Posts archived in Psychological research (inferential statistics)


2 comments

Where’s the evidence?

January 2, 2012 by .

The UK-based charity Science about Science aims to equip people to make sense about the scientific and medical claims in public discussions. Part of your study of psychology has similar aims – to teach you to make educated assessments of information presented to you.

Sense about Science gets particularly annoyed by the things said by celebrities. So every year they publish some of the claims made by people who know very little. For example the US reality TV personality Nicole ‘Snooki’ Polizzi said: “I don’t really like the beach. I hate sharks, and the water’s all whale sperm. That’s why the ocean’s salty.” No Snooki, the ocean is not salty because of whale sperm. And Simon Cowell also made the bad science list in 2011. Read these and more here.

You might also be interested in some of their other publications, such as this one about peer review.

0 comments

Doing your own qualitative research

October 19, 2011 by .

Here’s a useful resource if you want to practice qualitative research with your students. There are five interviews with undergraduate students along with a users guide, all prepared by The Higher Education Academy Psychology Network.

0 comments

New research on the effects of day care – not all it seems

September 25, 2011 by .

In the last month a report appeared in the Daily Mail entitled ‘Putting baby in nursery could raise its risk of heart disease because it sends levels of stress soaring‘. This conclusion is based on a report by Aric Sigman, a psychologist who has previously been attacked by Ben Goldacre for his bad science (see here). Sigman’s day care claims have come in for a blistering attack by Bishopblog ‘How to become a celebrity scientific expert’. It’s a great example of why we need to understand science – because it means we are less gullible.

In brief Sigman bases his conclusions on accepted research that has shown that children in day care have raised levels of the stress hormone cortisol. But he then assumes that such increased levels later have negative consequences. In fact some research suggests that increased cortisol levels may lead to reduced fearfulness, a positive consequence. And further, the link between cortisol and heart disease is based on studies of people over 65 so it is mistaken to assume that children with raised levels of cortisol are more at risk of heart disease. However, it’s a very appealing newspaper title and has led to lots of comments from parents on the ill effects of day care.

The moral of the story? Don’t believe all your read. Always ask questions.

2 comments

Getting Type 1 and 2 errors confused

January 4, 2011 by .

Type 1 and 2 errors are not easy to understand and recently one student (thank you Laura Hastings) wrote in to ask if we were also confused (!) and had made a mistake with Type 1 and 2 errors in our AQA A A2 book. Fortunately we hadn’t but the explanation was a bit unclear. On page 266 (Chapter on Anomalistic Psychology) it says:

Causal thinking evolved because it allows people to understand and control their environment, i.e. to be able to predict that, for example, if you eat a red mushroom you will die. This causal thinking is adaptive but may sometimes lead to Type 1 errors – where you believe something is true when it isn’t, for example you believe that tying your shoes laces twice causes luck.

The problematic phrase is ‘where you believe something is true when it isn’t’. Laura was confused because a Type 1 error is defined on page 300 as ‘when a null hypothesis is rejected when it is true’. So it sounds like we got it wrong – but in fact both Type 1 and Type 2 errors are ‘where you believe something that isn’t true’:

  • Type 1 error (false positive) – you believe the null hypothesis isn’t true (and reject it) but in reality the null hypothesis is true. So, in the case of shoe laces you believe shoe laces and luck are linked but, in reality, there is no link. Or you avoid mushrooms for ever after because you think they will make you die but this link is mistaken.
  • Type 2 error (false negative) – you believe the null hypothesis is true (and accept it) when in reality the null hypothesis is not true. In the case of shoe laces and luck, you believe tying your shoe laces twice has no effect on luck but in fact it has. Or you believe that red mushrooms don’t cause death but they do.

The point is that we err on the side of making Type 1 errors (and believing erroneous causal relationships) because we might otherwise make Type 2 errors.

As for the text book, it would be better if it said ‘Type 1 errors – where you believe the null hypothesis is wrong when it isn’t’.

