, educational psychology, penn state university 208 cedar, AC 8148632401, mailto:[EMAIL PROTECTED] http://roberts.ed.psu.edu/users/droberts/drober~1.htm = Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =
Re: ranging opines about the range
jeff rasmussen wrote: > > Dear statistically-enamored, > > There was a question in my undergrad class concerning how to define the > range, where a student pointed out that contrary to my edict, the range was > "the difference between the maximum & minimum". I'd always believed that > the correct answer was the "difference between the maximum & minimum plus > one" One what? Any statistic that depends on the units used seems rather arbitrary to me. If I compute the range of weights of a group of people (in kilograms) I ought to get the same actual *weight* as an American using pounds or a Brit using stones. Suppose I have three meter sticks - are you telling us that the range of their lengths is a little over one meter? I'm afraid I vote with your students. -Robert Dawson = Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =
RE: MCAS, statistics and other math problems
At 07:03 AM 10/5/01 -0500, Olsen, Chris wrote: >Professor Gallagher and All -- > > >It would appear that neither the "appeal systems" nor a claim of >"technical adequacy" would be a response to your concern about bad >questions. The claim of technical adequacy, i.e. "that good students tend >to answer them correctly anyway, but poor students don't" does not, to my >mind, constitute technical adequacy. this is absolutely correct ... all they have to go on is the score on the test ... if we toss in "ability" on something else as a defense ... then, why give them THIS test in the first place? _ dennis roberts, educational psychology, penn state university 208 cedar, AC 8148632401, mailto:[EMAIL PROTECTED] http://roberts.ed.psu.edu/users/droberts/drober~1.htm = Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =
"Pluma y Fuente" Nº 181 del 05/10/2001.
__ Logos Traducciones - www.logos.it __ "Pluma y Fuente" del 05/10/2001. Edición Nº 181. Informaciones seleccionadas por Reporters Online EDITORIAL DEL DÍA. ¿Cuánta libertad de prensa será sacrificada en el altar de la seguridad? Es la pregunta se que plantea en los medios de información de los Estados Unidos. ¿Y el resto del mundo qué dice? http://www.reportersonline.org/owa-k/press.parentesi.vedi?Hlingua=es&Hcodice=339 REPORTERSONLINE ofrece sábado y domingo una síntesis de las principales noticias de la semana. Nuestras páginas del sábado se dedican al panorama mundial mientras que las del domingo se refieren exclusivamente a América Latina y el Caribe ÁFRICA - Los Presidentes de Angola y del Congo Democrático discuten sobre la ofensiva de Kinshasa para desalojar del territorio congoleño las fuerzas insurgentes. - Elecciones municipales y legislativas en Mauritania desde el 19 al 26 de octubre. Esta vez las oposiciones participan revocando un comportamiento usual en el pasado. http://www.reportersonline.org/owa-k/press.news_es.print?H=Africa&D=05-OCT-2001&L=es ASIA-PACÍFICO - El Gobierno de Pakistán consideró ayer que las pruebas contra bin-Laden son «suficientes» para acusarlo de los recientes actos terroristas. - Aumentan los rumores, por ahora sin confirmación, sobre deserciones afganas masivas y la alianza del Norte anuncia nuevos éxitos militares contra los Talibán. http://www.reportersonline.org/owa-k/press.news_es.print?H=Asia&D=05-OCT-2001&L=es EUROPA - Tony Blair entregó ayer al Parlamento del Reino Unido y a los líderes de la oposición el «documento secreto y confidencial» que demostraría la culpabilidad de Osama bin-Laden. - Fuentes de EE.UU. insisten en decir que el avión ruso con 78 personas fue abatido ayer por un mísil superficie-aire SA-5 disparado desde una batería en la costa de Crimea. - Terminó ayer con el «procedimiento del silencio» el plazo para que la OTAN respondiera a las 8 peticiones de ayuda de EE.UU. Robertson dice que se aceptaron todas. - Misterio sobre la causa de la explosión del avión ruso Tu-154 con 78 pasajeros. ¿Atentado o mísil tierra-aire de la Marina de Ucrania? El Gobierno desmiente. Recuperan algunos cadáveres. http://www.reportersonline.org/owa-k/press.news_es.print?H=Europa&D=05-OCT-2001&L=es IBEROAMÉRICA - Un hombre y una mujer salvadoreños acusados de haber ayudado, quizá sin saber, a los terroristas del 11 de septiembre. Uno habría falsificado documentos para los atentadores. - A pesar de las críticas contra el Gobierno de Colombia también hoy, por tercer día, las guerrillas de las FARC y el Comisionado para la paz continúan sus negociaciones. - Vicente Fox se encuentra con el Presidente Bush y reitera la solidaridad del pueblo mejicano. Los gobernantes aclaran algunas dudas surgidas en las relaciones bilaterales durante estas semanas. - Un organismo de la OEA, la Junta Directiva de la Agencia Interamericana, discute en Nicaragua sobre cooperación y desarrollo regional. - El Presidente de Venezuela, país con vastas riquezas amazónicas, participará el lunes en la reunión ONU sobre la desertificación en Ginebra. - El Gobierno de Brasil rechaza definitivamente la petición de asilo político del general paraguayo César Oviedo que Asunción busca para procesar por golpismo. http://www.reportersonline.org/owa-k/press.news_es.print?H=Iberoamerica&D=05-OCT-2001&L=es LENGUAS - UNA BUENA PALABRA: Resaltar y Destacar - «La lengua española ante los retos de la globalización», será el tema del II Congreso Internacional del 16 al 19 octubre en Valladolid, España. - Cuando los acontecimientos de la historia desafían las lenguas. El debate sobre las palabras «Talibán y talibanes». Dudas y respuestas. http://www.reportersonline.org/owa-k/press.news_es.print?H=Lingue&D=05-OCT-2001&L=es MEDIO ORIENTE - En una operación del Ejército de Israel esta mañana mueren 6 palestinos y otros 45 resultan heridos. Soldados de este país ocupan varios