stats onramps

numerical variables

have values that represent quantities

discrete variable

variables that can only take on specific values meaning theres gaps between possible values. (ex. number of siblings, year of birth, etc.)

continuous variable

a quantitative variable that can take on any real number value. (ex. height, temperature, etc.)

categorical variables

values that are names or labels. These are data that cannot be averaged or represented by a scatter plot as they have no numerical meaning. (qualitative)

nominal variables

variables have categories with no distinct or defined order; or a difference in name only. Also, variables with only two categories. (ex. sex, attendance, yes or no answers, etc.)

ordinal variables

variables have an inherent or obvious order. (ex. Likert scales (strongly agree, agree, disagree, strongly disagree), class in school (freshman,sophomore, junior, senior)

Population

all possible members or outcomes for a group

Parameter

what we are calculating in our study

Sample

a smaller study group chosen to represent a larger population

Statistic

a calculation derived from our sample

sampling eror

natural error that occurs from taking a sample

simple random sampling

every member of the population has an equal probability of being selected for the sample

stratified random sampling

Dividing a population into groups or clusters and then randomly drawing from each cluster

convenience sampling

randomly drawing from people you know or who are close to you

Bias

systematic or repeated errors in how we sampling that create samples that are not fully represented of the population

questionairre / interview bias

the way in which a question asked can almost force people to answer in a specific way

Instrument bias

systematically measuring responses inaccurately

selection bias

individuals in a population are more likely to be selected than others

under/over representation

we choose to select our sample from a time or place during which certain portions of the population are selected more or less frequently

Non-responsive bias

people selected to participate don't respond

voluntary response

sampling design where individuals can choose on their own whether to participate in the sample

confounding variables

variables that can inadvertently affect the parameters of interest