Quantitative Research - Data Collection & Analysis Flashcards
What is reliability?
Addresses whether repeated assessments would provide consistent results given the same initial circumstances
What is the main outcome called?
Primary outcome
Validity in a study means:
The measurement tool measures what it is intended to measure
List some threats to internal validity
History, maturation, testing, mortality
What is the Hawthorne effect?
A participant’s response to being in a study
What is internal validity?
Results being legitimate because of study method:- ‘did independent variable really change the dependent variable?’
What is external validity?
Concerns whether the results are transferable to other groups
Appropriate study outcomes should be:
Meaningful, measurable and responsive
How are selection effects threats to external validity?
Ideal sample population may be unobtainable
How are reactive effects threats to external validity?
There may be responses just because participants are in a study (Hawthorne effect)
How are measurement effects threats to external validity?
Measurement and testing affect generalisability
What are ‘descriptive statistics’?
Data that is displayed & summarised in a way that is easily understood
List 3 ways in which numbers can be displayed
Numerical result, Coded category and ordered categories
What are the 4 levels of measurement in quantitative research?
Nominal, ordinal, interval & ratio
When presenting data, mode can be used in which types of measurement?
Nominal, ordinal, interval & ratio
When presenting data, median can be used in which types of measurement?
Ordinal, interval & ratio
When presenting data, mean can be used in which types of measurement?
Interval & ratio
What is the purpose of statistical analysis?
To draw inferences from the sample
What is a P value?
Is the probability of obtaining the study results if the null hypotheses is true. Varies between 0 & 1. Closer to 0, the more likely the null hypotheses will be rejected.
If the null hypotheses is rejected but turns out to be true, what sort of error would that be?
Type 1 error, alpha, False positive error
If the null hypotheses is accepted but turns out to be false, what sort of error would that be?
Type 2 error, beta, False negative error
What is the ‘power’ of a study?
The probability of being able to detect a difference between study groups - usually expressed as a %
What is a confidence interval?
A measure of the precision with which the quantity of interest is estimated
Statistics that produce p values are called?
Inferential statistics
What is baseline data?
the data that is collected before the intervention but after the recruitment
Which level of measurement has a fixed zero?
Ratio
