This week our class was assigned a video to watch entitled Don’t Be Fooled by Bad Statistics. In this video we were given three forms of bad statistics. These were poorly collected data, leading questions, and finally misuses of the center. Along with these three forms, we were informed on something called the Michael Jordan Fallacy. This short 5-minute video really opened up my eyes as to how easy it truly is to either create a poor statistic, or read into one in an entirely wrong way. Poorly collected data occurs when you don’t get the full perspective of all individuals for a data set. According to the video (2010), an example of this would be calling individuals to help create a statistic, but only calling in the middle of the day. In turn only stay at home moms answered, and because of this your data set would be skewed (Dressler, 2010). This can not only lead to misleading results but wasted time and money. Leading questions was the second form of bad statistics. In order to prevent this, you as the interviewer must word a question to induce a non biased response. The biggest issue regarding this form of bad statistics is that many people when asked a question, will more than likely …show more content…
In this form of bad statistics, it can all be avoided as long as use the numbers collected correctly to create a statistic. Many times people will use numbers that are accurate but in an inaccurate manner. This will lead to not only a bad statistic, but a false claim. An example of this talked about in the video was called the Michael Jordan Fallacy. According to the video (2010), this is when an outlier is used to create a statistic. The example given was the salary of Geography majors first year out of college at UNC. The problem with the number was that they used the salary of graduate and NBA superstar Michael Jordan (Dressler, 2010). Instead of using the median, they used the mean. This in turn created a misleading
The example of basketball makes the idea of the standards gap easier to fathom for readers who might not completely understand the issue. The analogy also puts into perspective the way minority students may feel when different expectations are set for them. Comparisons between one idea and another are also made in “Torture Might Work.” Pitts postulates that “...if you wanted to stop that carnage, it would be simple. Just make drunk driving a capital crime with instant punishment...
Numbers can be deceiving and at the same time provide a close analysis of the data which can yield valuable information. As identified in the chart above Thornton Fractional South High School is performing below average as compared to the Illinois State averages for both the ACT and PSAE. However, when broken down by demographics there is another story that becomes abundantly clear. Some of our students are performing well on the state tests while others are fairing very poorly. The White demographic in our building is performing significantly better than either the Black...
Joel Best’s Damned Lies and Statistics is a book all about recognizing statistics that are legitimate and others that are really quite horrible. The goal of this book is not that the average every day person be able to read a statistical table from a scholarly journal, but rather that anyone could personally value a statistic he or she may come across in a newspaper article or on a news program. Best was essentially effective in achieving his goal; however, he was effective to the point of overdoing his job of showing that there are bad statistics which give readers cause to evaluate them outside of hearing them on the news.
The ability for all children from varying walks of life to receive a well-rounded education in America has become nothing more than a myth. In excerpt “The Essentials of a Good Education”, Diane Ravitch argues the government’s fanatical obsession with data based on test scores has ruined the education system across the country (107). In their eyes, students have faded from their eyes as individual hopefully, creative and full of spirit, and have become statistics on a data sheet, percentages on a pie chart, and numbers calculated to show the intelligence they have from filling out bubbles in a booklet. In order for schools to be able to provide a liberal education, they need the proper funding, which comes from the testing.
Overall, it was very difficult for me to find valid responses to his arguments. This documentary has left me with three questions: what is the most logical solution to fix this problem, how to prevent this problem from occurring in the future, and does the increase in population affect the data in any way?
The films effective use of statistics undoubtedly enhances its credibility. For example, the film states that one in every four college students will not make it to their sophomore
Evans, Donia. "The Case Against Standardized Tests." The Meridian Star. 24 Nov. 2013. The Meridian Star. 01 Dec. 2013 .
These facts also relate to the poor quality to which standardized testing has fallen and directly to the poor quality of education received in our public school systems. These tests ...
"Study Finds Standardized Tests Hurting Students." Chicago Tribune. 16 Oct. 1992. Web. 23 Apr. 2014.
Alfie Kohn, author of The Case against Standardized Testing, recalls a specific incident of how children are being cheated out of valuable class time. He states that a school in Massachusetts used a remarkable unit, for a middle-school class, where students chose an activity and extensively researched it, and reported or taught, it to the class. This program has had to be removed from the course curriculum in order to devote enough time to teaching prescribed material for their standardized tests.
indicates towards a fraud. On eof the most important qualities or benefits of this model is that it understands the pattern in the data and generates the result. Once the result is generated the model checks as to how close was the result from the actual results. Based on this analysis the model adjusts its weights to give an accurate result the next time. Once this model has been trained to give accurate results, it can be used to analyze other data as well. Even when Neural Networks are widely accepted, they are not really used that much in the marketing industry merely by the fact that data preparation for this model is very complex time consuming as compared to the Regression Analysis. The marketers are much comfortable using the Regression Analysis over Neural Networks because of the ease of interpreting the results in the Regression Analysis.
...en Goldachre. (2011). The statistical error that just keeps on coming. Available: http://www.guardian.co.uk/. Last accessed 10/12/2011.
This chapter taught me the importance of understanding statistical data and how to evaluate it with common sense. Almost everyday we are subjected to statistical data in newspapers and on TV. My usual reaction was to accept those statistics as being valid. Which I think is a fair assessment for most people. However, reading this chapter opens my eyes to the fact that statistical data can be very misleading. It shows how data can be skewed to support a certain group’s agenda. Although most statistical data presented may not seem to affect us personally in our daily lives, it can however have an impact. For example, statistics can influence the way people vote on certain issues.
Primary source data collection relies on structured interviews and questionnaires, which many argue do not offer enough fluidity to relate to everyday lives and therefore are not valid research tools (Bryman 2001, p.77). Critics also continue to associate positivism and quantitative methods failing to see that quantitative researchers do not apply the scientific method to all data and can account for influencing variables (Bryman 2001, p.77; Matthews and Ross 2010, p.29). Quantitative methods in the social sciences were highlighted by the positivist epistemology during the mid 20th century; however, Jones (2010) explains how the principles of positivist epistemology are not fully consistent with modern quantitative methods in the social sciences (Matthews and Ross 2010, p.27). Positivist research parallels that of the natural sciences, where data collection and hypothesis testing is conducted from information that can be observed and recorded by the senses (Matthews and Ross 2010, p.27). Because information can only be observed, positivists look for regularities and explain causation when one event regularly follows another, which is why many will criticize quantitative methods if they associate them with the positivist approach to research (Jones
...rue and lie. It depends on how it is used, collected and analyzed. Therefore, readers should understand what reliable statistics are. Yet, statistics are very important for researchers, scientists, students, employers and individuals to make decisions as well as to evidence any claims or scientific theories.