Welcome

My Quotes in Naked Statistics: Stripping the Dread from the Data

84 Kuotes | 50 Books

Search:


Import Kindle clippings easily

Beta status: Bulk Kuote import!!!!

Log in & Sign in using:

Naked Statistics: Stripping the Dread from the Data

Wheelan, Charles
Statistics is more important than ever before because we have more meaningful opportunities to make use of data. Yet the formulas will not tell us which uses of data are appropriate and which are not. Math cannot supplant judgment.
Naked Statistics: Stripping the Dread from the Data - Wheelan, Charles Posição 4324-4326 - Seu destaque na página 256 | Adicionado na data segunda-feira, 20 de maio de 2013, 11:14:20
Permalink Share Paper Clasic Modern +Kuotes
Duflo was awarded the John Bates Clark Medal. This prize is presented by the American Economic Association to the best economist under the age of forty.* Among economist geeks, this prize is considered to be more prestigious than the Nobel Prize in Economics because it was historically awarded only every two years. (Beginning with Duflo?s award in 2010, the medal is now presented annually.) In any case, the Clark Medal is the MVP award for people with thick glasses (metaphorically speaking).
Naked Statistics: Stripping the Dread from the Data - Wheelan, Charles Posição 4267-4271 - Seu destaque na página 251 | Adicionado na data segunda-feira, 20 de maio de 2013, 10:36:13
Permalink Share Paper Clasic Modern +Kuotes
The answer: When the women do well, they spend some of their extra cash on more food for the family. The men don?t. Sorry guys.
Naked Statistics: Stripping the Dread from the Data - Wheelan, Charles Posição 4266-4267 - Seu destaque na página 251 | Adicionado na data segunda-feira, 20 de maio de 2013, 10:35:05
Permalink Share Paper Clasic Modern +Kuotes
For example, one of the longstanding problems with schools in India is absenteeism among teachers, particularly in small, rural schools with only a single teacher. Duflo and her coauthor Rema Hanna tested a clever, technology-driven solution on a random sample of 60 one-teacher schools in the Indian state of Rajasthan.16 Teachers in these 60 experimental schools were offered a bonus for good attendance. Here is the creative part: The teachers were given cameras with tamperproof date and time stamps. They proved that they had showed up each day by having their picture taken with their students.17 Absenteeism dropped by half among teachers in the experimental schools compared with teachers in a randomly selected control group of 60 schools. Student test scores went up, and more students graduated into the next level of education. (I bet the photos are adorable, too!)
Naked Statistics: Stripping the Dread from the Data - Wheelan, Charles Posição 4239-4246 - Seu destaque na página 250 | Adicionado na data segunda-feira, 20 de maio de 2013, 10:31:02
Permalink Share Paper Clasic Modern +Kuotes
But hold on. Let?s not fire anybody yet. The Air Force Academy study had another relevant finding?about student performance over a longer horizon. Carrell and West found that in math and science the students who had more experienced (and more highly credentialed) instructors in the introductory courses do better in their mandatory follow-on courses than students who had less experienced professors in the introductory courses. One logical interpretation is that less experienced instructors are more likely to ?teach to the test? in the introductory course. This produces impressive exam scores and happy students when it comes to filling out the instructor evaluation. Meanwhile, the old, crusty professors (whom we nearly fired just one paragraph ago) focus less on the exam and more on the important concepts, which are what matter most in follow-on courses and in life after the Air Force Academy. Clearly we need to evaluate teachers and professors. We just have to make sure that we do it right. The long-term policy challenge, rooted in statistics, is to develop a system that rewards a teacher?s real value added in the classroom.
Naked Statistics: Stripping the Dread from the Data - Wheelan, Charles Posição 4223-4232 - Seu destaque na página 249 | Adicionado na data segunda-feira, 20 de maio de 2013, 10:26:54
Permalink Share Paper Clasic Modern +Kuotes
Scott Carrell and James West, professors at the University of California at Davis and the Air Force Academy, exploited this elegant arrangement to answer one of the most important questions in higher education: Which professors are most effective?15 The answer: The professors with less experience and fewer degrees from fancy universities. These professors have students who typically do better on the standardized exams for the introductory courses. They also get better student evaluations for their courses. Clearly these young, motivated instructors are more committed to their teaching than the old, crusty professors with PhDs from places like Harvard. The old guys must be using the same yellowing teaching notes that they used in 1978; they probably think PowerPoint is an energy drink?except that they don?t know what an energy drink is either. Obviously the data tell us that we should fire these old codgers, or at least let them retire gracefully.
Naked Statistics: Stripping the Dread from the Data - Wheelan, Charles Posição 4216-4223 - Seu destaque na página 249 | Adicionado na data segunda-feira, 20 de maio de 2013, 10:25:55
Permalink Share Paper Clasic Modern +Kuotes
