refs.bib

@article{petersonGestaltPrincipleSimilarity2013,
  title = {The {{Gestalt}} Principle of Similarity Benefits Visual Working Memory},
  author = {Peterson, Dwight J. and Berryhill, Marian E.},
  year = {2013},
  month = dec,
  journal = {Psychonomic Bulletin \& Review},
  volume = {20},
  number = {6},
  pages = {1282--1289},
  issn = {1531-5320},
  doi = {10.3758/s13423-013-0460-x},
  urldate = {2025-06-04},
}

@article{pomerantzGroupingEmergentFeatures2011,
  title = {Grouping and Emergent Features in Vision: {{Toward}} a Theory of Basic {{Gestalts}}.},
  shorttitle = {Grouping and Emergent Features in Vision},
  author = {Pomerantz, James R. and Portillo, Mary C.},
  year = {2011},
  journal = {Journal of Experimental Psychology: Human Perception and Performance},
  volume = {37},
  number = {5},
  pages = {1331--1349},
  issn = {1939-1277, 0096-1523},
  doi = {10.1037/a0024330},
  urldate = {2025-06-04},
}

@article{lupyanConceptualGroupingEffect2008,
  title = {The Conceptual Grouping Effect: {{Categories}} Matter (and Named Categories Matter More)},
  shorttitle = {The Conceptual Grouping Effect},
  author = {Lupyan, Gary},
  year = {2008},
  month = aug,
  journal = {Cognition},
  volume = {108},
  number = {2},
  pages = {566--577},
  issn = {0010-0277},
  doi = {10.1016/j.cognition.2008.03.009},
  urldate = {2025-06-04},
}

@article{zekiFunctionalSpecializationGeneralization2013,
  title = {Functional Specialization and Generalization for Grouping of Stimuli Based on Colour and Motion},
  author = {Zeki, Semir and Stutters, Jonathan},
  year = {2013},
  month = jun,
  journal = {NeuroImage},
  volume = {73},
  pages = {156--166},
  issn = {1053-8119},
  doi = {10.1016/j.neuroimage.2013.02.001},
  urldate = {2025-06-04},
}

@article{robinsonPerceptionCognitiveImplications,
  ids = {robinsonPerceptionCognitiveImplicationsa},
  title = {Perception and {{Cognitive Implications}} of {{Logarithmic Scales}} for {{Exponentially Increasing Data}}: {{Perceptual Sensitivity Tested}} with {{Statistical Lineups}}},
  shorttitle = {Perception and {{Cognitive Implications}} of {{Logarithmic Scales}} for {{Exponentially Increasing Data}}},
  author = {Robinson, Emily A. and Howard, Reka and Vanderplas, Susan},
  journal = {Journal of Computational and Graphical Statistics},
  year = {2025},
  volume = {0},
  number = {ja},
  pages = {1--14},
  publisher = {ASA Website},
  issn = {1061-8600},
  doi = {10.1080/10618600.2025.2476097},
  urldate = {2025-03-11},
  abstract = {Logarithmic transformations are a standard solution to displaying data that span several magnitudes within a single graph. This paper investigates the impact of log scales on perceptual sensitivity through a visual inference experiment using statistical lineups. Our study evaluated participant's ability to detect differences between exponentially increasing data, characterized by varying levels of curvature, using both linear and logarithmic scales. Participants were presented with a series of plots and asked to identify the panel that appeared most different from the others. Due to the choice of scale altering the contextual appearance of the data, the results revealed slight perceptual advantages for both scales depending on the curvatures of the compared data. This study serves as the initial part of a three-paper series dedicated to understanding the perceptual and cognitive implications of using logarithmic scales for visualizing exponentially increasing data. These studies serve as an example of multi-modal graphical testing, examining different levels of engagement and interaction with graphics to establish nuanced and specific guidelines for graphical design.},
  keywords = {graphical testing,log scales,visual inference},

}

@article{brysbaertHowManyParticipants2019,
  title = {How Many Participants Do We Have to Include in Properly Powered Experiments? {{A}} Tutorial of Power Analysis with Reference Tables},
  shorttitle = {How Many Participants Do We Have to Include in Properly Powered Experiments?},
  author = {Brysbaert, Marc},
  year = {2019},
  month = jul,
  journal = {Journal of Cognition},
  volume = {2},
  number = {1},
  issn = {2514-4820},
  doi = {10.5334/joc.72},
  urldate = {2025-03-15},
  abstract = {Given that an effect size of d = .4 is a good first estimate of the smallest effect size of interest in psychological research, we already need over 50 participants for a simple comparison of two within-participants conditions if we want to run a study with 80\% power. This is more than current practice. In addition, as soon as a between-groups variable or an interaction is involved, numbers of 100, 200, and even more participants are needed. As long as we do not accept these facts, we will keep on running underpowered studies with unclear results. Addressing the issue requires a change in the way research is evaluated by supervisors, examiners, reviewers, and editors. The present paper describes reference numbers needed for the designs most often used by psychologists, including single-variable between-groups and repeated-measures designs with two and three levels, two-factor designs involving two repeated-measures variables or one between-groups variable and one repeated-measures variable (split-plot design). The numbers are given for the traditional, frequentist analysis with p \< .05 and Bayesian analysis with BF \> 10. These numbers provide researchers with a standard to determine (and justify) the sample size of an upcoming study. The article also describes how researchers can improve the power of their study by including multiple observations per condition per participant.},
  langid = {american},

}

@article{loyVariationsQQPlots2016,
  title = {Variations of {{Q-Q Plots}}: {{The Power}} of {{Our Eyes}}!},
  shorttitle = {Variations of {{{\emph{Q}}}} -- {{{\emph{Q}}}} {{Plots}}},
  author = {Loy, Adam and Follett, Lendie and Hofmann, Heike},
  year = {2016},
  month = apr,
  journal = {The American Statistician},
  volume = {70},
  number = {2},
  pages = {202--214},
  issn = {0003-1305, 1537-2731},
  doi = {10.1080/00031305.2015.1077728},
  url = {https://www.tandfonline.com/doi/full/10.1080/00031305.2015.1077728},
  urldate = {2019-05-10},
  abstract = {In statistical modeling, we strive to specify models that resemble data collected in studies or observed from processes. Consequently, distributional specification and parameter estimation are central to parametric models. Graphical procedures, such as the quantile--quantile (Q--Q) plot, are arguably the most widely used method of distributional assessment, though critics find their interpretation to be overly subjective. Formal goodness of fit tests are available and are quite powerful, but only indicate whether there is a lack of fit, not why there is lack of fit. In this article, we explore the use of the lineup protocol to inject rigor into graphical distributional assessment and compare its power to that of formal distributional tests. We find that lineup tests are considerably more powerful than traditional tests of normality. A further investigation into the design of Q--Q plots shows that de-trended Q--Q plots are more powerful than the standard approach as long as the plot preserves distances in x and y to be the same. While we focus on diagnosing nonnormality, our approach is general and can be directly extended to the assessment of other distributions.},
  langid = {english},
}

@article{liPlotWorthThousand2024,
  title = {A {{Plot}} Is {{Worth}} a {{Thousand Tests}}: {{Assessing Residual Diagnostics}} with the {{Lineup Protocol}}},
  shorttitle = {A {{Plot}} Is {{Worth}} a {{Thousand Tests}}},
  author = {Li, Weihao and Cook, Dianne and Tanaka, Emi and Vanderplas, Susan},
  year = {2024},
  month = may,
  journal = {Journal of Computational and Graphical Statistics},
  publisher = {Taylor \& Francis},
  issn = {1061-8600},
  url = {https://www.tandfonline.com/doi/abs/10.1080/10618600.2024.2344612},
  urldate = {2024-06-18},
  abstract = {Regression experts consistently recommend plotting residuals for model diagnosis, despite the availability of many numerical hypothesis test procedures designed to use residuals to assess problems ...},
  copyright = {{\copyright} 2024 The Author(s). Published with license by Taylor \& Francis Group, LLC.},
  langid = {english},
}

