ellies1mpson


“Are there benefits to gaining a strong statistical background?”
September 30, 2011, 11:01 pm
Filed under: Uncategorized

Statistics are a powerful tool for condensing  and analising large quantites of data.   They are standardised techniques that are recognisable and understood throughout the scientific community.  They enable information to be presented and interpreted in both an accurate and informative way.   A strong statistical background for a study can give evidence to either  support or refute a hypothesis.   But be aware statistics can be manipulated.  The advertsing industry is a perfect example of this (see link below.)

htt.p://lipstick-and-pearls.blogspot.com/2011/07/how-cosmetic-adverts-manipulate-sample.html

As the link shows one method of manipulation, a small sample size is not representative to the entire population.   The Avon study consisted of 52 participants,  75% of whom agree with the products claims.  This relates to  39 of the 52 participants .  Therefore with a UK population of 60,000,000, only 0.000065% of women in the UK agree with the products’ claims.  The smaller the sample size, the less people need to agree to produce a large percentage.

Statistics are often selectively reported with a bias towards data that supports the hypothesis while omitting  other data  that contradicts the hypothesis.  Often inferences and conclusions are much more sweeping than statistical analysis surgests.  Researchers and reviewers should consider the bigger picture taking  into account all the procedings of a study from the research methods used, participants, analysis and interpretation of data and also who is conducting the research and who has commisioned the research.  So with this bigger  picture in mind  a strong statistical background goes along way to lending strength to a therory.

 

 

Advertisements

5 Comments so far
Leave a comment

I like how you demonstrated just how small the sample is in comparison to the rest of the population. It just shows how much advertisers manipulate statistics to make their product sell and look much more effective then other leading competitors. So in this case having knowledge of statistics is a great advantage, you unlike many others would be able to spot the manipulated statistics and this is a benefit.

Comment by itsstats3453

I agree that having a strong statistical background is very helpful when trying to identify statistical data that has been manipulated in favour of certain products, what I am worried about is that people without a strong understanding of statistics may begin to distrust the data shown on advertisements because they know it isn’t accurate but then they will begin to distrust data from reputable sources like journals as well because they think they all do things the same way. It would be a real shame if people started to disregard important staistical data because of a few adverts with shoddy data about Gillettes new closest ever shave.

Comment by statisticalperrin

I enjoyed your use of an everyday example of how statistics is used. I especially like how you evaluated it to show that it is important to look into how research is conducted to ensure that you are getting the whole picture and the statistic is all how it seems.

As you have noted having a strong statistical background can be beneficial but there are also negatives. Statistics is good at interpreting all aspects of the data and ensuring the results and not only reliable and valid (by using tests such as ANOVA and T test) but they can also tell you if your results are significant ( by looking at the P value). However by simply using certain participants or presenting the statistics in a certain way can manipulate how people read and therefore interpret the results.

Comment by serenapsychology

I agree with whats being said here, but refering to the comment above shouldn’t we still question how statistics from reputable sources came to be? As they could still be interpreting their data incorrectly either intentially or unintentially.

Comment by samanthakirby

The link and evaluation touch on a significant issue in statistics, and I like the fact that you focused on how a strong statistical background can help you understand and possibly improve these issues through statistical analysis of your own.
Looking at the above comment, I thought that statistics is not a part of gathering data but the analysing processes. Data that is not from a valid source will never be valid, no matter how good statistics could ever be.

Comment by psud30stats




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: