Intro to statistical testing Flashcards
What is the first step in the research process?
Find a topic that you’re interested in and do some research into what has been studied before
What is the second step in the research process?
Create an aim and hypothesis
What is the third step in the research process?
Design the study, including type of experiment, experimental design, sampling technique, ethical considerations.
What is the forth step in the research process?
Gain ethical approval from an ethics committee
What is the fifth step in the research process?
Do a pilot study
What is the sixth step in the research process?
Make refinements and conduct the study
What is the seventh step in the research process?
Analyse the results using descriptive statistics to identify trends
What is the eighth step in the research process?
Conclusion (based on red) - statistical test
What are the final 3 steps in the research process?
Write up, Peer review, Publish Results
What are inferential statistics?
A type of statistical analysis that allow researchers to determine whether they have found a significant result (i.e.that there is a difference or relationship between the variables they studied) or if it occured by chance (coincidence or fluke).
What do inferential statistics allow us to do?
We can determine which of our hypotheses (alternative or null) should be accepted and which should be rejected based on them. They allow you to make inferences (i.e. Draw conclusions) about target population from a sample of data.
What does it mean if the data is found to be significant?
hypothesis
They found a real difference/ correlation/ association, therefore can reject the null hypothesis and accept the alternative hypothesis.
What does it mean if the data is found to be insignificant?
They have not found a real difference/ correlation/ association therefore accept the null hypothesis (coincidence).
What does a significance level of p<0.05 mean?
It is concluding that it is significant but accepting that there is a probability of less than 5% that the results occurred by chance.
What is the aim of statistical testing?
The purpose of statistical testing (inferential statistics) is to determine the likelihood (probability) that the effect/ difference/ relationship/ association found in the study is significant or due to chance.
What do psychologists mean by ‘probability’?
Statistical tests work on the basis of probability (a numerical measure of the likelihood that a particular event will occur ranging from 0 to 1 where 0 indicated statistical impossibility and 1 indicates statistical certainty).
What is a significance level?
This is the point at which the researcher can claim to have discovered a significant difference or correlation within the data. In other words, this is the point at which the researcher can reject the null hypothesis and accept the alternative hypothesis.
Why can psychologists never be 100% certain about a particular result?
Psychologists can never be 100% certain about a particular result because they have not studied all members of the population under all possible circumstances.
What values do psychologists compare in statistical tests?
In any statistical test that psychologists use, they compare the result of their test (the calculated value) to a critical value for the significance level that the psychologist has chosen.
Why do psychologists compare these values in statistical tests?
If a significance level of p≤0.05 is chosen by a psychologist, comparing their calculated value to the critical value allows them to determine whether their results have a 5% or less probability of occurring by chance and are therefore significant, or whether they have more than a 5% probability of occurring by chance and so are not significant. Critical values are found in a critical values table.
When would a p<0.05 significance level be used?
If the study is not one that involves a human cost and is not a one-off study that couldn’t be repeated in the future.
What is a one-tailed study?
Directional hypothesis e.g. people will be happier
What is a two-tailed study?
Non-directional hypothesis e.g. There will be a difference
What is a calculated value?
The number achieved from a statistical test e.g. the sign test
What is a critical value?
Each statistical test has its own critical values table where we can find the critical value to compare our calculated value to.
When should you use the sign test (3 rules)?
- researchers investigating difference
- a related design
- nominal data
What is the difference between a related and unrelated design?
Related: matched pairs, repeated measures
Unrelated: independent design
What is the first step of the sign test?
Identify the your 3 categories of results (e.g. better before, better after, no difference)
What is the second step of the sign test?
Calculate the number of participants in each category
What is the third step of the sign test?
Assign the no difference category a 0 sign
What is the forth step of the sign test?
Assign one of the other two categories a + sign and the other a – sign.
What is the fifth step of the sign test?
Out of the + and – sign categories, identify the category with the smaller number. This number is S.
What is S (sign test)?
The calculated value