@article{vanderplasSpatialReasoningData2016,
  ids = {vanderplasSpatialReasoningData2016a,vanderplasSpatialReasoningData2016b},
  title = {Spatial {{Reasoning}} and {{Data Displays}}},
  author = {Vanderplas, Susan and Hofmann, Heike},
  year = {2016},
  month = jan,
  journal = {IEEE Transactions on Visualization \& Computer Graphics},
  volume = {22},
  number = {1},
  pages = {459--468},
  issn = {1077-2626},
  doi = {10.1109/TVCG.2015.2469125},
  urldate = {2019-01-26},
}

@article{loyModelChoiceDiagnostics2017,
  ids = {loyModelChoiceDiagnostics2017a},
  title = {Model {{Choice}} and {{Diagnostics}} for {{Linear Mixed-Effects Models Using Statistics}} on {{Street Corners}}},
  author = {Loy, Adam and Hofmann, Heike and Cook, Dianne},
  year = {2017},
  month = jul,
  journal = {Journal of Computational and Graphical Statistics},
  volume = {26},
  number = {3},
  pages = {478--492},
  publisher = {Taylor \& Francis},
  issn = {1061-8600, 1537-2715},
  doi = {10.1080/10618600.2017.1330207},
  urldate = {2019-05-10},
  abstract = {The complexity of linear mixed-effects (LME) models means that traditional diagnostics are rendered less effective. This is due to a breakdown of asymptotic results, boundary issues, and visible patterns in residual plots that are introduced by the model fitting process. Some of these issues are well known and adjustments have been proposed. Working with LME models typically requires that the analyst keeps track of all the special circumstances that may arise. In this article, we illustrate a simpler but generally applicable approach to diagnosing LME models. We explain how to use new visual inference methods for these purposes. The approach provides a unified framework for diagnosing LME fits and for model selection. We illustrate the use of this approach on several commonly available datasets. A large-scale Amazon Turk study was used to validate the methods. R code is provided for the analyses. Supplementary materials for this article are available online.},
  langid = {english},
  keywords = {Lineup protocol,Model diagnostics,Model selection,Statistical graphics,Visual inference},
}

@inproceedings{haiderStrategiesDetectingDifference2021,
	location = {Cham},
	title = {Strategies for Detecting Difference in Map Line-Up Tasks},
	isbn = {978-3-030-85613-7},
	doi = {10.1007/978-3-030-85613-7_36},
	abstract = {The line-up task hides a plot of real data amongst a line-up of decoys built around some plausible null hypothesis. It has been proposed as a mechanism for lending greater reliability and confidence to statistical inferences made from data graphics. The proposition is a seductive one, but whether or not line-ups guarantee consistent interpretation of statistical structure is an open question, especially when applied to representations of geo-spatial data. We build on empirical work around the extent to which statistical structure can be reliably judged in map line-ups, paying particular attention to the strategies employed when making line-up judgements. We conducted in-depth experiments with 19 graduate students equipped with a moderate background in geovisualization. The experiments consisted of a series of map line-up tasks with two map designs: choropleth maps and a centroid-dot alternative. We chose challenging tasks in the hope of exposing participants' sensemaking activities. Through structured qualitative analysis of think-aloud protocols, we identify six sensemaking strategies and evaluate their effects in making judgements from map line-ups. We find five sensemaking strategies applicable to most visualization types, but one that seems particular to map line-up designs. We could not identify one single successful strategy, but users adopt a mix of different strategies, depending on the circumstances. We also found that choropleth maps were easier to use than centroid-dot maps.},
	pages = {558--578},
	booktitle = {Human-Computer Interaction - {INTERACT} 2021},
	publisher = {Springer International Publishing},
	author = {Haider, Johanna Doppler and Pohl, Margit and Beecham, Roger and Dykes, Jason},
	editor = {Ardito, Carmelo and Lanzilotti, Rosa and Malizia, Alessio and Petrie, Helen and Piccinno, Antonio and Desolda, Giuseppe and Inkpen, Kori},
	year = {2021},
	langid = {english},
	keywords = {Visual perception, Graphical inference, Cognitive strategies, Geovisualization, Sensemaking, Spatial autocorrelation, Thinking-aloud},

}

@article{leeHowPeopleMake2016,
	title = {How do People Make Sense of Unfamiliar Visualizations?: A Grounded Model of Novice's Information Visualization Sensemaking},
	volume = {22},
	issn = {1941-0506},
	doi = {10.1109/TVCG.2015.2467195},
	shorttitle = {How do People Make Sense of Unfamiliar Visualizations?},
	abstract = {In this paper, we would like to investigate how people make sense of unfamiliar information visualizations. In order to achieve the research goal, we conducted a qualitative study by observing 13 participants when they endeavored to make sense of three unfamiliar visualizations (i.e., a parallel-coordinates plot, a chord diagram, and a treemap) that they encountered for the first time. We collected data including audio/video record of think-aloud sessions and semi-structured interview; and analyzed the data using the grounded theory method. The primary result of this study is a grounded model of {NOvice}'s information {VIsualization} Sensemaking ({NOVIS} model), which consists of the five major cognitive activities: 1 encountering visualization, 2 constructing a frame, 3 exploring visualization, 4 questioning the frame, and 5 floundering on visualization. We introduce the {NOVIS} model by explaining the five activities with representative quotes from our participants. We also explore the dynamics in the model. Lastly, we compare with other existing models and share further research directions that arose from our observations.},
	pages = {499--508},
	number = {1},
	journal = {{IEEE} Transactions on Visualization and Computer Graphics},
	author = {Lee, Sukwon and Kim, Sung-Hee and Hung, Ya-Hsin and Lam, Heidi and Kang, Youn-Ah and Yi, Ji Soo},
	urldate = {2024-07-15},
	date = {2016-01},
	year = 2016,
}

@article{kulhavyCartographicExperienceThinking1992,
	title = {Cartographic Experience and Thinking Aloud about Thematic Maps},
	volume = {29},
	doi = {10.3138/H61J-VX35-J6WW-8111},
	pages = {1--9},
	number = {1},
	journal = {Cartographica},
	author = {Kulhavy and Pridemore and Stock},
	year = {1992},
}

@article{jakelSpatialFouralternativeForcedchoice2006,
	title = {Spatial four-alternative forced-choice method is the preferred psychophysical method for naive observers},
	volume = {6},
	issn = {1534-7362},
	doi = {10.1167/6.11.13},
	abstract = {H. R. Blackwell (1952) investigated the influence of different psychophysical methods and procedures on detection thresholds. He found that the temporal two-interval forced-choice method (2-{IFC}) combined with feedback, blocked constant stimulus presentation with few different stimulus intensities, and highly trained observers resulted in the "best" threshold estimates. This recommendation is in current practice in many psychophysical laboratories and has entered the psychophysicists' "folk wisdom" of how to run proper psychophysical experiments. However, Blackwell's recommendations explicitly require experienced observers, whereas many psychophysical studies, particularly with children or within a clinical setting, are performed with naive observers. In a series of psychophysical experiments, we find a striking and consistent discrepancy between naive observers' behavior and that reported for experienced observers by Blackwell: Naive observers show the "best" threshold estimates for the spatial four-alternative forced-choice method (4-{AFC}) and the worst for the commonly employed temporal 2-{IFC}. We repeated our study with a highly experienced psychophysical observer, and he replicated Blackwell's findings exactly, thus suggesting that it is indeed the difference in psychophysical experience that causes the discrepancy between our findings and those of Blackwell. In addition, we explore the efficiency of different methods and show 4-{AFC} to be more than 3.5 times more efficient than 2-{IFC} under realistic conditions. While we have found that 4-{AFC} consistently gives lower thresholds than 2-{IFC} in detection tasks, we have found the opposite for discrimination tasks. This discrepancy suggests that there are large extrasensory influences on thresholds-sensory memory for {IFC} methods and spatial attention for spatial forced-choice methods-that are critical but, alas, not part of theoretical approaches to psychophysics such as signal detection theory.},
	pages = {13},
	number = {11},
	journal = {Journal of Vision},
	shortjournal = {Journal of Vision},
	author = {J{\"a}kel, Frank and Wichmann, Felix A.},
	urldate = {2025-03-14},
	date = {2006-11-10},
	year = 2006
}

