RESS Flashcards
Population
Every member of a defined group of interest
Representative Sample
Select group of the population
Prevalence calculation
No of smoker/total number
Categorical Variable
Can only be assigned to a number of distinct categories.
e.g. Sex, severity of symptoms
Nominal Data
Subgroup of categorical variable
Category with no natural ordering
e.g. sex
Ordinal Data
Subgroup of categorical variable
Natural ordering
e.g. severity of pain
Numerical Variables
Ones that take numerical value
e.g. age
Discrete data
Subgroup of numerical variable
Takes values of whole numbers only
e.g. no of hospital visits
Continuous data
Subgroup of numerical variable
No restrictions on value
e.g. weight
Frequency Table
Table showing frequency distributions
Data appropriate for bar charts
Categorical and discrete metric variables
Pie Chart
Categorical and numeric
Histograms
Continuous variables
Incidence
New cases of the disease arising in a population of a defined period of time
Prevalence
Number of people with a disease amongst the population at a given time
Adjustment
Refining case fatality rates and mortality rate to better represent the data
Risk
=Number of new cases / Number at risk
Odds
Number of times the event occurs divided by the number of times is does not occur
Odds ratio
Used to calculate relative risk
Relative Risk = 1
The risk/odds in the exposed group are the same as in the unexposed group
Relative risk <1 and >1
<1 = Exposure is associated with a protective effect >1 = Exposure increases risk of contracting the disease
Outcome Variable
Your health or healthcare issue
Exposure Variable
Factors affecting the outcome
T-Test
Hypothesis testing by calculating a test statistic that is compared to the critical value in the relevant statistical table - If T stat more than critical value, reject null hypothesis
P Value
Measure of the probability of obtaining the results of the test given that the null hypothesis is true. The smaller the p value, the less likely the results is to have occurred by chance
Significant correlation statistic
0.7
Linear regression
Regression of the best line to the observed data
Sensitivity
How well the tests detects a condition - No of correct positive tests / no with disease
Specificity
How well the test excludes those without the disease
No correctly test negative/ no without the disease
Positive predictive value
Probability someone has the condition if they test positive
= No have the disease/ no test positive
Negative predictive value
Probability someone doesn’t have the condition if they test negative
= No don’t have the disease/ no test negative