barrios de Hebrón en Cisjordania. http://www.reportersonline.org/owa-k/press.news_es.print?H=Medio&D=05-OCT-2001&L=es MUNDO - Amnistía Internacional denuncia graves brotes de racismo y de represión oportunista de las libertades civiles en al menos 10 países después del 11 de septiembre. - Otorgan los llamados «Premios Nobel alternativos»: premiadas personalidades de Oriente Medio, israelíes y palestinos, del Reino Unido y el sacerdote Leonardo Boff de Brasil. - El Reino Unido ratificó ayer sorpresivamente la creación del Tribunal Penal Internacional distanciándose de las posiciones que compartía con EE.UU. http://www.reportersonline.org/owa-k/press.news_es.print?H=Mondo&D=05-OCT-2001&L=es NORTEAMÉRICA - Paul O'Neill, Secretario del Tesoro de los EE.UU. es más bien pesimista sobre el futuro económico del país y considera imposible escapar al «crecimiento negativo». - Las autoridades sanitarias estadounidenses del CDC confirman un caso de carbunco en el Esta
RE: MCAS, statistics and other math problems
Professor Gallagher and All -- Let me first of all absolutely commend your professional interest, time, and dedication to fair testing practice! With high stakes testing apparently the fad of this particular few years in public education, fairness is -- if posible -- an even more important concern than usual. I have downloaded the newspaper article and your analysis I have not yet had a chance to read your criticisms, but I did notice something odd in the newspaper report. It would appear that neither the "appeal systems" nor a claim of "technical adequacy" would be a response to your concern about bad questions. The claim of technical adequacy, i.e. "that good students tend to answer them correctly anyway, but poor students don't" does not, to my mind, constitute technical adequacy. Presuming that the aforementioned claim is that the questions have positive discrimination, one is constrained to point out that an item may have good discrimination and still not be a valid question. For example, if you are correct that item X is in the 11th-12th grade curriculum, but given to 10th-12th graders, it would presumably have high discrimination, but still not be "fair" to 10th graders. Secondly, the "appeal system" seems to miss your concerns also. As quoted in the article, a technical appeal may be made if (1) the test was graded incorrectly, and (2) if competence can be established by other means. "[Scoring accurately" (Nelhaus quote) seems to mean having two readers for the 10th grade exams. If this is in response to (1), the validities of the individual questions are still unadressed -- it is not generally considered progress if you give a cannibal and knife AND a fork, to paraphrase the old epigram. It would seem to me the only place to address issues of validity is by tightening up on the test at the writing stage, not at the "Oops" stage. Again, my thanks for addressing this problem -- keep on it! -- Chris Chris Olsen George Washington High School 2205 Forest Drive SE Cedar Rapids, IA (319)-398-2161 > -Original Message- > From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]] > Sent: Thursday, October 04, 2001 9:33 PM > To: [EMAIL PROTECTED] > Subject: MCAS, statistics and other math problems > > > During the last week in August, there was a lengthy thread on > sci.stat.edu > about problems with the probability and statistics questions > in MCAS, the high > stakes test required for graduating from a MA public high school. > > Shortly after participating in that thread, I wrote up my > analyses of 6 of the > 41 questions on the 2001 exam and 4 of the 42 questions on > the 2000 exam. I > mentioned this group and several people who posted on that > thread in my > commentary. Four of the 2000 & 2001 questions were in the > area of statistics > and probability. The most severe problems appear to be > testing on concepts > intended only for 11th & 12th graders - a violation of the > basic principle of > MCAS. My commentary includes cross-references to these > learning standards. > > I sent my critique to the Dept. of Education in Aug. so that > they could delete > the flawed questions from the scores on which failure > decisions are based. As > described in the newspaper article linked below, there are no > appeals now > possible in MCAS for failing because of invalid questions. > Students must pass > this MCAS math test, or one of 4 retakes, to graduate in > 2003. 45-50% of MA > 10th graders failed the tests offered from 1998 through 2000. > > The MA Dept of Education's Press spokesman, Heidi Perlman, is > quoted in a > Berkshire Eagle story that DOE stands behind all of the > questions I discussed: > "But the Department of Education dismisses the > professor's analysis of the > test and stands by all its questions. In fact, the department > changed its > scoring policy on the 10th-grade tests this year to safeguard > against errors, > officials said. .. "Some of the questions could've been > slightly better worded, > but in total none of them are invalid questions," said > department spokeswoman > Heidi Perlman. She said it was reviewed by department staff, > but officials did > not agree with Gallagher's analysis. "We don't believe his > criticisms are > valid," Perlman said. > > Ms Perlman's comments can can be read in the following news > article from the > Berkshire Eagle, by Jennifer Fenn: > http://search.newschoice.com/ArchiveDisplay.asp?story=d:\index \newsarchive s\ne\nebe\fpg\20011002\1122674_mcaserrors.txt&source=www%2Eberkshireeagle% 2Ecom&puid=2269&paper=Berkshire+Eagle+Online One reporter told me that he wasn't sure how to handle my analysis of these questions because DOE says the questions are all valid, and I say that they aren't. He said that he's not a mathematician and can't judge who is correct. I said publish the questions, and let the mathematically literate readers respond. I would appreciate wha