@article{schuttPainfreeAccurateBayesian2016,
	title = {Painfree and accurate Bayesian estimation of psychometric functions for (potentially) overdispersed data},
	volume = {122},
	issn = {0042-6989},
	doi = {10.1016/j.visres.2016.02.002},
	abstract = {The psychometric function describes how an experimental variable, such as stimulus strength, influences the behaviour of an observer. Estimation of psychometric functions from experimental data plays a central role in fields such as psychophysics, experimental psychology and in the behavioural neurosciences. Experimental data may exhibit substantial overdispersion, which may result from non-stationarity in the behaviour of observers. Here we extend the standard binomial model which is typically used for psychometric function estimation to a beta-binomial model. We show that the use of the beta-binomial model makes it possible to determine accurate credible intervals even in data which exhibit substantial overdispersion. This goes beyond classical measures for overdispersion -- goodness-of-fit -- which can detect overdispersion but provide no method to do correct inference for overdispersed data. We use Bayesian inference methods for estimating the posterior distribution of the parameters of the psychometric function. Unlike previous Bayesian psychometric inference methods our software implementation -- psignifit 4 -- performs numerical integration of the posterior within automatically determined bounds. This avoids the use of Markov chain Monte Carlo ({MCMC}) methods typically requiring expert knowledge. Extensive numerical tests show the validity of the approach and we discuss implications of overdispersion for experimental design. A comprehensive {MATLAB} toolbox implementing the method is freely available; a python implementation providing the basic capabilities is also available.},
	pages = {105--123},
	journal = {Vision Research},
	shortjournal = {Vision Research},
	author = {Sch{\"u}tt, Heiko H. and Harmeling, Stefan and Macke, Jakob H. and Wichmann, Felix A.},
	urldate = {2025-03-14},
	date = {2016-05-01},
	year = 2016,
	keywords = {Bayesian inference, Beta-binomial model, Confidence intervals, Credible intervals, Non-stationarity, Overdispersion, Psychometric function, Psychophysical methods},
}

@article{valentinDesigningOptimalBehavioral2024,
	title = {Designing optimal behavioral experiments using machine learning},
	volume = {13},
	issn = {2050-084X},
	doi = {10.7554/eLife.86224},
	abstract = {Computational models are powerful tools for understanding human cognition and behavior. They let us express our theories clearly and precisely and offer predictions that can be subtle and often counter-intuitive. However, this same richness and ability to surprise means our scientific intuitions and traditional tools are ill-suited to designing experiments to test and compare these models. To avoid these pitfalls and realize the full potential of computational modeling, we require tools to design experiments that provide clear answers about what models explain human behavior and the auxiliary assumptions those models must make. Bayesian optimal experimental design ({BOED}) formalizes the search for optimal experimental designs by identifying experiments that are expected to yield informative data. In this work, we provide a tutorial on leveraging recent advances in {BOED} and machine learning to find optimal experiments for any kind of model that we can simulate data from, and show how by-products of this procedure allow for quick and straightforward evaluation of models and their parameters against real experimental data. As a case study, we consider theories of how people balance exploration and exploitation in multi-armed bandit decision-making tasks. We validate the presented approach using simulations and a real-world experiment. As compared to experimental designs commonly used in the literature, we show that our optimal designs more efficiently determine which of a set of models best account for individual human behavior, and more efficiently characterize behavior given a preferred model. At the same time, formalizing a scientific question such that it can be adequately addressed with {BOED} can be challenging and we discuss several potential caveats and pitfalls that practitioners should be aware of. We provide code to replicate all analyses as well as tutorial notebooks and pointers to adapt the methodology to different experimental settings.},
	journal = {{eLife}},
	shortjournal = {{eLife}},
	author = {Valentin, Simon and Kleinegesse, Steven and Bramley, Neil R and Seri{\'e}s, Peggy and Gutmann, Michael U and Lucas, Christopher G},
	urldate = {2025-03-14},
	date = {2024-01-23},
	year = 2024,
}

@article{shahConceptualLimitationsComprehending1995,
	title = {Conceptual Limitations in Comprehending Line Graphs},
	volume = {124},
	doi = {10.1037/1076-898X.4.2.75},
	pages = {43--61},
	number = {1},
	journal = {Journal of Experimental Psychology},
	author = {Shah, Priti and Carpenter, Patricia A},
	date = {1995},
	langid = {english},

}

@article{carpenterModelPerceptualConceptual1998,
	title = {A model of the perceptual and conceptual processes in graph comprehension.},
	volume = {4},
	issn = {1939-2192},
	doi = {10.1037/1076-898X.4.2.75},
	pages = {75},
	number = {2},
	journal = {Journal of Experimental Psychology: Applied},
	author = {Carpenter, Patricia A. and Shah, Priti},
	urldate = {2019-01-30},
	date = {1998-06-01},
	keywords = {college students, Comprehension, gaze pattern \& verbal descriptions of line graphs, Graphical Displays, Human Information Storage, Models, Pattern Discrimination, test of model integrated pattern-recognition \& encoding \& interpretive processes in graph comprehension},

}

@inproceedings{heerCrowdsourcingGraphicalPerception2010,
	location = {Atlanta Georgia {USA}},
	title = {Crowdsourcing graphical perception: using mechanical turk to assess visualization design},
	isbn = {978-1-60558-929-9},
	doi = {10.1145/1753326.1753357},
	shorttitle = {Crowdsourcing graphical perception},
	eventtitle = {{CHI} '10: {CHI} Conference on Human Factors in Computing Systems},
	pages = {203--212},
	booktitle = {Proceedings of the {SIGCHI} Conference on Human Factors in Computing Systems},
	publisher = {{ACM}},
	author = {Heer, Jeffrey and Bostock, Michael},
	urldate = {2023-07-31},
	date = {2010-04-10},
	year = 2010,
}


@book{andrichRaschModelsMeasurement1988,
	location = {Newbury Park, California},
	edition = {1},
	title = {Rasch Models for Measurement},
	isbn = {978-1-5063-1937-7},
	series = {Quantitative Applications},
	shorttitle = {Rasch Models for Measurement},
	abstract = {Examines the use of Rasch measurement models in the social sciences. This lucid introduction first focuses on general principles, so the applications and algebra of the model can be readily understood. Andrich then connects Rasch models to common procedures for social science measurement. Avoiding polemics, Andrich's presentation allows comparison between the Rasch models and other, better known measurement approaches. Rasch Models For Measurement concentrates on the simple logistic model, the most elementary and commonly used of the Rasch models. This excellent introduction uses one example from personality inventory throughout to provide continuity as the procedures and statistical arguments are explained. Essential reading for all researchers and students who use measurement models. "A valuable asset to those of us who are concerned with teaching measurement issues. . . . My only quibble is that we have had to wait so long for what is a clear, concise and very approachable introduction to a fairly complex area. . . . For its size this volume covers a lot of ground and it would seem to be an ideal book for postgraduate students with a special interest in psychometrics and professional psychologists who are concerned with measurement and assessment. . . . An ideal primer." --The Statistician "Rasch Models for Measurement is a concise introduction to the general principles, philosophy, and methods that underlie the approach to measurement developed by Georg Rasch (1960/1980). This book is a welcome addition to the Sage series on Quantitative Applications in the Social Sciences, or (as my students describe them) "the little green books." This series introduces methodological issues for individuals with limited backgrounds in statistics and mathematics, and Andrich has provided a useful resource for these individuals. . . . This book can be recommended for graduate students and colleagues who want a basic understanding of the Rasch model." --Applied Psychological Measurement},
	pagetotal = {101},
	number = {07-068},
	publisher = {{SAGE} Publications},
	author = {Andrich, David},
	date = {1988-03-01},
	year = 1988,
}

