2023 VIS Line Bias

D
Average Estimates in Line Graphs are
Biased Toward Areas of Higher Variability
Dominik Moritz, Lace Padilla, Francis Nguyen, and Steven Franconeri
Bias Towards Areas of Higher Variability
Experiments
Results
Bias Towards Areas of Higher Variability
Experiments
Results
William Playfair, Commercial and Political Atlas, 1786
Change
of
continuous
variable
Continuous variable, typically time
Stocks
Human Vitals
Sensor Data
Learning Curves
https://en.wikipedia.org/wiki/Learning_curve_(machine_learning)
Visualization Analysis and Design by Tamara Munzner
2023 VIS Line Bias
2023 VIS Line Bias
2023 VIS Line Bias
2023 VIS Line Bias
Increased Variability
Increased visual weight may
capture attention
Increased salience may
bias average estimates
Increasing
variability
2023 VIS Line Bias
2023 VIS Line Bias
Research questions
Line graph
Research questions
Line graph
Points equally spaced along the x-axis
Research questions
Line graph
Points equally spaced along the x-axis
Points spaced along the arc of the line
Experiment 1
Experiment 2
Research questions
Bias Towards Areas of Higher Variability
Experiments
Results
Experiment interface
Stimuli
Base series generated from
geometric Brownian motion
Stimuli
Base series generated from
geometric Brownian motion
Add noise based
on y-position
Low variability
High variability
Stimuli
Base series generated from
geometric Brownian motion
Add noise based
on y-position
Stimuli
Base series generated from
geometric Brownian motion
Scale
Add noise based
on y-position
Stimuli
Parameters:
• Seed
• Low and high variability
levels
• Mirrored or not mirrored
...
Experiment 1
2
⨉
2
0.15 Variability 0.4 Variability
Variability
Upper
Variability
Lower
All within subject
140 Participants
48 trials per participant
140 Participants
Experiment 1 Experiment 2
2
⨉
2
0.15 Variability 0.4 Variability
Variability
Upper
Variability
Lower
2
⨉
2
0.4 Variability
Variability
Upper
Variability
Lower
0 Variability
⨉
3
Line Point Arc Point
All within subject Variability and upper vs lower within subject
Mark type between subject
48 trials per participant
420 Participants
48 trials per participant
Hypotheses
H1: Estimation error will be signi
fi
cantly di
ff
erent than zero.
H2: There will be signi
fi
cantly more estimation error for trials with higher
variability compared to lower variability.
H3: Estimation error will be observed in the direction of the increased variability.
H4: There will be signi
fi
cantly more estimation error for trials with higher
variability than no additional variability.
H5: The least variability-overweighting will occur in graphs with points that are
equally spaced along the x-axis.
Preregistered Experiments
osf.io/j2vn3 osf.io/7h2zy
Bias Towards Areas of Higher Variability
Experiments
Results
Experiment 1
Is there a bias?
Experiment 1
Is there a bias?
Experiment 1
Is there a bias?
Experiment 2
Does the mark type a
ff
ect the bias?
Experiment 2
Does the mark type a
ff
ect the bias?
Experiment 2
Does the mark type a
ff
ect the bias?
Additional analyses in the paper
We asked participants for their
strategies and looked at how
strategies a
ff
ect estimation error.
We can model estimation error for
arbitrary line graphs based on the
true average and the average of
the points drawn along the arc.
Limitations of unbalanced and few stimuli
Thanks to Steve Haroz for pointing out this issue!
We used the same 12 seeds for each participant rather than a new seed for
each stimulus. This introduces biases.
Limitations of unbalanced and few stimuli
Thanks to Steve Haroz for pointing out this issue!
9/12 stimuli seeds have true averages below 0.5
➡ when using responses of 0.5, the error distributions ideally overlap
These should be the same
Our normalization (Section 4.2)
ensures that these are the same
Materials available at osf.io/aupbk/
Average Estimates in Line Graphs are
Biased Toward Areas of Higher Variability
domoritz@cmu.edu or vis.social/@dom
1 of 41

Recommended

StatisticsStatistics
Statisticsmandrewmartin
1.2K views49 slides
HypothesisHypothesis
Hypothesisdebarati roy
50 views16 slides
StatisticsStatistics
Statisticsmandrewmartin
596 views48 slides

More Related Content

Similar to 2023 VIS Line Bias(20)

TEST OF SIGNIFICANCE.pptxTEST OF SIGNIFICANCE.pptx
TEST OF SIGNIFICANCE.pptx
JoicePjiji306 views
HypothesisHypothesis
Hypothesis
jyotsna dwivedi327 views
Oarsi jr1Oarsi jr1
Oarsi jr1
Jonas Ranstam PhD371 views
Ds vs Is discuss 3.1Ds vs Is discuss 3.1
Ds vs Is discuss 3.1
Makati Science High School286 views
3.2 measures of variation3.2 measures of variation
3.2 measures of variation
leblance3.5K views
Data and graphsData and graphs
Data and graphs
My_VivJaan1.9K views
BiostatisticsBiostatistics
Biostatistics
priyarokz35.8K views
Conditional Correlation 2009Conditional Correlation 2009
Conditional Correlation 2009
yamanote579 views
Chapter 1 biostatistics by Dr Ahmed HusseinChapter 1 biostatistics by Dr Ahmed Hussein
Chapter 1 biostatistics by Dr Ahmed Hussein
Dr Ghaiath Hussein98 views
Important terminologiesImportant terminologies
Important terminologies
Rolling Plans Pvt. Ltd.772 views
TTests.pptTTests.ppt
TTests.ppt
MUzair211 view

Recently uploaded(20)

SIMPLE PRESENT TENSE_new.pptxSIMPLE PRESENT TENSE_new.pptx
SIMPLE PRESENT TENSE_new.pptx
nisrinamadani2135 views
Narration lesson plan.docxNarration lesson plan.docx
Narration lesson plan.docx
Tariq KHAN84 views
Streaming Quiz 2023.pdfStreaming Quiz 2023.pdf
Streaming Quiz 2023.pdf
Quiz Club NITW77 views
STERILITY TEST.pptxSTERILITY TEST.pptx
STERILITY TEST.pptx
Anupkumar Sharma97 views
Plastic waste.pdfPlastic waste.pdf
Plastic waste.pdf
alqaseedae72 views
NS3 Unit 2 Life processes of animals.pptxNS3 Unit 2 Life processes of animals.pptx
NS3 Unit 2 Life processes of animals.pptx
manuelaromero201368 views
STYP infopack.pdfSTYP infopack.pdf
STYP infopack.pdf
Fundacja Rozwoju Społeczeństwa Przedsiębiorczego125 views
How to present dataHow to present data
How to present data
Pavel Šabatka41 views
Chemistry of sex hormones.pptxChemistry of sex hormones.pptx
Chemistry of sex hormones.pptx
RAJ K. MAURYA93 views
Lecture: Open InnovationLecture: Open Innovation
Lecture: Open Innovation
Michal Hron68 views
Marilyn And Len Exchanges, EssayMarilyn And Len Exchanges, Essay
Marilyn And Len Exchanges, Essay
Melissa Dudas69 views
CWP_23995_2013_17_11_2023_FINAL_ORDER.pdfCWP_23995_2013_17_11_2023_FINAL_ORDER.pdf
CWP_23995_2013_17_11_2023_FINAL_ORDER.pdf
SukhwinderSingh895865452 views

2023 VIS Line Bias