Week 3 Flashcards
Vaccine example for populations and samples
Population - people in the world
The sample design creates a sample: participants for vaccine test
Test the sampled people to generate vaccine efficacy for participants
Then inference causes vaccine efficacy for people in the entire world
What is a sample
A subset of a given population
What defines good samples
Careful considerations on sub-categories to make sure that sample reliably represents the population (age, gender, socio-economic background)
Once samples are determined, it should not be modified for the sake of deriving a better conclusion – called cherry picking
What happened in the astraveneca/oxford vaccine sample design
Found that the study only included 5.67% of participants over 65
Variables
Set of related events that can take on more than one value
In research, it is something that can be changed such as a characteristic or value e.g. weight, exam mark, hometown
Statistical inference
figuring out how well a property of one variable can be predicted (inferred) by that of another variable
Dependent variable
Is the outcome, or something you are testing, relies on other variables
Independent variable
The predictors
Isnt changed by the other variables you are trying to measure
Control variable
variables that are kept constant to prevent them influencing the effect of IV or DV
Control variables included in a study about how drinking coffee effects sleep quality
time that coffee was drunk, amount of coffee drunk, other activities during evening
Nominal data
Nominal (categorical) - cannot be ordered or counted e.g. country, gender
Ordinal data
Ordinal – can be ordered, but cannot be added or substracted e.g. spicy level, education level
Interval data
Interval – can be ordered, and their difference can be measured, but you cannot compute a ratio between two values (no meaningful zero exits) e.g. year (you can ratio between year born and current year)
Ratio data
Ratio – interval + can take ratio between two e.g. distance, height (you are 10% taller than me), annual income
Nominal and ordinal variables are….
qualitative
