Quantitative Flashcards
What are the central tendencies?
Mean, mode, median
When would you use a Mann Whitney U test?
Non parametric data and when you’re comparing two different groups of people
When would you use a Wilcoxon sign rank test?
Non - parametric data
Comparing the same group of people under different conditions/time points
When would you use a paired t test?
Parametric/normal distribution data
comparing the same people under different conditions or different time points
When would you use an Unpaired T test?
Parametric data
Comparing two different groups of people
If the P value is greater than 0.05, what does this mean in terms of the data?
The data is not significant
Accept null hypothesis
If the P value is less than 0.05, what does this mean in terms of the data?
The data is significant
Reject null hypothesis
What is the P value?
Probability of error
It tells us if the data is significant or not, tells us if it is down to chance
What central tendency and variance would you use for normally distributed data?
What will the graph look like?
Mean and standard deviation
The graph will be a bell shaped curve
What central tendency and variance would you use for not normally distributed data?
Median and interquartile range
What does the R value show?
What does it mean if the R value is positive?
Strength and direction of the relationship
The relationship is positive (1 = really well correlated)
What is intention to treat analysis?
Why is this a bad thing?
Involves people that didn’t take part in the activity
Doesn’t tell you if the thing you’re researching actually works
what is pre-protocol analysis?
Only involves the people that take part in the study involved in the data
What are the 2 excel short cuts for standard deviation and what do they mean?
STDEV.P (population)
STDEV.S (sample)
What is a parallel design?
Subjects are randomly allocated to different groups and they will stay in that group throughout the whole study
What is a cross over design?
Where participants are randomly allocated to study arms where everyone does everything
What is a single blind trial?
On of either the participants or the researcher is aware of the group allocation
What is a double blind trial?
Neither the researcher or the participants are aware of the group allocation
What is a placebo?
Sham substance or treatment which is designed to have no therapeutic value
What is a prospective design?
Follows participants in time, observing them and collecting data at regular intervals
What is a case-control study design?
Type of observational study identify factors that may contribute to a specific outcome. Compares people who have a condition with those who don’t to determine factors
How would you work out median on excel?
= MEDIAN
How would you work out mean on excel?
= AVERAGE
How would you work out interquartile range on excel?
= INTERQUARTILE.INC (1)
= INTERQUARTILE.INC (3)
(3) - (1)