the case of the New York City teacher ratings, principals in the system had been prepped on the appropriate use of the value-added data and the inherent limitations. The public did not get that briefing. As a result, the teacher assessments are too often viewed as a definitive guide to the ?good? and ?bad? teachers. We like rankings?just think U.S. News & World Report college rankings?even when the data do not support such precision.
Naked Statistics: Stripping the Dread from the Data - Wheelan, Charles Posição 4206-4209 - Seu destaque na página 248 | Adicionado na data segunda-feira, 20 de maio de 2013, 10:23:09
Permalink Share Paper Clasic Modern +Kuotes
In 2012, New York City took the plunge and published ratings of all 18,000 public school teachers on the basis of a ?value-added assessment? that measured gains in their students? test scores while taking into account various student characteristics.12 The Los Angeles Times published a similar set of rankings for Los Angeles teachers in 2010. In both New York and LA, the reaction has been loud and mixed. Arne Duncan, the U.S. secretary of education, has generally been supportive of these kinds of value-added assessments. They provide information where none previously existed. After the Los Angeles data were published, Secretary Duncan told the New York Times, ?Silence is not an option.? The Obama administration has provided financial incentives for states to develop value-added indicators for paying and promoting teachers. Proponents of these evaluation measures rightfully point out that they are a huge potential improvement over systems in which all teachers are paid according to a uniform salary schedule that gives zero weight to any measure of performance in the classroom. On the other hand, many experts have warned that these kinds of teacher assessment data have large margins of error and can deliver misleading results. The union representing New York City teachers spent more than $100,000 on a newspaper advertising campaign built around the headline ?This Is No Way to Rate a Teacher.?13 Opponents argue that the value-added assessments create false precision that will be abused by parents and public officials who do not understand the limitations of this kind of assessment. This appears to be a case where everybody is right?up to a point. Doug Staiger, an economist at Dartmouth College who works extensively with value-added data for teachers, warns that these data are inherently ?noisy.? The results for a given teacher are often based on a single test taken on a single day by a single group of students. All kinds of factors can lead to random fluctuations?anything from a particularly difficult group of students to a broken air-conditioning unit clanking away in the classroom on test day. The correlation in performance from year to year for a single teacher that uses these indicators is only about .35. (Interestingly, the correlation in year-to-year performance for Major League baseball players is also around .35, as measured by batting average for hitters and earned run average for pitchers.)14
Naked Statistics: Stripping the Dread from the Data - Wheelan, Charles Posição 4184-4203 - Seu destaque na página 248 | Adicionado na data segunda-feira, 20 de maio de 2013, 10:20:59
Permalink Share Paper Clasic Modern +Kuotes
Test scores give us an objective measure of student performance. Yet we know that some students will do much better on standardized tests than others for reasons that have nothing to do with what is going on inside a classroom or a school. The seemingly simple solution is to evaluate schools and teachers on the basis of the progress that their students make over some period of time. What did students know when they started in a certain classroom with a particular teacher? What did they know a year later? The difference is the ?value added? in that classroom.
Naked Statistics: Stripping the Dread from the Data - Wheelan, Charles Posição 4175-4179 - Seu destaque na página 246 | Adicionado na data segunda-feira, 20 de maio de 2013, 10:18:15
Permalink Share Paper Clasic Modern +Kuotes
Autism rates did not decline when thimerosal was removed from the MMR vaccine, nor are autism rates lower in countries that never used this vaccine. Nonetheless, the false connection persists, which has caused some parents to refuse to vaccinate their children. Ironically, this offers no protection against autism while putting children at risk of contracting other serious diseases (and contributing to the spread of those diseases in the population).
Naked Statistics: Stripping the Dread from the Data - Wheelan, Charles Posição 4167-4170 - Seu destaque na página 246 | Adicionado na data segunda-feira, 20 de maio de 2013, 10:14:38
Permalink Share Paper Clasic Modern +Kuotes
An autism spectrum disorder often appears suddenly between a child?s first and second birthdays. This has led to a widespread belief that childhood vaccinations, particularly the triple vaccine for measles, mumps, and rubella (MMR), are causing the rising incidence of autism. Dan Burton, a member of Congress from Indiana, told the New York Times, ?My grandson received nine shots in one day, seven of which contained thimerosal, which is 50 percent mercury as you know, and he became autistic a short time later.?11
Naked Statistics: Stripping the Dread from the Data - Wheelan, Charles Posição 4162-4166 - Seu destaque na página 246 | Adicionado na data segunda-feira, 20 de maio de 2013, 10:13:51
