Week 2: Data Handling and Descriptive Statistics in R

Theoretical Constructs

Unobservable psychological entities (e.g., attitudes, beliefs).

Measures

Tools used to elicit data about a construct (e.g., survey items).

Data (Observations)

What is obtained when a measure is used.

Operationalization

Relates a 'construct' to a 'measure'.

Measurement

Relates 'measures' to 'observations'.

Nominal/Categorical

Values have no relationship or meaningful numbering (e.g., colors).

Ordinal

Natural ordering, but differences between values are not meaningful (e.g., rankings).

Interval

Natural ordering, and differences are meaningful, but ratios are not (e.g., temperature in Celsius).

Ratio

Natural ordering, zero means zero, and both differences and ratios are meaningful (e.g., height).

Discrete Variables

Values come in specific categories with no values in between (e.g., year).

Continuous Variables

Values vary smoothly with possible values in between (e.g., age).

Descriptive Statistics

Describes a specific dataset without drawing broader conclusions.

Mean

Sum of data points divided by N (e.g., mean(gdata$age) or sum(gdata$age)/length(gdata$age)). Use na.rm=TRUE to handle missing data (NA).

Mode

Most common point(s), usually for nominal data (e.g., modeOf(), maxFreq()).

Median

The halfway point (50th percentile) (e.g., median(gdata$age) or quantile(gdata$age, 0.5)).

Range

Difference between maximum and minimum values (e.g., max(gdata$age) - min(gdata$age) or range(gdata$age) - range(gdata$age)).

Interquartile Range (IQR)

The middle half of the data (e.g., quantile(gdata$age, c(0.25,0.75))).

Standard Deviation (SD)

How far data points are from the center (e.g., sd(gdata$age)).