Final Exam Flashcards
Why are pie charts not preffered?
If you use too many pieces it can make the visualization ineffective
Crosstab
like a table
Bar Chart
Column based displays
-used to compare discrete or categorical data
-show categorical data
Histogram
Column based displays
-frequency distribution of continuous variables
-present numerical data
What is the purpose of bins in a histogram?
Choice of unit and spacing on the X-Axis
What is a tree map
Multiple box map
-Display hierarchical data
-Display part to whole relationships
Bubble charts:
Bubbles
-used to make comparison between members of a categorical field
Continuous data
-Measurable and only numerical
-represented by line graph or histogram
-no gaps and can take any value within a range
Discrete Data
-clear spaces or gaps between values
-countable and can be numeric or categorical
-represented by a bar graph
Quantitative data
information that can be quantified and given a numerical value
Sequential
color is ordered from low to high
Diverging
two sequential colors with a neutral midpoint
Categorical
contrasting colors for individual comparison
Highlight
used to highlight something
Alert
used to get readers attention
4 D’s of storytelling
Define your story
Display the data
De clutter and remove any distracting junk
Direct your audience
Dimensions
Fields within the data that are usually more discrete or categorical in nature
-contain qualitative values
-affect the level of detail
-names, dates
Measures
Contain numeric quantitative values that you can measure
ex: longitude and latitude
ex: unit price and quantity
Green field/pills
measures dimensions that are continuous
-continuous field values treated as an infinite range
-ex: sum(profit) or year(date)
Blue field/pills
measures fields that are discrete
Dual axis chart/Combo chart
a chart that has 2 different types of charts
ex: column chart + line chart
Boolean calculations
True or False statements
Quick Table Calculations
allows you to apply a built in calculation to your visualization
Trend Lines / Regression
Used to estimate the trend or relationship between variables
Reference Line
A reference line may be defined as the line based on some aggregate function which is used to draw on visualization.
Live vs Extracted data
Live: live connection to your data, auto updates
Extracted: compressed snapshot of your data stored locally
Dates: discrete vs continuous
Continuous: Show how data changes over a range of time (line chart)
Discrete: show a specific unit of time(bar graph)
Filters vs Paramters:
Filters: specific to a data source
Parameters: used across entire workbook
Anscombe’s Quartet
A set of 4 data sets that look very different when plotted, but have the same basic statisitcs
Moire Effect
when two patterns with similar frequencies interact with each other.
-perception of movement in a solid object
Hermann effect
Similar to moire effect but instead of bars creating the illusion, it’s squares
Gestalt Effect
the brain’s innate organizing tendencies allow us to perceive things as organized wholes rather than individual elements (pac man triangle)
Motion
animated presentation of frames of data
Medium
The physical strata on which data is displayd
Context
The sensory and emotional environment
Structured vs Unstructured data
Structured: Excel or tableau
Unstructured: Book or movie
Data lake
collecting and storing data in raw form
Data aggregation
sorting and filtering data
data cleaning
detecting and correcting corrupt or inaccurate information records from a data set
data granularity
level of detail considered in a model or represented in an analysis
Descriptive analytics
describe past performance and history
Predictive analytics
predict future trends and patterns
Prescriptive analytics
indicating the best decisions to make or course of action to take
4 Key characteristics of big data
Variety: form of data (structured vs unstructured)
Veracity: uncertainty of data
Volume: scale/amount of data
Velocity: analysis of streaming data as it travels around the internet
Tooltip
show information when you hover your mouse over a datapoint in a Tableau visualization
T/F: To create a map in Tableau, you must drag latitude and longitude to “columns” and “rows.”
False