@article{luModelingJustNoticeable2022,
	title = {Modeling Just Noticeable Differences in Charts},
	volume = {28},
	issn = {1941-0506},
	doi = {10.1109/TVCG.2021.3114874},
	abstract = {One of the fundamental tasks in visualization is to compare two or more visual elements. However, it is often difficult to visually differentiate graphical elements encoding a small difference in value, such as the heights of similar bars in bar chart or angles of similar sections in pie chart. Perceptual laws can be used in order to model when and how we perceive this difference. In this work, we model the perception of Just Noticeable Differences ({JNDs}), the minimum difference in visual attributes that allow faithfully comparing similar elements, in charts. Specifically, we explore the relation between {JNDs} and two major visual variables: the intensity of visual elements and the distance between them, and study it in three charts: bar chart, pie chart and bubble chart. Through an empirical study, we identify main effects on {JND} for distance in bar charts, intensity in pie charts, and both distance and intensity in bubble charts. By fitting a linear mixed effects model, we model {JND} and find that {JND} grows as the exponential function of variables. We highlight several usage scenarios that make use of the {JND} modeling in which elements below the fitted {JND} are detected and enhanced with secondary visual cues for better discrimination.},
	pages = {718--726},
	number = {1},
	journal = {{IEEE} Transactions on Visualization and Computer Graphics},
	author = {Lu, Min and Lanir, Joel and Wang, Chufeng and Yao, Yucong and Zhang, Wen and Deussen, Oliver and Huang, Hui},
	date = {2022-01},
	year = 2022
	}

@article{chowdhury2018,
	title = {Measuring Lineup Difficulty By Matching Distance Metrics With Subject Choices in Crowd-Sourced Data},
	author = {Chowdhury, Niladri Roy and Cook, Dianne and Hofmann, Heike and Majumder, Mahbubul},
	year = {2018},
	month = {01},
	date = {2018-01-02},
	journal = {Journal of Computational and Graphical Statistics},
	pages = {132--145},
	volume = {27},
	number = {1},
	doi = {10.1080/10618600.2017.1356323},
	langid = {en}
}

@article{clusters,
	title = {Clusters {Beat} {Trend}!? {Testing} {Feature} {Hierarchy} in {Statistical} {Graphics}},
	volume = {26},
	copyright = {All rights reserved},
	issn = {1061-8600},
	doi = {10.1080/10618600.2016.1209116},
	abstract = {Graphics are very effective for communicating numerical information quickly and efficiently, but many of the design choices we make are based on subjective measures, such as personal taste or conventions of the discipline rather than objective criteria. We briefly introduce perceptual principles such as preattentive features and gestalt heuristics, and then discuss the design and results of a factorial experiment examining the effect of plot aesthetics such as color and trend lines on participants' assessment of ambiguous data displays. The quantitative and qualitative experimental results strongly suggest that plot aesthetics have a significant impact on the perception of important features in data displays. Supplementary materials for this article are available online.},
	number = {2},
	urldate = {2018-12-12},
	journal = {Journal of Computational and Graphical Statistics},
	author = {Vanderplas, Susan and Hofmann, Heike},
	month = apr,
	year = {2017},
	keywords = {Lineup protocol, Preattentive features, Saliency of plot aesthetics, User study, Visual inference, two-target lineup},
	pages = {231--242}
}

@inproceedings{vanderplasEscapingFlatlandGraphics2024,
  title = {Escaping {{Flatland}}: {{Graphics}}, {{Dimensionality}}, and~{{Human Perception}}},
  shorttitle = {Escaping {{Flatland}}},
  booktitle = {Human {{Interface}} and the {{Management}} of {{Information}}},
  author = {Vanderplas, Susan and Blankenship, Erin and Wiederich, Tyler},
  editor = {Mori, Hirohiko and Asahi, Yumi},
  year = {2024},
  pages = {140--156},
  publisher = {Springer Nature Switzerland},
  address = {Cham},
  doi = {10.1007/978-3-031-60114-9_11}
}

@article{riceTestingPerceptualAccuracy2024,
  title = {Testing {{Perceptual Accuracy}} in a {{U}}.{{S}}. {{General Population Survey Using Stacked Bar Charts}}},
  author = {Rice, Kiegan and Hofmann, Heike and {du Toit}, Nola and Mulrow, Edward},
  year = {2024},
  month = mar,
  journal = {Journal of Data Science},
  pages = {1--18},
  publisher = {School of Statistics, Renmin University of China},
  issn = {1680-743X, 1683-8602},
  doi = {10.6339/24-JDS1121},
  urldate = {2024-03-13}
}

@article{juOneModelThat2024,
  title = {One {{Model}} That Fits Them {{All}}: {{Psychometrics}} with {{Generalized Linear Mixed Effects Models}}},
  author = {Ju, Wanqian (Will) and Vanderplas, Susan and Hofmann, Heike},
  year = {2024},
  journal = {Electronic Imaging},
  pages = {1--9},
  publisher = {{Society for Imaging Science and Technology}},
  doi = {10.2352/EI.2023.35.1.VDA-A01},
  urldate = {2024-04-02},
  abstract = {Abstract The Conference on Visualization and Data Analysis (VDA) 2023 covers all research, development, and application aspects of data visualization and visual analytics. Since the first VDA conference was held in 1994, the annual event has grown steadily into a major venue for visualization researchers and practitioners from around the world to present their work and share their experiences. We invite you to participate by submitting your original research as a full paper, for an oral or interactive (poster) presentation, and attending VDA in the upcoming year.},
  langid = {english},

}

@article{sineillusion,
	title = {Signs of the {Sine} {Illusion} -- {Why} {We} {Need} to {Care}},
	volume = {24},
	copyright = {All rights reserved},
	issn = {1061-8600},
	doi = {10.1080/10618600.2014.951547},
	abstract = {Graphical representations have to be true to the data they display. Computational tools ensure this on a technical level. But we also need to take "flaws" of the human perceptual system into account. The sine illusion provides an example where human perception leads to systematic bias in the assessment of the optical stimulus, with a particularly notable impact on perception of time-series data with a seasonal component. In this article, we discuss the reasons for the illusion and various strategies useful to break the illusion or reduce its strength. We demonstrate the presence of the illusion in real-world and theoretical situations. We also present data from a user study, which demonstrate the dramatic effect the sine illusion can have on conclusions drawn from displayed data.},
	number = {4},
	urldate = {2018-12-12},
	journal = {Journal of Computational and Graphical Statistics},
	author = {Vanderplas, Susan and Hofmann, Heike},
	month = oct,
	year = {2015},
	keywords = {Graphics, Perception, Statistical graphics, Variance, sine illusion},
	pages = {1170--1190},
}

@article{power,
	title = {Graphical tests for power comparison of competing designs},
	volume = {18},
	doi = {10/f4fwkz},
	number = {12},
	journal = {IEEE Transactions on Visualization and Computer Graphics},
	author = {Hofmann, Heike and Follett, Lendie and Majumder, Mahbubul and Cook, Dianne},
	year = {2012},
	pages = {2441--2448},
}

@phdthesis{emily-diss,
	address = {Lincoln, NE},
	type = {Doctoral},
	title = {Human {Perception} of {Exponentially} {Increasing} {Data} {Displayed} on a {Log} {Scale} {Evaluated} {Through} {Experimental} {Graphics} {Tasks}},
	url = {https://github.com/earobinson95/EmilyARobinson-UNL-dissertation/raw/main/EmilyRobinson-final-dissertation.pdf},
	urldate = {2022-06-24},
	school = {University of Nebraska, Lincoln},
	author = {Robinson, Emily A.},
	month = jun,
	year = {2022},
}

@book{tufte,
	address = {USA},
	edition = {2},
	title = {The {Visual} {Display} of {Quantitative} {Information}},
	publisher = {Graphics Press},
	author = {Tufte, Edward},
	year = {1991},
}

@book{cairoTruthfulArtData2016,
	title = {The {Truthful} {Art}: {Data}, {Charts}, and {Maps} for {Communication}},
	isbn = {978-0-13-344053-9},
	shorttitle = {The {Truthful} {Art}},
	language = {en},
	publisher = {New Riders},
	author = {Cairo, Alberto},
	month = feb,
	year = {2016},
}

@book{cairoFunctionalArtIntroduction2012,
	title = {The {Functional} {Art}: {An} introduction to information graphics and visualization},
	isbn = {978-0-13-304136-1},
	shorttitle = {The {Functional} {Art}},
	language = {en},
	publisher = {New Riders},
	author = {Cairo, Alberto},
	month = aug,
	year = {2012},
}

