Week 7 Flashcards
What are the different levels data is collected at? Examples?
Within a person
- Response on question(aire)
- Reaction time
- Blood conc
- Physiological measurement
Between people
- individuals in a sample
- Samples in a population
- Classes, cohorts in a school
- Districts in a city
What do you do with averages?
Analyse them with tests - t-test, correlation, ANOVA, GLM etc.
What are the levels of data analysis?
Level 1 - Within person, within measurement - raw data eg using 100 individuals HR to estimate HR
Level 2 - Within person, within condition - summary data/descriptive stats eg using 10 reps of each condition to estimate pre/post HR
Level 3 - Between people - inferential stats eg using 16 athletes in each group to estimate interventions effect
General principles of stats?
- Within-subject (repeated) designs usually need less data
- Statistical power increases with the square root of N
- You need to set an arbitrary level of ‘significance’
- You need to evaluate sample size in context of other things
What is statistical power?
The probability that you will find a significant result, assuming there is real effect in the population
What are the assumptions of statistical power?
There is a real effect - your hypothesis is exactly true
It is as big as you say - specify effect size = R^2, f, d
Other stat assumptions are true - independent sampling, similar variance, indepedent residuals
What do you need for high statistical power ?
More repetitions the better
For double statistical power you must quadruple reps
What do you do with all the averages in data?
You find the average/mean until suitable to analyse.
Or you can look at averages of differences
Cohen’s d value ?
Cohen’s d is a measure of effect size that shows the difference between two group means in terms of standard deviation units
0.3 = small
0.5 = medium
0.8+ = bigger
