BIOL2300 - Biostatistic Ch.1 Terms

Quiz 1 content

Sampling population

a subset of units taken from the total population for characteristics that differ among individuals

parameter

true (but usually unknown) numerical value that describes an entire population. it is based on every member of a populatiom, it represents absolute “truth”

estimate

related quantity calculated specifically from a sample

estimation

the process you are performing — inferring the uknown

random sample

each member of a population has an equal and independent chance of being selected (minimizes bias + makes it possible to measure amount of samplig error)

sample of convenience

a group of people chosen because they’re easy to reach and close by (faster to perform)

sampling error

difference between an estimate and the population parameter being estimated caused by chance

bias

a systematic discrepancy that causes results to consistently differ from the true value (parameter)

volunteer bias

arises when there are systematic differences between pool of volunteers and general population

• physical health/activity studies might yield healthier individuals

accuracy

Closeness of a measurement to the real or accepted standard.

precision

Consistency or repeatability of independent measurements

categorical data

qualitative characteristics of individuals that do not have magnitude on a numerical scale

• nominal

• ordinal

nominal data

distinct categories with no inherent order or ranking,

• blood type

• sex

ordinal data

categories that follow a meaningful, ordered sequence

• cancer stages

• levels of obesity

numerical data

quantitative measurements that have magnitude on a numerical scal

• discrete

• continuous

discrete data

indivisible, counted in whole units

• number of siblings (3)

• number of cars (2)

continuous data

measured and can take any value within a range, including decimals

• weight of a person (151.4 lbs)

frequency distribution

describes the number of times each value of a variable occurs in a sample

absolute frequency

raw, whole-number count of occurrences.

• denoted by n

relative frequency

A proportion, fraction, decimal, or percentage calculated by dividing the absolute frequency by the total number of trials/observations

• denoted by p

incidence rate formula

x = (number of cases population / population) x R

• (per R)

Experimental Study

researchers apply a treatment or intervention to one group and compare it to a control group

• direct manipulation of variables

Observational Study

researchers record data on subjects in a natural setting without changing any conditions

• no intervention

explanatory (exposure) variable

expected cause that explains changes in an outcome

• health: smoking

response (outcome) variable

expected effect that measures that outcome

• health: lung cancer

confounding variable

a variable that masks or distorts the causal relationship (independent and dependent), making a fake or distorted connection between them.

categorical, nominal

qualtiative data type where categories have no inherent order

• blood type

• gender

categorical, ordinal

qualitative data type where categories have an inherent order or ranking

• obesity stages

• cancer stages

• ripeness of a fruit (underripe → ripe → overripe)

numerical, discrete

quantitative measurement thats its units are undivisible

• number of teeth

numerical, continuous

quantitative measurement that its units can be any real number

• temperature

• height

Recall bias

systematic error due to differences in accuracy or completeness of recall to memory of past events or experiences

Measurement bias

a systematic, non-random error that happens when collecting or recording data in a study. It causes the measured results to consistently differ from the true value.

Selection bias

a logical error of focusing only on the winners or survivors of a selection process while ignoring the ones that failed

Observer Bias

when a researcher's expectations, opinions, or prejudices unintentionally influence what they perceive, record, or interpret during a study