@book{wilkinsonGrammarGraphics1999,
	address = {New York},
	title = {The grammar of graphics},
	isbn = {978-1-4757-3100-2 978-1-4757-3102-6},
	url = {http://public.ebookcentral.proquest.com/choice/publicfullrecord.aspx?p=3085765},
	abstract = {This book was written for statisticians, computer scientists, geographers, research and applied scientists, and others interested in visualizing data. It presents a unique foundation for producing almost every quantitative graphic found in scientific journals, newspapers, statistical packages, and data visualization systems. This foundation was designed for a distributed computing environment (Internet, Intranet, client-server), with special attention given to conserving computer code and system resources. While the tangible result of this work is a Java production graphics library (GPL) developed in collaboration with Dan Rope and Dan Carr, this book focuses on the deep structures involved in producing quantitative graphics from data. What are the rules that underly the production of pie charts, bar charts, scatterplots, function plots, maps, mosaics, radar charts? These rules are abstracted from the work of Bertin, Cleveland, Kosslyn, MacEachren, Pinker, Tufte, Tukey, Tobler, and other theorists of quantitative graphics. Those less interested in the theoretical and mathematical foundations can still get a sense of the richness and structure of the system by examining the numerous and often unique color graphics it can produce. Leland Wilkinson is Senior VP, SYSTAT Products at SPSS Inc. and Adjunct Professor of Statistics at Northwestern University. He wrote the SYSTAT statistical package and founded SYSTAT Inc. in 1984. Wilkinson joined SPSS in a 1994 acquisition and now works on research and development of graphical applications for data mining and statistics. He is a Fellow of the ASA and an Associate Editor of The American Statistician. In addition to journal articles and the original SYSTAT computer program and manuals, Wilkinson is the author (with Grant Blank and Chris Gruber) of Desktop Data Analysis with SYSTAT.},
	language = {en},
	urldate = {2020-01-29},
	publisher = {Springer},
	author = {Wilkinson, Leland},
	year = {1999},
}

@book{bertin1983semiology,
	title = {Semiology of graphics: diagrams, networks, maps},
	volume = {1},
	publisher = {University of Wisconsin press Madison},
	author = {Bertin, Jacques and Berg, William J},
	year = {1983},
}

@misc{ribeccaSearchChartsData,
	title = {The Data Visualisation Catalogue},
	howpublished = {https://datavizcatalogue.com},
	note = {Online; accessed 2022-06-25},
	author = {Ribecca, Severino},
	year = 2022
}


@article{asme-standards-graphics,
	author = {Joint committee on standards for graphic presentation},
	title = {Preliminary Report Published for the Purpose of Inviting Suggestions for the Benefit of the Committee},
	volume = {14},
	issn = {15225437},
	url = {http://www.jstor.org/stable/2965153},
	number = {112},
	urldate = {2022-06-25},
	journal = {Publications of the American Statistical Association},
	year = {1915},
	pages = {790--797},
}


@article{clevelandShapeParameterTwoVariable1988,
	title = {The {Shape} {Parameter} of a {Two}-{Variable} {Graph}},
	volume = {83},
	issn = {0162-1459},
	doi = {10.1080/01621459.1988.10478598},
	abstract = {The shape parameter of a two-variable graph is the ratio of the horizontal and vertical distances spanned by the data. For at least 70 years this parameter has received much attention in writings on data display, because it is a critical factor on two-variable graphs that show how one variable depends on the other. But despite the attention, there has been little systematic study. In this article the shape parameter and its effect on the visual decoding of slope information are studied through historical, empirical, theoretical, and experimental investigations. These investigations lead to a method for choosing the shape that maximizes the accuracy of slope judgments.},
	number = {402},
	urldate = {2022-06-25},
	journal = {Journal of the American Statistical Association},
	author = {Cleveland, William S. and McGill, Marylyn E. and McGill, Robert},
	month = jun,
	year = {1988},
	pages = {289--300},
}

@incollection{allenVisualizingScientificData2016,
	edition = {4},
	title = {Visualizing {Scientific} {Data}},
	isbn = {978-1-107-41578-2 978-1-107-05852-1},
	language = {en},
	urldate = {2022-06-25},
	booktitle = {Handbook of {Psychophysiology}},
	publisher = {Cambridge University Press},
	author = {Allen, Elena A. and Erhardt, Erik Barry},
	editor = {Cacioppo, John T. and Tassinary, Louis G. and Berntson, Gary G.},
	month = dec,
	year = {2016},
	doi = {10.1017/9781107415782.031},
	pages = {679--697},
}

@article{desnoyersTaxonomyVisualsScience2011,
	title = {Toward a {Taxonomy} of {Visuals} in {Science} {Communication}},
	volume = {58},
	abstract = {Purpose: To develop and present a systematic, hierarchical taxonomy of visuals used in science communication, in order to facilitate analysis as well as selection and design of visuals.
Methods: Iterative analysis of commonly used visuals and existing typologies and selection of a classification system.
Results: A taxonomy is proposed based on Linnean principles, which distinguishes three classes of visuals based on their information and sign content; these are subdivided in orders and families. A systematic nomenclature is described.
Conclusions: Used successfully in training sessions and research, the taxonomy offers the basis for the development of comprehensive guidelines and improvements in the design and usage of visuals.},
	language = {en},
	journal = {Technical Communication},
	number = {2},
	author = {Desnoyers, Luc},
	year = {2011},
	pages = {16},
}


@article{haemerDoubleScalesAre1948,
	title = {Double {Scales} are {Dangerous}},
	volume = {2},
	issn = {0003-1305, 1537-2731},
	doi = {10.1080/00031305.1948.10501588},
	language = {en},
	number = {3},
	urldate = {2020-06-26},
	journal = {The American Statistician},
	author = {Haemer, Kenneth W.},
	month = jun,
	year = {1948},
	pages = {24--24},
}

@book{fewInformationDashboardDesign2006,
	title = {Information {Dashboard} {Design}: {The} {Effective} {Visual} {Communication} of {Data}},
	isbn = {978-0-596-10016-2},
	shorttitle = {Information {Dashboard} {Design}},
	language = {en},
	publisher = {O'Reilly Media, Incorporated},
	author = {Few, Stephen},
	year = {2006},
}

@book{kosslynGraphDesignEye2006,
	title = {Graph {Design} for the {Eye} and {Mind}},
	isbn = {978-0-19-530662-0},
	language = {en},
	publisher = {Oxford University Press},
	author = {Kosslyn, Stephen M.},
	year = {2006}
}


@article{croxtonBarChartsCircle1927,
	title = {Bar {Charts} {Versus} {Circle} {Diagrams}},
	volume = {22},
	issn = {0162-1459},
	doi = {10.2307/2276829},
	number = {160},
	urldate = {2019-03-17},
	journal = {Journal of the American Statistical Association},
	author = {Croxton, Frederick E. and Stryker, Roy E.},
	year = {1927},
	pages = {473--482},
}

@article{croxtonGraphicComparisonsBars1932,
	title = {Graphic {Comparisons} by {Bars}, {Squares}, {Circles}, and {Cubes}},
	volume = {27},
	language = {en},
	number = {177},
	journal = {Journal of the American Statistical Association},
	author = {Croxton, Frederick E.},
	month = mar,
	year = {1932},
	pages = {54--60},
}

@article{eellsRelativeMeritsCircles1926,
	title = {The {Relative} {Merits} of {Circles} and {Bars} for {Representing} {Component} {Parts}},
	volume = {21},
	issn = {0162-1459},
	doi = {10.2307/2277140},
	number = {154},
	urldate = {2019-03-18},
	journal = {Journal of the American Statistical Association},
	author = {Eells, Walter Crosby},
	year = {1926},
	pages = {119--132},
}

