Classes #29-#34: Introduction to Biostatistics in Epidemiology Flashcards
What is the Null Hypothesis (H0)?
Null Hypothesis -> a research perspective which states there will be NO (true) difference between the groups being compared.
*most conservative and commonly utilized
What are the 3 various statistical-perspectives can be taken by the researcher?
1) superiority
2) non-inferiority
3) equivalency
What is the alternative hypothesis (H1)?
Alternative Hypothesis-> a research perspective which states there WILL BE a (true) difference between the groups being compared.
What does the researcher do with the null hypothesis concerning their research?
Researchers either accept or reject this perspective, based on results (data analysis).
What are the 2 key attributes of data measurement (variables)?
1) magnitude (dimensionality)
2) consistency of scale (or fixed interval)
True or False:
Each of the key attributes of data measurement (variables) must be assessed with a “yes” or “no” response.
True - each attribute can be assessed with a yes or no response.
What are the study measurement steps that are used by the researcher conducting the project?
1) measurements (data) will be collected on desired “variables”
>dependent variable(s) [outcome variables]
>independent variables
2) comparisons will be made (statistical analyses)
3) inference will be made about the sample-derived measurements and their comparisons (in relation to Null Hypothesis).
>inferences will also be made to the full population of similar subjects (generalizability).
What is the difference between the study population, population, and sample?
Study Population -> is the final group of individuals selected for a study.
Population -> all individuals making up a common group; from which a sample (smaller set) can be obtained, if desired.
Sample -> a subset or portion of the full, complete population (“representatives”).
What are the 3 categories for data (variables) based on the answer to the 2 key attributes (magnitude and consistency of scale)?
1) nominal
2) ordinal
3) interval/ratio
What is nominal data?
Nominal data (dichotomous/binary; non-ranked named categories) has:
> NO magnitude
> NO consistency of scale
> NO rational zero
Nominal variables are simply labeled variables without quantitative characteristics.
** ALL data that is forced into 2 categories is instantly NOMINAL.
What is ordinal data?
Ordinal data (ranked categories; non-equal-distance) is data that has:
> YES magnitude
> NO consistency of scale
> NO rational zero
- ranked categories are an example of ordinal
- ALL pain scales are ordinal in nature. but in Larry’s world, all pain scales, even those that use numbers, are still ordinal.
What is interval/ratio data?
Interval/ratio data (order and magnitude and equal interval-of-scale (units)) data has:
> YES magnitude
> YES consistency of scale
> NO or YES rational zero (NO-interval; YES-ratio)
- number of living siblings and personal age (in years)
** anything that is physiological measured is interval/ratio in nature.
True or False:
After data is collected, we can appropriately go down in specificity/detail of data measurement (levels), but never up.
TRUE
*you can change levels of measurement of data as long as you go down, but not up.
Ratio (absolute zero)
Interval (distance is meaningful)
Ordinal (attributes can be ordered)
Nominal (attributes are only named; weakest)
Which 2 key levels and attributes of measurements are considered discrete?
Nominal (all dichotomous and non-ranked categories)
- NO / NO
Ordinal (all ranked categories)
- YES / NO
Which one of the key levels and attributes of measurements is considered continuous?
Interval (all numerical scales with true units)
- YES / YES
