Chapter 1 Concepts

ordinal

categorical variable that is ordered

categorical variable

represent types of data which may be divided into groups

numerical discrete

variable that represents a count

numerical continuous

variable that represents measurable amounts

explanatory variable

what you manipulate or observe changes in

response variable

what changes as a result of the explanatory variable

observational study

collect data in a way that does not directly interfere with how the data arises

observational study

evidence of a naturally occurring association (correlation), can be generalized

experiment

researchers randomly assign subjects to various treatments in order to establish casual connections

association

when two variables show some connection with one another

independent

no evident connection between two variables

experiment

can establish causation, cannot be generalized

census

sample entire population, complex and expensive

non-response

sampling bias when only a fraction of people sampled respond

voluntary

sample bias when people only respond because they have a strong opinion

convenience

sample bias where only individuals easily accessible are included

simple random sample

randomly select cases from the population where there is no implied connection

stratified sampling

the population is divided into similar observations (strata) and random samples are taken of each stratum

cluster sampling

data is clustered, a simple random sample of clusters are taken, data is sampled from all clusters

control

control for potential effects of variables other than the ones being directly studied

randomize

randomly sample and assign subjects to treatments

replicate

to reproduce the exact study on a different sample

block

if there are variables that are known or suspected to affect the response variable, the subjects are grouped into blocks based on these variables and then randomly assigned cases

descriptive statistics

summarized collected data through numbers such as averages and percentages

inferential statistics

draw conclusions about the population based on data from a sample of the population

parameter

numerical summary of the population

statistic

numerical summary of the sample

parameter

μ,σ,ρ

statistic

x̅,s,r

treatment group

receives the variable being tested

control group

does not receive any treatment

placebo

an innocuous or inert medication; given as a pacifier or to the control group in experiments on the efficacy of a drug

placebo effect

any effect that seems to be a consequence of administering a placebo; the change is usually beneficial and is assumed result from the person's faith in the treatment or preconceptions about what the experimental drug was supposed to do

double-blind

doctors or researches who interact with patients and the patients are unaware of who is or is not receiving the treatment