@article{vonhuhnFurtherStudiesGraphic1927,
	title = {Further {Studies} in the {Graphic} {Use} of {Circles} and {Bars}: {A} {Discussion} of the {Eell}'s {Experiment}},
	volume = {22},
	issn = {0162-1459},
	shorttitle = {Further {Studies} in the {Graphic} {Use} of {Circles} and {Bars}},
	doi = {10.2307/2277346},
	number = {157},
	urldate = {2019-03-18},
	journal = {Journal of the American Statistical Association},
	author = {von Huhn, R.},
	year = {1927},
	pages = {31--39}
}
@article{feenstraOnlineCognitionFactors2017,
  title = {Online Cognition: Factors Facilitating Reliable Online Neuropsychological Test Results},
  shorttitle = {Online Cognition},
  author = {Feenstra, Heleen E. M. and Vermeulen, Ivar E. and Murre, Jaap M. J. and Schagen, Sanne B.},
  year = {2017},
  month = jan,
  journal = {The Clinical Neuropsychologist},
  volume = {31},
  number = {1},
  pages = {59--84},
  publisher = {Routledge},
  issn = {1385-4046},
  doi = {10.1080/13854046.2016.1190405},
  url = {10.1080/13854046.2016.1190405},
  urldate = {2025-03-16},
  abstract = {Objective: Online neuropsychological test batteries could allow for large-scale cognitive data collection in clinical studies. However, the few online neuropsychological test batteries that are currently available often still require supervision or lack proper psychometric evaluation. In this paper, we have outlined prerequisites for proper development and use of online neuropsychological tests, with the focus on reliable measurement of cognitive function in an unmonitored setting.Method: First, we identified several technical, contextual, and psychological factors that should be taken into account in order to facilitate reliable test results of online tests in the unmonitored setting. Second, we outlined a methodology of quality assurance needed in order to obtain reliable cognitive data in the long run.Results: Based on factors that distinguish the online unmonitored test setting from the traditional face-to-face setting, we provide a set of basic requirements and suggestions for optimal development and use of unmonitored online neuropsychological tests, including suggestions on acquiring reliability, validity, and norm scores.Conclusions: When properly addressing factors that could hamper reliable test results during development and use, online neuropsychological tests could aid large-scale data collection for clinical studies in the future. Investment in both proper development of online neuropsychological test platforms and the performance of accompanying psychometric studies is currently required.},
  pmid = {27266677},
  keywords = {cognition,neuropsychological test battery,Online testing,test validity,unsupervised}
}

@article{uittenhoveLabTestingWebTestingCognitive2023,
  title = {From {{Lab-Testing}} to {{Web-Testing}} in {{Cognitive Research}}: {{Who You Test}} Is {{More Important}} than How {{You Test}}},
  shorttitle = {From {{Lab-Testing}} to {{Web-Testing}} in {{Cognitive Research}}},
  author = {Uittenhove, Dr Kim and Jeanneret, Stephanie and Vergauwe, Evie},
  year = {2023},
  month = jan,
  journal = {Journal of Cognition},
  volume = {6},
  number = {1},
  pages = {13},
  doi = {10.5334/joc.259},
  url = {https://pmc.ncbi.nlm.nih.gov/articles/PMC9854315/},
  urldate = {2025-03-16},
  abstract = {The transition to web-testing, although promising, entails many new concerns. Web-testing is harder to monitor, so researchers need to ensure that the quality of the data collected is comparable to the quality of data typically achieved by ...},
  langid = {english},
  pmid = {36721797}
}
@article{peerDataQualityPlatforms2022,
  title = {Data Quality of Platforms and Panels for Online Behavioral Research},
  author = {Peer, Eyal and Rothschild, David and Gordon, Andrew and Evernden, Zak and Damer, Ekaterina},
  year = {2022},
  month = aug,
  journal = {Behavior Research Methods},
  volume = {54},
  number = {4},
  pages = {1643--1662},
  issn = {1554-3528},
  doi = {10.3758/s13428-021-01694-3},
  url = {10.3758/s13428-021-01694-3},
  urldate = {2025-03-16},
  abstract = {We examine key aspects of data quality for online behavioral research between selected platforms (Amazon Mechanical Turk, CloudResearch, and Prolific) and panels (Qualtrics and Dynata). To identify the key aspects of data quality, we first engaged with the behavioral research community to discover which aspects are most critical to researchers and found that these include attention, comprehension, honesty, and reliability. We then explored differences in these data quality aspects in two studies (N\,{\textasciitilde}\,4000), with or without data quality filters (approval ratings). We found considerable differences between the sites, especially in comprehension, attention, and dishonesty. In Study 1 (without filters), we found that only Prolific provided high data quality on all measures. In Study 2 (with filters), we found high data quality among CloudResearch and Prolific. MTurk showed alarmingly low data quality even with data quality filters. We also found that while reputation (approval rating) did not predict data quality, frequency and purpose of usage did, especially on MTurk: the lowest data quality came from MTurk participants who report using the site as their main source of income but spend few hours on it per week. We provide a framework for future investigation into the ever-changing nature of data quality in online research, and how the evolving set of platforms and panels performs on these key aspects.},
  langid = {english},
  keywords = {Amazon mechanical turk,Attention,Comprehension,Data quality,Honesty,Online research,Prolific,Reliability}
}

@article{kochariConductingWebBasedExperiments2019,
  title = {Conducting {{Web-Based Experiments}} for {{Numerical Cognition Research}}},
  author = {Kochari, Arnold R.},
  year = {2019},
  month = sep,
  journal = {Journal of Cognition},
  volume = {2},
  number = {1},
  pages = {39},
  issn = {2514-4820},
  doi = {10.5334/joc.85},
  url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6753310/},
  urldate = {2025-03-16},
  abstract = {It is becoming increasingly popular and straightforward to collect data in cognitive psychology through web-based studies. In this paper, I review issues around web-based data collection for the purpose of numerical cognition research. Provided that the desired type of data can be collected through a web-browser, such online studies offer numerous advantages over traditional forms of physical lab-based data collection, such as gathering data from larger sample sizes in shorter time-windows and easier access to non-local populations. I then present results of two replication studies that employ classical paradigms in numerical cognition research: the number-size congruity paradigm and comparison to a given standard, which also included a masked priming manipulation. In both replications, reaction times and error rates were comparable to original, physical lab-based studies. Consistent with the results of original studies, a distance effect, a congruity effect, and a priming effect were observed. Data collected online thus offers a level of reliability comparable to data collected in a physical lab when it comes to questions in numerical cognition.},
  pmcid = {PMC6753310},
  pmid = {31576378},

}

@book{easterlingFundamentalsStatisticalExperimental2015,
  title = {Fundamentals of {{Statistical Experimental Design}} and {{Analysis}}},
  author = {Easterling, Robert G.},
  year = {2015},
  month = oct,
  publisher = {John Wiley \& Sons},
  abstract = {Professionals in all areas -- business; government; the physical, life, and social sciences; engineering; medicine, etc. -- benefit from using statistical experimental design to better understand their worlds and then use that understanding to improve the products, processes, and programs they are responsible for. This book aims to provide the practitioners of tomorrow with a memorable, easy to read, engaging guide to statistics and experimental design.  This book uses examples, drawn from a variety of established texts, and embeds them in a business or scientific context, seasoned with a dash of humor, to emphasize the issues and ideas that led to the experiment and the what-do-we-do-next? steps after the experiment. Graphical data displays are emphasized as means of discovery and communication and formulas are minimized, with a focus on interpreting the results that software produce. The role of subject-matter knowledge, and passion, is also illustrated. The examples do not require specialized knowledge, and the lessons they contain are transferrable to other contexts.   Fundamentals of Statistical Experimental Design and Analysis introduces the basic elements of an experimental design, and the basic concepts underlying statistical analyses. Subsequent chapters address the following families of experimental designs:    Completely Randomized designs, with single or multiple treatment factors, quantitative or qualitative Randomized Block designs Latin Square designs Split-Unit designs Repeated Measures designs Robust designs Optimal designs   Written in an accessible, student-friendly style, this book is suitable for a general audience and particularly for those professionals seeking to improve and apply their understanding of experimental design.},
  isbn = {978-1-118-95465-2},
  langid = {english},
  keywords = {Mathematics / General,Mathematics / Probability & Statistics / General,Mathematics / Probability & Statistics / Stochastic Processes}
}