Permalink Share Paper Clasic Modern +Kuotes
As usual, a simple comparison between the students who attend summer school and those who do not would be worse than useless. The students who attend summer school are there because they are struggling. Even if the summer school program is highly effective, the participating students will probably still do worse in the long run than the students who were not required to take summer school. What we want to know is how the struggling students perform after taking summer school compared with how they would have done if they had not taken summer school. Yes, we could do some kind of controlled experiment in which struggling students are randomly selected to attend summer school or not, but that would involve denying the control group access to a program that we think would be helpful. Instead, the treatment and control groups are created by comparing those students who just barely fell below the threshold for summer school with those who just barely escaped it. Think about it: the students who fail a midterm are appreciably different from students who do not fail the midterm. But students who get a 59 percent (a failing grade) are not appreciably different from those students who get a 60 percent (a passing grade). If those who fail the midterm are enrolled in some treatment, such as mandatory tutoring for the final exam, then we would have a reasonable treatment and control group if we compared the final exam scores of those who barely failed the midterm (and received tutoring) with the scores of those who barely passed the midterm (and did not get tutoring).
Naked Statistics: Stripping the Dread from the Data - Wheelan, Charles Posição 4018-4029 - Seu destaque na página 238 | Adicionado na data segunda-feira, 20 de maio de 2013, 09:44:56
Permalink Share Paper Clasic Modern +Kuotes
Whatever happened after the tax cut cannot be attributed solely to the tax cut. The challenge with any ?before and after? kind of analysis is that just because one thing follows another does not mean that there is a causal relationship between the two.
Naked Statistics: Stripping the Dread from the Data - Wheelan, Charles Posição 3991-3992 - Seu destaque na página 236 | Adicionado na data segunda-feira, 20 de maio de 2013, 09:41:18
Permalink Share Paper Clasic Modern +Kuotes
Students who attended more selective colleges earned roughly the same as students of seemingly similar ability who attended less selective schools. The one exception was students from low-income families, who earned more if they attended a selective college or university. The Dale and Krueger approach is an elegant way to sort out the treatment effect (spending four years at an elite institution) from the selection effect (the most talented students are admitted to those institutions). In a summary of the research for the New York Times, Alan Krueger indirectly answered the question posed in the title of this chapter, ?Recognize that your own motivation, ambition, and talents will determine your success more than the college name on your diploma.?8
Naked Statistics: Stripping the Dread from the Data - Wheelan, Charles Posição 3977-3983 - Seu destaque na página 235 | Adicionado na data segunda-feira, 20 de maio de 2013, 09:10:21
Permalink Share Paper Clasic Modern +Kuotes
(A 2008 study by PayScale.com found that the median pay for Dartmouth graduates with ten to twenty years of work experience was $134,000, the highest of any undergraduate institution; Princeton was second with a median of $131,000.)6 As I hope you realize by this point, these impressive numbers tell us absolutely nothing about the value of a Dartmouth or Princeton education. Students who attend Dartmouth and Princeton are talented when they apply; that?s why they get accepted. They would probably do well in life no matter where they went to college.
Naked Statistics: Stripping the Dread from the Data - Wheelan, Charles Posição 3959-3964 - Seu destaque na página 233 | Adicionado na data segunda-feira, 20 de maio de 2013, 09:01:02
Permalink Share Paper Clasic Modern +Kuotes
Beginning in 1985, Tennessee?s Project STAR did a controlled experiment to test the effects of smaller classes.3 (Lamar Alexander was governor of Tennessee at the time; he later went on to become secretary of education under President George H. W. Bush.) In kindergarten, students in seventy-nine different schools were randomly assigned to either a small class (13?17 students), a regular class (22?25 students), or a regular class with both a regular teacher and a teacher?s aide. Teachers were also randomly assigned to the different classrooms. Students stayed in the class type to which they were randomly assigned through third grade. Assorted life realities chipped away at the randomization. Some students entered the system in the middle of the experiment; others left. Some students were moved from class to class for disciplinary reasons; some parents lobbied successfully to have students moved to smaller classes. And so on. Still, Project STAR remains the only randomized test of the effects of smaller classes. The results turned out to be statistically and socially significant. Overall, students in the small classes performed .15 standard deviations better on standardized tests than students in the regular-size classes; black students in small classes had gains that were twice as large. Now the bad news. The Project STAR experiment cost roughly $12 million. The study on the effect of prayer on postsurgical complications cost $2.4 million. The finest studies are like the finest of anything else: They cost big bucks.
