6. summarizing categorical data Flashcards
Frequency tables are for…
…One Categorical Variable
Contingency Table are for…
…two categorical variables
In contingency tables, row proportions add up to 100% at the end of the row whereas
column proportions do add up to 100% at the bottom of the column
MinimumWhisker
Q1−1.5×IQR
Maximum Whisker
Q3 +1.5xIQR
Unimodal Distribution
One peak/mode
Bimodal Distribution
two peaks/mode
when figuring out standard deviation, do you do mean - number or number - mean?
Number - Mean
when the data only represents one/two cases and it is unclear whether these cases are actually representative of the population.
Anecdotal Evidence
in a scatter plot what should be the x and what should be the y axis
Y is the independent variable
X is the dependent variable
You should have one aesthetic to
to one variable
Outlier is how much above or below Q3 and Q1
1.5IQR
the extent to which how different mean is to median
Skewed
average distance from the mean
deviation
Design Principles of Data Visualization (5)
- principle of direction (reading left to right)
2.remove chart junk + unnecessary info - less is more
- visual changes must correspond with data changes
- we identify changes in length more easily than changes in angles