@article{muszynskiAttentionChecksHow2023,
  ids = {muszynskiAttentionChecksHow2023a},
  title = {Attention Checks and How to Use Them: {{Review}} and Practical Recommendations},
  shorttitle = {Attention Checks and How to Use Them},
  author = {Muszy{\'n}ski, Marek},
  year = {2023},
  journal = {Ask: Research and Methods},
  volume = {32},
  number = {1},
  pages = {3--38},
  issn = {12349224, 25440799},
  doi = {10.18061/ask.v32i1.0001},
  url = {https://kb.osu.edu/handle/1811/103631},
  urldate = {2025-03-16},
  abstract = {Web surveys dominate contemporary data collection in numerous disciplines within the broadly understood social sciences. However, this mode of data collection comes with additional challenges, particularly related to careless or insufficient effort responding (C/IER), which can distort study results and poses a direct threat to the validity. One of the recommended approaches to address this problem is using attention checks, which are additional tasks or items with objective answers that indicate attentive responding. Despite the potential benefits of attention checks, recent evidence suggests that they are still not sufficiently researched to justify their uncritical use in screening out inattentive participants. This article provides an abridged review of the attention checks literature, offers evidence-based practical recommendations, and highlights crucial gaps in research regarding attention checks. Evidence-based recommendations concerning the type, number, and placement of attention checks in a survey are presented. Generally, including more than one attention check in a survey is advisable, especially for longer surveys. Long instructed manipulation checks should be avoided, instead, covert attention checks, which are difficult for participants to identify, are recommended to reduce negative side effects such as noncompliance. In addition to attention checks, other criteria, such as item-level response time analysis, should be used in combination to identify inattentive participants. It is crucial to carefully analyse all data before making decisions about participant elimination. Ethical considerations related to the use of attention checks are also discussed, recognizing the importance of maintaining participant trust and understanding the potential impact on survey completion rates and data quality. Overall, attention checks hold certain promise as a tool to enhance data quality, but further research and a thoughtful implementation are necessary to maximise their effectiveness.},
  langid = {english},

}

@article{albertComparingAttentionalDisengagement2023,
  title = {Comparing Attentional Disengagement between {{Prolific}} and {{MTurk}} Samples},
  author = {Albert, Derek A. and Smilek, Daniel},
  year = {2023},
  month = nov,
  journal = {Scientific Reports},
  volume = {13},
  number = {1},
  pages = {20574},
  publisher = {Nature Publishing Group},
  issn = {2045-2322},
  doi = {10.1038/s41598-023-46048-5},
  url = {https://www.nature.com/articles/s41598-023-46048-5},
  urldate = {2025-03-16},
  abstract = {Attention often disengages from primary tasks in favor of secondary tasks (i.e., multitasking) and task-unrelated thoughts (i.e., mind wandering). We assessed whether attentional disengagement, in the context of a cognitive task, can substantially differ between samples from commonly used online participant recruitment platforms, Prolific and Mechanical Turk (MTurk). Initially, eighty participants were recruited through Prolific to perform an attention task in which the risk of losing points for errors was varied (high risk\,=\,80\% chance of loss, low risk\,=\,20\% chance of loss). Attentional disengagement was measured via task performance along with self-reported mind wandering and multitasking. On Prolific, we observed surprisingly low levels of disengagement. We then conducted the same experiment on MTurk. Strikingly, MTurk participants exhibited more disengagement than Prolific participants. There was also an interaction between risk and platform, with the high-risk group exhibiting less disengagement, in terms of better task performance, than the low-risk group, but only on MTurk. Platform differences in individual traits related to disengagement and relations among study variables were also observed. Platform differences persisted, but were smaller, after increasing MTurk reputation criteria and remuneration in a second experiment. Therefore, recruitment platform and recruitment criteria could impact results related to attentional disengagement.},
  copyright = {2023 The Author(s)},
  langid = {english},
  keywords = {Human behaviour,Psychology},

}

@article{clevelandGraphicalPerceptionTheory1984,
  ids = {cleveland1984a},
  title = {Graphical Perception: {{Theory}}, Experimentation, and Application to the Development of Graphical Methods},
  author = {Cleveland, William S. and McGill, Robert},
  year = {1984},
  month = sep,
  journal = {Journal of the American Statistical Association},
  volume = {79},
  number = {387},
  pages = {531--554},
  doi = {10.1080/01621459.1984.10478080},
  url = {http://dx.doi.org/10.1080/01621459.1984.10478080},
  langid = {english},
  keywords = {perception},

}

@article{clevelandGraphicalPerceptionGraphical1985,
	title = {Graphical {Perception} and {Graphical} {Methods} for {Analyzing} {Scientific} {Data}},
	volume = {229},
	issn = {0036-8075, 1095-9203},
	doi = {10.1126/science.229.4716.828},
	language = {en},
	number = {4716},
	urldate = {2018-08-14},
	journal = {Science},
	author = {Cleveland, W. S. and McGill, R.},
	month = aug,
	year = {1985},
	pages = {828--833},
}

@Manual{R,
  title = {R: A Language and Environment for Statistical Computing},
  author = {{R Core Team}},
  organization = {R Foundation for Statistical Computing},
  address = {Vienna, Austria},
  year = {2022},
  url = {https://www.R-project.org/},
}

@Book{ggplot2,
    author = {Hadley Wickham},
    title = {ggplot2: Elegant Graphics for Data Analysis},
    publisher = {Springer-Verlag New York},
    year = {2016},
    isbn = {978-3-319-24277-4},
    url = {https://ggplot2.tidyverse.org},
}

@Manual{shiny,
  title = {shiny: Web Application Framework for R},
  author = {Winston Chang and Joe Cheng and JJ Allaire and Carson Sievert and Barret Schloerke and Yihui Xie and Jeff Allen and Jonathan McPherson and Alan Dipert and Barbara Borges},
  year = {2021},
  note = {R package version 1.7.1},
  url = {https://CRAN.R-project.org/package=shiny},
}

@article{d3,
	title = {D3 {Data}-{Driven} {Documents}},
	volume = {17},
	issn = {1077-2626},
	doi = {10/b7bhhf},
	number = {12},
	journal = {IEEE Transactions on Visualization and Computer Graphics},
	author = {Bostock, M. and Ogievetsky, V. and Heer, J.},
	month = dec,
	year = {2011},
	pages = {2301--2309},
}

@article{bujaStatisticalInferenceExploratory2009,
	title = {Statistical inference for exploratory data analysis and model diagnostics},
	volume = {367},
	number = {1906},
	journal = {Philosophical Transactions of the Royal Society of London A: Mathematical, Physical and Engineering Sciences},
	author = {Buja, Andreas and Cook, Dianne and Hofmann, Heike and Lawrence, Michael and Lee, Eun-Kyung and Swayne, Deborah F and Wickham, Hadley},
	year = {2009},
	pages = {4361--4383},},
}

@article{majumderValidationVisualStatistical2013,
	title = {Validation of visual statistical inference, applied to linear models},
	volume = {108},
	doi = {10/f5gntt},
	number = {503},
	journal = {Journal of the American Statistical Association},
	author = {Majumder, Mahbubul and Hofmann, Heike and Cook, Dianne},
	year = {2013},
	pages = {942--956},
}

@article{wickhamGraphicalInferenceInfovis2010,
	title = {Graphical inference for infovis},
	volume = {16},
	doi = {10.1109/TVCG.2010.161},
	number = {6},
	journal = {IEEE Transactions on Visualization and Computer Graphics},
	author = {Wickham, Hadley and Cook, Dianne and Hofmann, Heike and Buja, Andreas},
	year = {2010},
	pages = {973--979},
}

@article{vanderplasTestingStatisticalCharts2020,
	title = {Testing {Statistical} {Charts}: {What} {Makes} a {Good} {Graph}?},
	volume = {7},
	copyright = {All rights reserved},
	issn = {2326-8298, 2326-831X},
	shorttitle = {Testing {Statistical} {Charts}},
	language = {en},
	number = {1},
	doi = {10.1146/annurev-statistics-031219-041252},
	urldate = {2020-02-10},
	journal = {Annual Review of Statistics and Its Application},
	author = {Vanderplas, Susan and Cook, Dianne and Hofmann, Heike},
	month = mar,
	year = {2020}
}