Naked Statistics: Stripping the Dread from the Data - Wheelan, Charles Posição 3906-3918 - Seu destaque na página 231 | Adicionado na data segunda-feira, 20 de maio de 2013, 08:52:17
Permalink Share Paper Clasic Modern +Kuotes
Here is how Jonathan Klick and Alexander Tabarrok, researchers at the University of Pennsylvania and George Mason University, respectively, studied how putting more police officers on the street affects the crime rate. Their research strategy made use of the terrorism alert system. Specifically, Washington, D.C., responds to ?high alert? days for terrorism by putting more officers in certain areas of the city, since the capital is a natural terrorism target. We can assume that there is no relationship between street crime and the terrorism threat, so this boost in the D.C. police presence is unrelated to the conventional crime rate, or ?exogenous.? The researchers? most valuable insight was recognizing the natural experiment here: What happens to ordinary crime on terrorism ?high alert? days? The answer: The number of crimes committed when the terrorism threat was Orange (high alert and more police) was roughly 7 percent lower than when the terrorism threat level was Yellow (elevated alert but no extra law enforcement precautions). The authors also found that the decrease in crime was sharpest in the police district that gets the most police attention on high-alert days (because it includes the White House, the Capitol, and the National Mall). The important takeaway is that we can answer tricky but socially meaningful questions?we just have to be clever about it. Here are some of the most common approaches for isolating a treatment effect.
Naked Statistics: Stripping the Dread from the Data - Wheelan, Charles Posição 3845-3855 - Seu destaque na página 227 | Adicionado na data segunda-feira, 20 de maio de 2013, 08:25:20
Permalink Share Paper Clasic Modern +Kuotes
John Ioannidis, a Greek doctor and epidemiologist, examined forty-nine studies published in three prominent medical journals.8 Each study had been cited in the medical literature at least a thousand times. Yet roughly one-third of the research was subsequently refuted by later work. (For example, some of the studies he examined promoted estrogen replacement therapy.) Dr. Ioannidis estimates that roughly half of the scientific papers published will eventually turn out to be wrong.9 His research was published in the Journal of the American Medical Association, one of the journals in which the articles he studied had appeared. This does create a certain mind-bending irony: If Dr. Ioannidis?s research is correct, then there is a good chance that his research is wrong.
Naked Statistics: Stripping the Dread from the Data - Wheelan, Charles Posição 3786-3792 - Seu destaque na página 223 | Adicionado na data segunda-feira, 20 de maio de 2013, 08:10:04
Permalink Share Paper Clasic Modern +Kuotes
Even the results of clinical trials, which are usually randomized experiments and therefore the gold standard of medical research, should be viewed with some skepticism. In 2011, the Wall Street Journal ran a front-page story on what it described as one of the ?dirty little secrets? of medical research: ?Most results, including those that appear in top-flight peer-reviewed journals, can?t be reproduced.?7 (A peer-reviewed journal is a publication in which studies and articles are reviewed for methodological soundness by other experts in the same field before being approved for publication; such publications are considered to be the gatekeepers for academic research.) One reason for this ?dirty little secret? is the positive publication bias described in Chapter 7.
Naked Statistics: Stripping the Dread from the Data - Wheelan, Charles Posição 3774-3780 - Seu destaque na página 223 | Adicionado na data segunda-feira, 20 de maio de 2013, 08:05:37
Permalink Share Paper Clasic Modern +Kuotes
And then, while millions of women were being prescribed hormone replacement therapy, estrogen was subjected to the most rigorous form of scientific scrutiny: clinical trials. Rather than searching a large data set like the Nurses? Health Study for statistical associations that may or may not be causal, a clinical trial consists of a controlled experiment. One sample is given a treatment, such as hormone replacement; another sample is given a placebo. Clinical trials showed that women taking estrogen had a higher incidence of heart disease, stroke, blood clots, breast cancer, and other adverse health outcomes. Estrogen supplements did have some benefits, but those benefits were far outweighed by other risks. Beginning in 2002, doctors were advised not to prescribe estrogen for their aging female patients. The New York Times Magazine asked a delicate but socially significant question: How many women died prematurely or suffered strokes or breast cancer because they were taking a pill that their doctors had prescribed to keep them healthy? The answer: ?A reasonable estimate would be tens of thousands.?3
Naked Statistics: Stripping the Dread from the Data - Wheelan, Charles Posição 3609-3617 - Seu destaque na página 213 | Adicionado na data segunda-feira, 20 de maio de 2013, 00:19:01
Permalink Share Paper Clasic Modern +Kuotes

