Test - Statistics and Epidemiology Flashcards
(40 cards)
Independent variables
variable the researcher is manipulating
Dependent variables
the effect of the independent variables (outcome variable)
What are the 4 levels of data?
Norminal, ordinal, internal, ratio
Norminal
the number is a label i.e. male or female
Ordinal
has an order - i.e. 1st, 2nd, 3rd in a race
Internal
has a fixed value between numbers e.g. temperature
ratio
has a fixed value between numbers but has an absolute zero - e.g. time to finish the race, power, forces etc
What are the measures of central tendency?
Mean, median, mode
Mean
the average of the values
Median
the middle number
Mode
the most frequent number
What are the masures of variation?
Standard deviation (SD) and range
Variation
Spread of data
Standard deviation
How data is distributed
Measures variation round the mean
How much the members of a group differ from mean value for the group
Range
expressed either as the biggest to smallest number in the data or the difference between the biggest to smallest
To determine the effect a treatment (independent variable) has on a measure (dependent variable)
Hypothesis testing
Null hypothesis
e.g. there is no difference between the flexibility of men and women
What is a p-value a measure of?
probability - the null hypothesis is true
Hypothsis testing steps
- Set a null hypothesis
- Set research (alternative) hypothesis
- Set significance level
- Collect data
- Statistical test
- P-value from test
- Compare p value to significance level
- Conclusion - make decision
What does p<0.05 indicate?
Significant difference
What does p>0.05 indicate?
no significant difference
What is the drawback of the p-value?
Does not tell us what the difference is, or how large the difference is
Gives us a range of values in which we are confident the population mean is likely to fall
confident interval
Supplementing the p-values with ‘likely’ or confidence interval will indicate the possible size of the effect
95% confidence interval
