Stats Chapter 2 Lecture 2

bar charts

categorical variables are displayed using ______

(count ÷ total) × 100

Percent frequency = _______

dot plot or histogram

numerical variables are displayed using ______

dotplot

If you have a small/medium amount of numerical data → ______

histogram

If you have a large amount of numerical data → _______

do not

Bar chart (categorical), bars ______ touch

do

Histogram (numerical), bars ______ touch

dotplot

histogram

_______ = individual values
_______ = grouped ranges

mode

the most common value/range

tallest bar

On a histogram, the mode is usually the ______

peak

A _______ is an area where the graph gets high

1 peak, 2 peaks, same height

for numerical graphs, unimodal has _______, bimodal has ______, and uniform is when values/bars are the ______

tails

bars declining away from the mode

Right-skewed

long tail going to the RIGHT

Left-skewed

long tail going to the LEFT

high

low

Right skewed = _______ values

Left skewed = _______ values

Symmetric

roughly equal tails; when the two sides look roughly like mirror images

mean ≈ median

For a symmetric distribution: _______

outlier

isolated bar(s) separated from the rest by a gap

far away

An outlier is a value that is ______ from the rest of the data

gap

On a histogram, you might see an isolated bar separated by a ______

median

in right-skewed, mean is pulled rightward, above the ______

bimodal

Often signals two subgroups mixed together

Two-way frequency table + side-by-side/stacked bar chart

2 categorical variables are displayed by ______

Side-by-side boxplots or dotplots

1 categorical + 1 numerical variable is displayed by ______

Scatterplot

2 numerical variables are displayed by _____

two variables

one variable

_______ → look for a relationship between them

_______ → describe its distribution

Two-Way Tables

Count observations for every combination of two categorical variables

Side-by-side bar chart

one cluster of bars per group, one bar per category

Stacked bar chart

categories stacked for each group

numerical, categorical

1 categorical + 1 numerical → compare the ______ variable across the _______ groups

Direction (Positive/negative) + Form (Linear/curved) + Strength (Strong/weak) + Outliers

What 4 things do you look for in a scatterplot?

bar charts

categorical, bars don't touch

dotplots

numerical, shows every value

histograms

numerical, grouped into equal-width classes, bars touch

the proportion of data in that class

for a histogram, what does the area of a bar represent?