0 comments

Peer review is cracking up

July 6, 2010 by .

In a recent edition of the New Scientist (16 June 2010) the editorial discussed cracks in the peer review system. Staff at the New Scientist analysed a range of scientific journals and found a strong tendency for American researchers to be published faster and in higher profile journals than their rivals elsewhere. Th New Scientist undertook the analysis because a group of researchers had recently taken the unusual step of writing a letter to a leading journal complaining of ‘unreasonable and obstructive peer reviews’. Of course it may simply be that Americans are doing better research, but the New Scientist editorial says we will never know unless peer reviews are published. Some journals are already doing this and the New Scientist hopes this practice increases so that justice can be seen to be done. The editorial concludes by saying that ‘peer review may be flawed but it is the least-worst system we’ve got’.

0 comments

You may never use powerpoint again….

June 8, 2010 by .

There’s a useful presentation on experimental design to be found here

But equally interesting is the software that has been used to produce it – you can have a play here – it’s really easy to use, and you have to agree the presentations look pretty slick..

I was wondering – this could be used for a quick class experiment: Ask one group to present information using powerpoint (i.e. in a linear fashion), ask another to present the same info using the more hierarchical prezi software, to see if the way in which information is organised affects recall in independent groups of subjects?

0 comments

Change blindness

May 1, 2010 by .

I showed this video at a number of recent psychology conferences when I was talking about research methods, and thought I would share it on this site because it is quite entertaining.

Change blindness describes how people are quite poor at noticing change, something demonstrated in a number of studies (see also Daniel Simon and Daniel Levin’s classic ‘door study‘ or Richard Wiseman’s colour changing card trick or just look up change blindness).

Change blindness is different from inattentional blindness where people do not see things which are in plain sight – famously demonstrated in this video (and by Daniel Simons) this one from Richard Wiseman.

You may ask why I was using the video when talking about research methods – I suggested that students might think of ways to further test these phenomena. For example there is evidence that people are more likely to notice change if the other people are the same age as themselves.

0 comments

BPS New Ethical Guidelines

March 16, 2010 by .

Many of you may not be aware that the BPS published new documents relating to ethical practice in August 2009 which you can access here. There has been quite a considerable shift of emphasis. There is now a general document ‘Code of Ethics and Conduct’ which identifies four overriding principles: respect, competence, responsibility and integrity. In conjunction with this are various ethical guidelines such as ‘Ethical principles for conducting research with human participants’ and ‘Guidelines for minimum standards of ethical approval in psychological research’. There are also guidelines for conducting research on the internet, research within the NHS, research with people who do not have the capacity to consent and research with animals.

In the document on research with human participants the following issues are discussed: consent, deception, debriefing, withdrawal from the investigation, confidentiality, protection of participants and privacy in observational research.

0 comments

Science and the law

December 19, 2009 by .

The case of Simon Singh has challenged British libel laws. Simon Singh is a science writer – having authored best selling books such as Fermat’s Last Theorem and contributing regularly to The Guardian. In 2008 he was sued for libel by the British Chiropractic Association (BCA) because of an article he wrote pointing out that some of the treatments offered are bogus, such as those for treating child colic and feeding problems. Singh’s view was that such practice was pseudoscientific and not evidence-based. However the BCA’s claim is that Singh has no evidence to support this and therefore his views are libelous. Within the scientific community this is regarded a challenge to the very nature of science – it should not be libelous to ask a scientist ‘where’s your evidence’ – in fact such a move would stifle the progress of science. Singh’s case and campaign has gained very high profile support from the science and entertainment business (including Jonathan Ross and Stephen Fry) – you can see the names and read much more about the case here (KEEP LIBEL LAWS OUT OF SCIENCE) or here.

0 comments

Inferential Statistics For Dummies

May 17, 2009 by .

PsychExchange.co.uk Shared Resource

« Older Entries