Is it the sign of the last few years of hiding the truth http://www.elitetrader.com/vb/showthread.php?s=&threadid=26238&perpage=6&pagenumber=2 "Santa Claus rally and more new highs! Dec 24 2003 (from today's Hotline) Commerce Department data confirmed the incredible 8.2% 3Q GDP growth, providing the Christmas cheer to move NYSE indices to further highs. Consumer spending and sentiment both were announced and very positive, giving added confirmation to investor optimism. Year end often sees a market rally, as bonuses and dividends are invested, but after the strong ...[Subscribe to read more] " "INCREDIBLE" to say the least. It's much easier for Gov today to use "stats" than in the old days (as you will see they didn't need medias to invent virtual reality ) "The value of shares in the Louisiana, or Mississippi stock, had fallen very rapidly, and few indeed were found to believe the tales that had once been told of the immense wealth of that region. A last effort was therefore tried to restore the public confidence in the Mississippi project. For this purpose, a general conscription of all the poor wretches in Paris was made by order of government. Upwards of six thousand of the very refuse of the population were impressed, as if in time of war, and were provided with clothes and tools to be embarked for New Orleans, to work in the gold mines alleged to abound there. They were paraded day after day through the streets with their pikes and shovels, and then sent off in small detachments to the out-ports to be shipped for America. Two-thirds of them never reached their destination, but dispersed themselves over the country, sold their tools for what they could get, and returned to their old course of life. In less than three weeks afterwards, one-half of them were to be found again in Paris. The manoeuvre, however, caused a trifling advance in Mississippi stock. Many persons of superabundant gullibility believed that operations had begun in earnest in the new Golconda, and that gold and silver ingots would again be found in France."
It seems that the distrust is general and in other countries also http://www.archive.official-documents.co.uk/document/ons/govstat/chap-1.htm Statistics: A Matter of Trust Chapter 1 -------------------------------------------------------------------------------- Introduction 1.1. Reliable official statistics are a cornerstone of democracy and are essential to good public management and accountability. The public, government and Parliament all have a legitimate interest in statistics which provide an objective account of the economy and society, both over time and geographically. Such statistics offer a window on the work and performance of government itself. They also help government in the formulation and evaluation of policies and in the management of services for which they are responsible. It is the responsibility of government to provide reliable official statistics and to ensure the public has confidence in them. 1.2. The current range of UK official statistics is wide, covering all key areas of national life. However, public confidence in the integrity of official statistics has been called into question. <font color=red>Reports by a number of organisations and bodies, including Parliament and the Royal Statistical Society have raised concerns about the quality of statistics and their degree of freedom from political interference. Surveys indicate that the public shares this concern. </font>
Let's use Tchebichev formula (which doesn't assume normal law) which gives the probability that the observed proportion k/n is different from a theorical proportion p; his theorem says that this prob is less than 1/4ne^2 : Pr[|k/n - p|>e] < 1/4ne^2 k=12 n=18 p=0.5 e=12/18-0.5=0.16666 1/4ne^2=1/(4*18*0.17^2)=1/2 = 50% Not conclusive Now what if we also counts others categories: k=17 n=23 p=0.5 e=17/23-0.5=0.23913043478 1/4ne^2=1/(4*23*0.23^2)=1/4.8 = 20% This is more conclusive: there is only 20% of probability that if there was 50% of people that believe in these stats, we got such proportion 17/23=74% of skepticals and undecisive people.