's Books


Calder%80%A0%A6%F3n%20y%20Szmukler%20-%20Cultura%20pol%80%A0%A6%EDtica%20y%20desarrollo Calderon 34 Kuotes ETICA Y LIDERAZGO EMPRESARIAL GBosch 32 Kuotes GTZ NORTE POTOSI Carlos Balderrama Mariscal 82 Kuotes Estudio de las políticas públicas VILLANUEVA 44 Kuotes How the Mind Works Steven Pinker 64 Kuotes SEGURIDAD ALIMENTARIA NUTRICIONAL EN BOLIVIA Administrador 32 Kuotes Why We Get Fat Gary Taubes 232 Kuotes Semanal Fr 87 Kuotes Kürk Mantolu Madonna Sabahattin Ali 43 Kuotes KindleSEO1 summa 132 Kuotes Ibn Verga. Vara de Juda Autor desconocido 45 Kuotes libro_de_chistes CRQLL 62 Kuotes @Long Articles: Sunday, Dec. 30 Instapaper 49 Kuotes Instapaper: Tuesday, May. 21 Instapaper 46 Kuotes luces-de-bohemia Desconocido 71 Kuotes The Power of Now Tolle, Eckhart 242 Kuotes Tristram Shandy Spanish Edition 32 Kuotes OLSEN-La-Cultura-Material-Despues-Del-Texto administrador 47 Kuotes Kuote Coord. Cómputo 302 Kuotes Pocket calibre 92 Kuotes Instapaper: Friday, Jun. 22 Instapaper 39 Kuotes DH I - CLASE 7 Erik Martinelly 56 Kuotes Copia de PDM PUNATA primera parte LINUX 62 Kuotes Flavia Marco 05 de octubre 2012 TULLOA 62 Kuotes Bourdieu Pierre - Sociología y Cultura - ISBN 968-419-852-6 Daniel 302 Kuotes Resilience Ann Marie Healy and Andrew Zolli 57 Kuotes PB006 Ismeretlen 151 Kuotes Como_se_hace_una_tesis Eco 226 Kuotes Influence Cialdini, Robert B. 421 Kuotes Introduccion al narcisismo Freud 93 Kuotes Protein Power: The High-Protein/Low-Carbohydrate Way to Lose Weight, Feel Fit, and Boost Your Health--In Just Weeks! Michael R. Eades; Mary Dan Eades 178 Kuotes The Body Language Rules Judi James 52 Kuotes ESTADO DEL ARTE QUINUA EN BOLIVIA 104 Kuotes Changing Signs of Truth: A Christian Introduction to the Semiotics of Communication Crystal L. Downing 142 Kuotes Las tres hijas de su madre Pierre Louÿs 128 Kuotes El medio pelo en la sociedad argentina Arturo Jauretche 45 Kuotes The Way of the Superior Man: A Spiritual Guide to Mastering the Challenges of Women, Work, and Sexual Desire David Deida 76 Kuotes Read more articles conversion-rate-experts.com 129 Kuotes Moonwalking with Einstein: The Art and Science of Remembering Everything Joshua FOER 40 Kuotes Agilmente Bachrach, Estanislao 90 Kuotes KindlePB3 summa 194 Kuotes Steve Jobs Walter Isaacson 220 Kuotes 47_GarciaSanchez NUEVA GESTIÓN PÚBLICA 46 Kuotes Pobreza. Un Glosario internacionall CLACSO 387 Kuotes Aprenda A Meditar c.1.1 124 Kuotes La troika y los 40 ladrones Santiago Camacho 38 Kuotes SEO, Blogging etc: Sunday, Dec. 30 Instapaper 51 Kuotes The Natural: How to Effortlessly Attract the Women You Want La Ruina, Richard 331 Kuotes Gaudium et Spes Documentos del CVII 116 Kuotes Quarto Livro de Crónicas LOBO ANTUNES, ANTÓNIO 90 Kuotes