Statistics Chapter 1

Statistics is the science concerned with the collection, interpretation, and presentation of data.

Data is a collection of observations or measurements.

A population consists of an entire collection of data.

A sample is a subcollection of all data.

A voluntary response sample, or self-selected sample, is a non-random sampling method where respondents volunteer to answer.

A parameter is a measurement describing a population on the other hand

A statistic describes a sample.

Quantitative or numerical data consists of counts and measurements.

Categorical data (also called qualitative or attribute data) concerns non-measuring names and labels.

Discrete numerical data can be counted reliably. If you had octopus hands, you could keep counting this type of data.

Continuous data technically can’t be counted since there are many infinitely many values in this type of range.

Data with a nominal level of measurement can’t be ordered or arranged. They should not be used in direct calculations.

Data with an ordinal level of measurement can be arranged but subtracting them would be meaningless.

Data with an interval level of measurement can be arranged and subtracted. However, they do not have a “true” zero.

Data with a ratio level of measurement can be arranged, subtracted, and interpreted with a “true zero”.

An experiment observes the effects of a treatment on subjects.

An observational study observes people as-is without trying to change them.

A random sample is a sample where all of a population had the same chance of being selected.

In a simple random sample, there is an equal chance of having selected another sample of the same size.

A systematic sample takes a pattern of subjects, like every 5th.

A convenience sample takes whatever data is simple to get.

A cluster sample divides a population into clumps and then select partitions’ samples.

A stratified sample divides a population into strata and then into stratum, randomly sampling that stratum.