4.2.3.3 PROBABILITY AND SIGNIFICANCE Flashcards
what are psychologists interested in finding out about their results or their studies?
if they show real differences or correlations, or if the results are due to chance factors
eg. the probability of the IV having affected the DV
how do psychologists determine whether results are significant?
to determine whether they’re significant and not due to chance factors
- researchers use a measure of the level of significance
what must researchers decide to conclude that the observed result is unlikely to be due to chance?
must decide how long an effect or relationship is required
this decision is reflected in the level of significance applied to the data
how is the level of significance expressed?
as a decimal value where ‘p’ stands for the probability that chance factors are responsible for the results
for most purposes in psychology, what level of significance is appropriate?
the 5% level of significance is appropriate which is expressed as p<0.05
ie) the probability of chance factors producing the observed result is less than or equal to 5%
how is the critical value found?
what does this determine?
the research will use statistical tables to find the critical value
- this will determine whether or not they can reject the null hypothesis
what are inferential statistics?
- enable us to draw inferences about the population
- designed to tell us the likelihood that the IV affected the DV
- refer to a probability factor of less than 0.05 (conventional level)
-> 5% or less, likely that a chance factor affected the DV
-> 95% or more, likely IV affected DV - can go lower for things like drug trials
-> ‘p’ is less than 0.01
what are descriptive statistics?
- show patterns / trends in data of the sample taken from that population
- measures of central tendency
-> average, mean, median, mode - measures of dispersion
-> spread in data, range, standard deviation, spread of data around the mean - don’t tell us anything about it affecting the DV
when is an observed value gained?
what needs to happen with it?
- once the researcher has conducted a statistical test they have an observed value which is used to determine whether results are significant
- this observed value needs to be compared to the critical value in the statistical tables
what is a Type I error?
- they occur when the null hypothesis is rejected when it should have been accepted
ie) the researcher claims that the results are significant when in fact they’re not (aka a ‘false positive’) - more likely to happen when the researcher uses a probability value that’s too high
eg) 0.1 rather than 0.0.5
what is a Type II error?
- occur when the null hypothesis is accepted when it should’ve been rejected
ie) the researcher claims that the results aren’t significant when in fact they are (aka ‘false negative’) - more likely to happen when the researcher uses a probability value that’s too low
eg) 0.01 instead of 0.05
what 3 things are needed to be considered in order to choose a stats test?
1) test of difference or association
- difference = experiment, IV, DV
- association = correlation, 2+ co-variables
2) experimental design
- independent groups = unrelated data
- matched pairs and repeated measures = related data
3) level of data
- nominal data
- ordinal data
- interval data