Report from Union of Concerned Scientists Scientific Integrity in Policymaking Executive Summary (PDF) Full Report (PDF) The U.S. government runs on vast amounts of information. Researchers at the National Weather Service gather and analyze meteorological data to know when to issue severe-weather advisories. Specialists at the Federal Reserve Board collect and analyze economic data to determine when to raise or lower interest rates. Experts at the Centers for Disease Control examine bacteria and viral samples to guard against a large-scale outbreak of disease. The American public relies on the accuracy of such governmental data and upon the integrity of the researchers who gather and analyze it. However, at a time when one might expect the federal government to increasingly rely on impartial researchers for the critical role they play in gathering and analyzing specialized data, there are numerous indications that the opposite is occurring. A growing number of scientists, policy makers, and technical specialists both inside and outside the government allege that the Bush administration has suppressed or distorted the scientific analyses of federal agencies to bring these results in line with administration policy. In addition, these experts contend that irregularities in the appointment of scientific advisors and advisory panels are threatening to upset the legally mandated balance of these bodies. The quantity and breadth of these charges warrant further examination, especially given the stature of many of the individuals lodging them. Toward this end, the Union of Concerned Scientists (UCS) undertook an investigation of many of the allegations made in the mainstream media, in scientific journals, and in overview reports issued from within the federal government and by non-governmental organizations. To determine the validity of the allegations, UCS reviewed the public record, obtained internal government documents, and conducted interviews with many of the parties involved (including current and former government officials). Scientific Integrity in Policymaking: An Investigation into the Bush Administration's Misuse of Science presents the finding of this investigation and offers solutions to help restore scientific integrity to the federal policymaking process. Download the full report or the executive summary. http://www.ucsusa.org/global_environment/rsi/page.cfm?pageID=1322
Even some "scientists" cheat with stats in their article (see below this month's article in Scientific mag Nature ) so if supposed scientists cheat how can we expect that politicians / corporates don't do so and at a much more heavy degree when there is no law that can forbid that ? They make law for forbidding citizens to cheat them but not them to cheat citizens haha ! http://www.nature.com/nsu/040531/040531-3.html "Double check casts doubt on science statistics" Errors found in Nature and BMJ papers. 3 June 2004 HELEN PEARSON Statistical errors can skew science. © Photodisc A study highlighting statistical gaffes in scientific literature has brought renewed calls for vigilance among mathematically challenged researchers and journal editors. Statistical tests are sometimes seen as a necessary evil by researchers, who fear their complexity but know that they are needed to test hypotheses. With this aversion in mind, biostatisticians Emili GarcÃa-Berthou and Carles Alcaraz of the University of Girona, Spain, gauged the extent of statistical errors in four volumes of Nature from 2001 (409â412) and a sample of results in two BMJ volumes (322â323) from the same year. The pair used three standard software packages to recalculate 'P values', the parameters by which researchers measure whether a result has statistical significance. Generally a P value of less than 0.05 is taken to be significant and unlikely to have resulted from chance. This may indicate, for example, that blood pressure in a patient group was reduced more by an active drug than by a placebo. In the Nature and BMJ papers, each P value was calculated from two other parameters that are included in the papers. GarcÃa-Berthou and Alcaraz recalculated the P values from these numbers, and found that their results differed from those published in more than 11% of cases. They also found small mistakes, such as rounding errors, in 38% of the Nature papers and 25% of the BMJ ones1. There are small mistakes that may occasionally have big consequences Martin Bland University of York, UK In only 1 case out of 27 did an incorrect P value change a significant result to a non-significant one. But, although minor, some believe that the slip-ups expose a pervasive sloppiness towards statistics in published research. "There are small mistakes that may occasionally have big consequences," says Martin Bland, an expert in medical statistics at the University of York, UK. Philip Campbell, the editor-in-chief of Nature, says the journal will take a closer look at the study's numbers before deciding whether remedial action is needed. He adds that Nature has amended its editing practices since the period covered by the study. Richard Smith, editor of the BMJ, says that one way forward is for researchers or journals to publish more raw data on the Internet, where others would be able to check them.
From the same Nature mag: Scientists behaving badly http://www.nature.com/nsu/040301/040301-9.html Conflicts of interest also rear their head in the report. One journal ran a paper on passive smoking from authors who omitted to mention that they had received funding from the tobacco industry. Further probing revealed that the author had received tobacco company money throughout his career and even lobbied for the industry. In cases where the misconduct concerns medical treatments, the report becomes more disturbing. The editors discuss several studies where medical procedures were run by researchers who did not have proper ethical clearance. One paper revealed that blood samples were taken from healthy babies to set up a control group for a study. This was a painful procedure that the paper's authors later said wouldn't normally be sanctioned for research purposes. The nature of their ethical approval for the procedure was never cleared up. When confronted with such issues, journal editors usually contact the researchers' employers or ethics committees, who may take action. But this is not compulsory. The publishing committee wants to formalize this course of action in a code of ethical conduct for editors. It has published a draft of such a code alongside its report, and a final version should be ready in the next few months. The committee wants all editors of medical journals, including its 180 or so members, to sign up to the code and agree to be bound by the associated disciplinary procedures. Such a code should clarify editors' duties. It should also make clear, if it is not already, which activities are inappropriate. The report describes one bid to persuade an editor to accept a manuscript, in which an anonymous caller offered to buy 1000 reprints of the published paper. "And," the caller added, "I will buy you dinner at any restaurant you choose."