Soc 210 Midterm 1

mathematical tools used to organize, summarize, and manipulate data

• observations gathered from an experiment, survey, or observational study
• scores on variables, info expressed as numbers (quantitatively)

• quantities that vary
• traits or characteristics that can change values from case to case (ex. age, gender, income)

the entities from which data are gathered (ex. ppl, groups, provinces, countries)

• univariate
• bivariate
• multivariate

summarize a single variable (ex. GPA)

• summarize the strength and direction of the relationship between two variables 
• ex. older students having higher GPA than younger students

• summarize the relationship between 3 or more variables
• ex. GPA increases with age for females but not males

generalize/infer from a sample to a population

• variable beyond our control
• used to help explain dependent variables

• what we want to explain (usually)
• depends on the independent variable

• measured in units that can't be subdivided
• ex. marital status, country of birth

• measured in units that can be subdivided (often infinitely)
• age in years, income in dollars

• allow for only qualitative classification
• scores are different from one another but can't be treated as numbers, and don't have order to them
• ex. region, 1=urban, 2=suburban, 3=rural

• scores ranked from high to low or more to less
• always discrete variables
• can say something is more/less than something else
• ex. 1=strongly disagree, 2=disagree, 3=agree, etc

• scores are actual numbers and have equal intervals between them
• can be discrete or continuous
• ex. age (years), income (dollars), number of kids

• refers to the number of actual occurrences of an event divided by the number of possible occurrences, per some unit of time
• rate=#actual/#possible in a period of time

• refers to absolute change
• ex. the new percentage - the old percentage

• refers to relative change

summarize the distribution of a variable by reporting the # of times each score of a variable occured

• exhaustive
• mutually exclusive
• relatively homogenous

show differences in frequencies and percentages among the categories of a nominal or ordinal variable

show the differences in frequencies or percentages among categories of a nominal or ordinal level variable

• show differences in frequencies and percentages among categories of an interval-ratio variable
• bars are touching to indicate a continuous variable

• similar to histograms
• uses lines and dots to represent frequencies

• the most typical, central, or common score of a variable
• mode, median, mean

• most common score
• can be used at all 3 levels of measurement
• most often used with nominal level variables

• score of the middle case
• divides the distribution into two equal parts
• can be used with ordinal or interval-ratio variables because they have some kind of order to them

mean

number of cases in a sample

the number of vases in the population

• all scores cancel out around the mean
• the mean is the point of minimized variation
• the mean incorporates all of the scores

• the shape of the distribution
• can be unskewed (perf normal curve), positively skewed, negatively skewed