Skip to content
May 15, 2011 / rohanmsmith

The Media’s Misinterpretation of Statistics

Scientific research and the media go hand in hand. Without one another, both are severely restricted. For researchers, what good is a ground-breaking discovery if you have no way to get your findings to the general public? The scientific community rely heavily upon the media for this reason.

Firstly lets discuss why are statistics important. Statistics quantify information, and make it more easily understood. They allow a higher level of detail to be portrayed, and add credibility to research. With this in mind, lets look at two statements.

  1. Some university students drive to university.
  2. On average, 50% of university students drive to university. **

Adding the percentage value transforms the statement from common sense, to something relevant and meaningful. Statistics are an invaluable component in scientific research, and one that must be given considerable thought.

**Disclaimer: This is purely for illustrative purposes, the actual number is likely to be different.

Statistics can be confusing however, and as such it is vital for them to be reported accurately. A complication is that the media will often not fully understand details of the research. Resultantly, it is important that research is presented both accurately, and at a level that can be understood. This responsibility falls squarely upon the researcher. Given these requirements are fulfilled by researcher, accurate reporting statistics is the responsibility of the media. Journalists hold an important role in communicating to the public, and must ensure they present details accurately.

Often it is not the actual statistics that are debated, but the conclusions made from the research. Scientists are accustomed to making conclusions based on research, but this is a skill less practised in journalism. This is the case in the article “Can breastfeeding halt obesity – or is the media misreading the research?”.

A recent study found that 32 percent of babies are obese, a shocking statistic. The original article attributed this to a combination of bad food, and eating solids too early. Several media sources including MSNBC and AOL Health, came to the conclusion that mothers should breastfeed rather than use formula. Whilst the statistics were reported accurately, the resulting conclusions were anything but. Given that the general public are far more likely to see the article from the press than the original study, this is worrying. In this case, misinforming the general public on a large scale is the outcome – obviously undesirable. Or is it?

Political tacticians are not in search of scholarly truth or even simple accuracy. They are looking for ammunition to use in the information wars. Data, information, and knowledge do not have to be true to blast an opponent out of the water.

In my research on the topic, I came across the above quote. It introduces the concept that misreporting statistics, or making incorrect conclusions may not be accidental. There are many situations where adjusting conclusions could be done deliberately for personal reasons. For example, if the owner of a newspaper had a family member who was the CEO of a fast food company. Directing the attention away from the bad food causing obesity in babies and using a scapegoat (baby formula) would be beneficial for the newspaper owner. Far-fetched? Maybe, but its definitely something to think about.

[1] Goldin, R. (2011). Can breastfeeding halt obesity – or is the media misreading the research?. STATS.org

Image Credit: http://davidmlane.com/ben/cartoons.html

Advertisements

4 Comments

Leave a Comment
  1. piyasd01 / May 16 2011 2:44 am

    Hi Rohan,

    I thoroughly enjoyed reading your blog and the accompanying article “Can breastfeeding halt obesity – or is the media misreading the research?”

    I like the way you made a simple comparison between the use and non-use of statistics to add credibility to a news item with reference to driving to university. It is important to use such knowledge (statistics) when a journalist reports the findings of a study but should not get bogged down in the details; rather, focus on the main message.

    You raised some good points with regards to who is responsible to accurately present statistics. I agree with you in that it is the scientist’s (researcher) job to make sure the statistics are reported accurately and in a manner that the audience will understand. They also need to make sure that the final message is not lost to the statistics that are found in the study. In saying that, the journalist needs to play a much important role in communicating that information to the public in an accurate manner. Therefore, I believe that journalists should report statistics accurately but also concentrate on the main message a research study is trying to send out.

    Lastly, I would have liked to see you refer to actual examples (or links to a website) where the media misrepresented information from a study (other than the article used for this blog). Nonetheless, an interesting topic to blog about.

    Regards,
    Devinka

  2. rohanmsmith / May 17 2011 8:54 am

    Hi Devinka,

    Thanks for the comment, I’m glad you enjoyed reading my post.

    You make a good point, my argument would have been considerably stronger with specific examples or links of the media misrepresenting information.

    As we’ve both said, accurately reporting research and statistics needs to be a collaborative effor between scientists and journalists. With a ‘middle man’ (in this case the journalist), I guess the loss of clarity is a fairly big issue, kind of like in a game of Chinese Whispers (http://en.wikipedia.org/wiki/Chinese_whispers).

    I guess the way around this is consultation between researcher and scientist, however this often is not possible. Journalists aren’t trained in the specifics of scientific research or statistics, and this is something researchers need to be aware of.

    Rohan

  3. tim16 / May 19 2011 7:47 am

    Hi Rohan,
    I think you did a great job clarifying the importance of statistics and presenting the roles of both researchers and journalists. I believe it is an ethical obligation for the researcher to both make the correct conclusions when analysing their data and present them using language that non-scientists (ie journalists) can understand.
    Your final point was a good addition to your blog and an effective note to end on. I agree that many organisations have their own agenda that is supported by journalists who work for them and twist the original message of studies, such as this breastfeeding research.
    An example of when a researcher has made dodgy conclusions regarding their results is highlighted by Dr Joe Schwartz in his essay “Lies, Damned Lies, and Statistics”:

    “Take, for example, the recent study that showed a 30 percent increase in risk of breast cancer among women taking estrogen supplements. Sounds terribly frightening! But consider that within a ten-year period, only 3 to 4 percent of menopausal women will be struck by breast cancer. A 30 percent increase in this risk doesn’t seem quite as impactive. Putting it another way, a postmenopausal woman who takes estrogen reduces her chance of remaining cancer-free from about 96 percent to 95 percent.”

    I suppose some researchers assume journalists wont question their conclusions (because they are unfamiliar with the research) so the researcher’s conclusions are exaggerated etc. Also, a reader should always be aware of the potential misintepretation of statistics, though some reporters would understand that many readers are not aware of this and take advantage of that.

    Cheers,
    Tim

  4. afiza / Jun 6 2011 3:02 pm

    Hi Rohan,

    Reading your post makes me realize the importance of deliver the statistic accurately to the general public. I agree with Devinka that researchers should report their finding in the manner of that the audience will understand. However, not all people can interpret statistic accurately even people who deal with statistic daily also could misinterpret. So the question is how good is the researcher in reporting?
    People most likely misinterpret because they misunderstood the statistical definitions and concepts behind the information that used by the researchers. Thus, one journalist should become familiar with the definitions for terms used by the researchers before reporting it to the public. In my opinion, the best way is to interview the researchers to get more clear picture of what is the research was about.

    Regards
    afiza

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: