Group one that is not given the same treatment as the

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Issues To Consider with Experiments Experiments The Placebo effect – fake treatment used as a control in an experiment (e.g., sugar pills) that often gets results as well pills) – Strangely, in many studies, a certain Strangely, percentage of people who don’t get the treatment say that they feel better anyway treatment – This may be due to the simple attention to the This problem or possibly even to the release of endorphins when you believe something endorphins will make you feel better Issues To Consider with Experiments Experiments Random assignment – each individual has the same probability as any other in being assigned to the experimental or control conditions control – Why is it necessary that this happens in an Why experiment? – What if we chose groups based on some What variable such as gender or ethnic group? variable Issues To Consider with Experiments - II Experiments Blind and double-blind studies – experiments done where either or both the experimenter and/or the subjects don’t know which group they are in (experimental or control) (experimental – E.g., AIDS drugs – have to know if they work, so need a E.g., control group. Single blind study – subjects don’t know which group they’re in Double blind study – neither subjects nor experimenters know Double which group is which (i.e., which group is getting the treatment and which is not and Statistics Statistics Descriptive statistics – sum up the data – Mean – the average of a bunch of numbers – Median – when ordering scores from highest to Median lowest, the value of the middle number lowest, – Mode – the most frequently occurring score Statistics – II Standard deviation – the average difference between scores in a distribution and the distribution’s mean distribution’s – This is easiest to see on a normal curve Statistics – III Normal curve – represents a normal distribution represents – Also called a ‘bell curve’ – Represents many phenomena in science (e.g., IQ, scores on a Represents given test, height, weight) given – Some notable qualities of the normal distribution: The mean is also its mode and median. The mode median 68% of the area under the curve is within one standard 68% deviation of the mean. 95% of the area is within two standard deviations. 95% 99% of the area is within three standard deviations. 99% 99.99% of the area is within four standard deviations. 99.99% Statistics – III – Normal Curve Statistics Statistics – IV Significance testing – Answers the question – “Would this finding ever Answers happen by chance?” happen – “Significance” is reached by getting results Significance” where the probability of the result happening by coincidence (chance) is less than 5 chances in 100. 100. Statistics V - Correlations Statistics A correlation is a measure of the strength of two correlation events, characteristics, behaviors, etc. – E.g., lots of running is correlated with knee problems ...
View Full Document

This note was uploaded on 10/03/2013 for the course SOCI 1000 taught by Professor Tim during the Fall '13 term at CUHK.

Ask a homework question - tutors are online