MCS 140/142

Introduction

“Statistics is the science of data.”

Statistics involves

Collection—by “design”

Data description and analysis

Statistical inference

“Data are numbers with a context.”

(Our text and The Everyday Writer: “data” is plural of “datum.”)

The “spreadsheet” view of data sets!

“Variable” = a characteristic of an individual.

“Individual” = a person, animal, or thing observed.

“Case” = the data for one individual.

Looking at Data—Distributions

Scales of measurement of a variable

Categorical/nominal: Values are labels.

Quantitative: Values are numbers for which some arithmetic makes sense.

It’s important to specify the units of measurement.

Ordinal: Ordering (<) is meaningful.

Interval: Differences are meaningful.

Ratio: Ratios are meaningful.

The distribution of a variable specifies its values and their frequencies.

Graphical representations of distributions

For categorical variables

Pie charts

Bar graphs

For quantitative variables

Stemplots (stem-and-leaf plots)

Histograms

Time plots