Statistical Analysis - Unit One

Inferential Statistics

Uses properties (mean, median, mode, etc.) from a sample group to draw conclusions about the broader population

Descriptive Statistics

Describes the properties of a sample (mean, median, mode, standard deviation, etc.)

Random Sampling

Unbiased sampling of individuals from a population. The best method to ensure a obtain a representative sample of the greater population.

Point Estimate

A single value that serves as the “best guess” for an unknown population parameter, such as mean.

Ex: The calculated sample mean is a point estimate of the true population mean.

Margin of Error (MoE)

A statistical measure of the amount of random sampling error, indicating the range within which the true population value likely fails.

Confidence Interval (CI)

Quantifies our uncertainty about the population. It gives the range of population values which are plausible or likely given the sample data. It is the point estimate ± the margin of error.

Short Confidence Interval

Precise estimate, meaning little uncertainty.

Long Confidence Interval

Not a precise estimate, meaning a lot of uncertainty.

Reliable study

Repeatable; similar results on repeated measurments

Valid study

Accurate, true, measuring what is meant to be measured

Nominal level of measurement

Classifies data into categories without any order or ranking; the labels are simply names, such as gender, hair color, or jersey numbers.

Ordinal Levels of Measurement

Organizes data into a natural or ranked order, movie ratings (★ to ★★★★★), or likert scale responses (agree → disagree).

Interval Levels of Measurement

Orders data with equal intervals between values, and no true zero point, examples include temperature (°C) and calendar years (2000-2010).

Ratio Levels of Measurement

Orders data with equal intervals and includes a true zero point, examples include height, weight, age, distance, and time.

NOIR

A mnemonic device to remember levels of measurement: Nominal, Ordinal, Interval, Ratio.