Representation and Bias
Representation and Bias
By
Deborah Callaway
Herzing College Online
W4A1-Reflection Assignment
November 26, 2009
Representation and Bias When creating or reviewing a research study, we need to consider the information and decide if it is representative or biased in order to make clear decisions. When the information or sample is representative, it means that the people studied are like the people who you wish to generalize and it must have the same significant characteristics in the same proportions as the target group. If the information or sample is biased, it means that it does not provide adequate evidence to support the conclusion. A biased sample can also mean that the research organization performing the study has a vested interest in the outcome of the study. An example of representation and bias can be found in the following newspaper article. In Erin Conroy’s article “Something in the Turkey?”, he writes “Eating turkey might make you sleepy, but most Americans are not napping on Thanksgiving, according to a recent survey. Instead, they are sleeping in the next morning and eluding Black Friday discounts. The telephone poll of 1,001 Americans found that 71 percent stay awake on the holiday despite turkey’s soporific power while, curiously, more than half said they know someone who isn’t able to. Contrary to popular thinking, it’s not the turkey’s fault that people tend to feel drowsy after the holiday meal due to an amino acid in turkey that induces fatigue, but experts say it really just results from a combination of eating and drinking too much.” Ipsos Public Affairs on behalf of bedding products Web site SleepBetter.com, between Nov.5 and Nov. 8 conducted the telephone poll. It may be fair to surmise that these researchers are biased because they have a vested interest in the results. And, though the sample size is acceptable, there is not sufficient evidence to show it is random and representative of
By
Deborah Callaway
Herzing College Online
W4A1-Reflection Assignment
November 26, 2009
Representation and Bias When creating or reviewing a research study, we need to consider the information and decide if it is representative or biased in order to make clear decisions. When the information or sample is representative, it means that the people studied are like the people who you wish to generalize and it must have the same significant characteristics in the same proportions as the target group. If the information or sample is biased, it means that it does not provide adequate evidence to support the conclusion. A biased sample can also mean that the research organization performing the study has a vested interest in the outcome of the study. An example of representation and bias can be found in the following newspaper article. In Erin Conroy’s article “Something in the Turkey?”, he writes “Eating turkey might make you sleepy, but most Americans are not napping on Thanksgiving, according to a recent survey. Instead, they are sleeping in the next morning and eluding Black Friday discounts. The telephone poll of 1,001 Americans found that 71 percent stay awake on the holiday despite turkey’s soporific power while, curiously, more than half said they know someone who isn’t able to. Contrary to popular thinking, it’s not the turkey’s fault that people tend to feel drowsy after the holiday meal due to an amino acid in turkey that induces fatigue, but experts say it really just results from a combination of eating and drinking too much.” Ipsos Public Affairs on behalf of bedding products Web site SleepBetter.com, between Nov.5 and Nov. 8 conducted the telephone poll. It may be fair to surmise that these researchers are biased because they have a vested interest in the results. And, though the sample size is acceptable, there is not sufficient evidence to show it is random and representative of
References: Conroy, E. (2009). Relax without getting the ax/ fewer turkey naps. Retrieved November 26, 2009, from http://www.grovesun.com/articles/2009/11/25/health/health/doc4b0c2dcdccaab428307893.txt.