Denta Beauté - all types of health insurance accepted | 1190 Wien, Billrothstraße 29 | Phone:+43 1 369 66 25

Statistics

    https://www.denta-beaute.com/en/dentallexikon-category/a-en/
  • A
  • https://www.denta-beaute.com/en/dentallexikon-category/b-en/
  • B
  • https://www.denta-beaute.com/en/dentallexikon-category/c-en/
  • C
  • https://www.denta-beaute.com/en/dentallexikon-category/d-en/
  • D
  • https://www.denta-beaute.com/en/dentallexikon-category/e-en/
  • E
  • https://www.denta-beaute.com/en/dentallexikon-category/f-en/
  • F
  • https://www.denta-beaute.com/en/dentallexikon-category/g-en/
  • G
  • https://www.denta-beaute.com/en/dentallexikon-category/h-en/
  • H
  • https://www.denta-beaute.com/en/dentallexikon-category/i-en/
  • I
  • https://www.denta-beaute.com/en/dentallexikon-category/j/
  • J
  • https://www.denta-beaute.com/en/dentallexikon-category/k-en/
  • K
  • https://www.denta-beaute.com/en/dentallexikon-category/l-en/
  • L
  • https://www.denta-beaute.com/en/dentallexikon-category/m-en/
  • M
  • https://www.denta-beaute.com/en/dentallexikon-category/n-en/
  • N
  • https://www.denta-beaute.com/en/dentallexikon-category/o-en/
  • O
  • https://www.denta-beaute.com/en/dentallexikon-category/p-en/
  • P
  • https://www.denta-beaute.com/en/dentallexikon-category/r-en/
  • R
  • https://www.denta-beaute.com/en/dentallexikon-category/s-en/
  • S
  • https://www.denta-beaute.com/en/dentallexikon-category/t-en/
  • T
  • https://www.denta-beaute.com/en/dentallexikon-category/u-en/
  • U
  • https://www.denta-beaute.com/en/dentallexikon-category/v-en/
  • V
  • https://www.denta-beaute.com/en/dentallexikon-category/w-en/
  • W
  • https://www.denta-beaute.com/en/dentallexikon-category/x-en/
  • X
  • https://www.denta-beaute.com/en/dentallexikon-category/z-en/
  • Z

Statistics refers to the analysis of data using certain mathematical methods that have been specifically observed. Why is the specific analysis of data important? In this short clip, we cannot transform you into a statistician, but we will use two simple examples to demonstrate the importance of statistics and how results can be manipulated using statistical tricks.
Example 1: Imagine a big city with 1 million inhabitants. In 1860, many people die from tuberculosis. Years pass and mayors come and go in the government building until the year 1980. The current mayor is a very thoughtful man and wants to know if medical care in his city has improved. He chooses death from tuberculosis as an indicator and orders an official study on all deaths from tuberculosis between 1880 and 1980.
His civil servants get to work and soon come up with an evaluation for him. The mayor knows nothing about statistics. Therefore, he interprets the evaluation in a way that demonstrates a continuously decreasing death rate from tuberculosis between 1880 and 1980. He is satisfied with the city’s medical institutions and believes that they must be doing a good job. An expensive new hospital is built.
What he does not realize is that the analytical evaluation of the data has been inaccurately presented. In this analysis, the number of deaths were decimalized, or changed to the decimal system, leading to a distortion of the graphic. In this calculation, the number of deaths should have been presented logarithmically or on a scale that uses a logarithm of the physical quantity.
The numbers are identical, but a different presentation changes the graphic instantly. Now it becomes apparent that the death rate only dropped significantly after 1946. If you take into account that a terrible war had ended in 1945, and people finally had more food and a roof over their heads, the impact of medical institutions on decreasing deaths due to tuberculosis diminishes. Thus, a different presentation of the same statistics makes it more obvious that the construction of a new hospital was not required.
Example 2: Mistakes such as those mentioned in Example 1 can be due to a lack of knowledge, which unfortunately can be intentionally abused. Even scientist are sometimes not above misrepresenting statistics. In 1990, a large pharmaceutical company sent a letter to numerous doctors to play down the side effects of one of its medications, Prozac.
In the letter, the pharmaceutical company claimed that the medication had been tested on more than 11,000 individuals. The doctors were put at ease and kept prescribing the medication without second thoughts. What they did not know was that the number had been faked by skillful manipulation. In reality, the medication had only been tested on 286, and not 11,000 individuals.
Furthermore, only 63 patients had been tested for more than 2 years; the rest of the individuals involved in the study had to stop taking the drug because of its side effects and/or ineffectiveness.
Even today, there is no study that proves the effectiveness of this medication; nevertheless, it is still being prescribed. Since the side effects are significant, the company simply extended the package instruction leaflet.
Such simple examples highlight the importance of being familiar with statistics and studies. All treatment recommendations should be either evidence-based or rely on information from respectable organizations of doctors and scientists, which publish only reliable information.

Statistics