@article{vanderplasStatisticalSignificanceCalculations2021,
	title = {Statistical significance calculations for scenarios in visual inference},
	volume = {10},
	issn = {2049-1573},
	doi = {10.1002/sta4.337},
	language = {en},
	number = {1},
	urldate = {2022-06-25},
	journal = {Stat},
	author = {Vanderplas, Susan and R{\"o}ttger, Christian and Cook, Dianne and Hofmann, Heike},
	year = {2021},
}

@article{dunbar1995scientists,
	title = {How scientists really reason: {Scientific} reasoning in real-world laboratories},
	volume = {18},
	journal = {The nature of insight},
	author = {Dunbar, Kevin},
	year = {1995},
	pages = {365--395}
}

@article{traftonTurningPicturesNumbers2000,
	title = {Turning pictures into numbers: extracting and generating information from complex visualizations},
	volume = {53},
	issn = {10715819},
	shorttitle = {Turning pictures into numbers},
	url = {10.1006/ijhc.2000.0419},
	language = {en},
	number = {5},
	urldate = {2019-03-18},
	journal = {International Journal of Human-Computer Studies},
	author = {Trafton, Gregory J. and Kirschenbaum, Susan S. and Tsui, Ted L. and Miyamoto, Robert T. and Ballas, James A. and Raymond, Paula D.},
	month = nov,
	year = {2000},
	pages = {827--850}
}

@inproceedings{kirschenbaum2003comparative,
	title = {Comparative {Cognitive} {Task} {Analysis}: {The} {Cognition} of {Weather} {Forecasting}},
	volume = {47},
	booktitle = {Proceedings of the {Human} {Factors} and {Ergonomics} {Society} {Annual} {Meeting}},
	author = {Kirschenbaum, Susan S},
	year = {2003},
	pages = {473--477},
	doi = {10.1177/154193120304700347}
}

@article{katzYouDrawIt2017,
	chapter = {The Upshot},
	title = {You {Draw} {It}: {Just} {How} {Bad} {Is} the {Drug} {Overdose} {Epidemic}?},
	issn = {0362-4331},
	shorttitle = {You {Draw} {It}},
	url = {https://www.nytimes.com/interactive/2017/04/14/upshot/drug-overdose-epidemic-you-draw-it.html},
	abstract = {An interactive quiz provides deeper context to the opioid epidemic by asking readers to draw the trends in deaths from guns, the H.I.V. epidemic, car accidents and drug overdoses.},
	language = {en-US},
	urldate = {2022-06-25},
	journal = {The New York Times},
	author = {Katz, Josh},
	month = apr,
	year = {2017},
}

@article{robinson2023you,
  title={'You Draw It': Implementation of visually fitted trends with r2d3},
  author={Robinson, Emily A and Howard, Reka and VanderPlas, Susan},
  journal={Journal of Data Science},
  volume={21},
  number={2},
  pages={281--294},
  year={2023},
  publisher={School of Statistics, Renmin University of China}
}

@article{robinson2023eye,
  title={Eye Fitting Straight Lines in the Modern Era},
  author={Robinson, Emily A and Howard, Reka and VanderPlas, Susan},
  journal={Journal of Computational and Graphical Statistics},
  volume={32},
  number={4},
  pages={1537--1544},
  year={2023},
  publisher={Taylor \& Francis}
}

@misc{niladriroychowdhurySeeValueApp2020,
	title = {The {See} {Value} {App}: {Visual} {Decision} {Making} for {Drug} {Development}},
	shorttitle = {The {See} {Value} {App}},
	howpublished = {https://rinpharma.com/publication/rinpharma\_183/},
	abstract = {Statistical graphics play an important role in exploratory data analysis, model checking and diagnostics. The lineup protocol (Buja et. al 2009) enables statistical significance testing using visualizations, bridging the gap between exploratory and inferential statistics. We created an R-shiny App that facilitates the user to generate these lineups by using preloaded examples or by uploading their own data. The user can then act as a human judge to select the plot which he/she think has the real data and see if a correct choice is made. If a correct choice is made, it would be enough evidence to believe that the real plot is significantly different from the "null" plots. The app also calculates the "see"-value based on the selections made by multiple independent users which can be used to decide statistical significance. The app supports different types of analysis using continuous, binary or time-to-event response and continuous or categorical predictors.},
	language = {en-us},
	urldate = {2022-06-25},
	author = {Chowdhury, Niladri Roy and Diehl, Hannah and Broderick, Tamara and Stein, Andy},
	month = oct,
	year = {2020},
}

@article{hullmanDesigningInteractiveExploratory2021,
	title = {Designing for {Interactive} {Exploratory} {Data} {Analysis} {Requires} {Theories} of {Graphical} {Inference}},
	volume = {3},
	doi = {10.1162/99608f92.3ab8a587},
	language = {en},
	number = {3},
	urldate = {2022-06-25},
	journal = {Harvard Data Science Review},
	author = {Hullman, Jessica and Gelman, Andrew},
	month = jul,
	year = {2021},
}

@article{cookFoundationAvailableThinking2021,
	title = {The {Foundation} {Is} {Available} for {Thinking} {About} {Data} {Visualization} {Inferentially}},
	volume = {3},
	doi = {10.1162/99608f92.8453435d},
	language = {en},
	number = {3},
	urldate = {2022-06-25},
	journal = {Harvard Data Science Review},
	author = {Cook, Dianne and Reid, Nancy and Tanaka, Emi},
	month = jul,
	year = {2021},
}

@article{vanderplasDesigningGraphicsRequires2021,
	title = {Designing {Graphics} {Requires} {Useful} {Experimental} {Testing} {Frameworks} and {Graphics} {Derived} {From} {Empirical} {Results}},
	volume = {3},
	doi = {10.1162/99608f92.7d099fd0},
	language = {en},
	number = {3},
	urldate = {2022-06-25},
	journal = {Harvard Data Science Review},
	author = {Vanderplas, Susan},
	month = jul,
	year = {2021},
}

@article{vanderplasFramedReproducingRevisiting2019,
	title = {Framed! {Reproducing} and {Revisiting} 150 year old charts},
	copyright = {All rights reserved},
	issn = {1537-2715},
	doi = {10.1080/10618600.2018.1562937},
	journal = {Journal of Computational and Graphical Statistics},
	author = {Vanderplas, Susan and Goluch, Ryan and Hofmann, Heike},
	year = {2019},
}

@article{vanderplasSpatialReasoningData2016a,
	title = {Spatial {Reasoning} and {Data} {Displays}},
	volume = {22},
	issn = {1077-2626},
	doi = {10.1109/TVCG.2015.2469125},
	number = {1},
	urldate = {2022-06-26},
	journal = {IEEE Transactions on Visualization and Computer Graphics},
	author = {Vanderplas, Susan and Hofmann, Heike},
	month = jan,
	year = {2016},
	pages = {459--468},
}

@article{majumderHumanFactorsInfluencing2014,
	title = {Human {Factors} {Influencing} {Visual} {Statistical} {Inference}},
	url = {http://arxiv.org/abs/1408.1974},
	language = {en},
	urldate = {2019-07-26},
	journal = {arXiv:1408.1974 [stat]},
	author = {Majumder, Mahbubul and Hofmann, Heike and Cook, Dianne},
	month = aug,
	year = {2014}
}

@article{ushakovStatisticalAnalysisRounded2017,
	title = {Statistical analysis of rounded data: {Recovering} of information lost due to rounding},
	volume = {46},
	issn = {2005-2863},
	shorttitle = {Statistical analysis of rounded data},
	doi = {10.1016/j.jkss.2017.01.003},
	language = {en},
	number = {3},
	urldate = {2022-06-27},
	journal = {Journal of the Korean Statistical Society},
	author = {Ushakov, N. G. and Ushakov, V. G.},
	month = sep,
	year = {2017},
	pages = {426--437},
}

@article{heitjanIgnorabilityCoarseData1991,
	title = {Ignorability and {Coarse} {Data}},
	volume = {19},
	issn = {0090-5364, 2168-8966},
	doi = {10.1214/aos/1176348396},
	number = {4},
	urldate = {2022-06-27},
	journal = {The Annals of Statistics},
	author = {Heitjan, Daniel F. and Rubin, Donald B.},
	month = dec,
	year = {1991},
	pages = {2244--2253}
}

@book{tourangeau_rips_rasinski_2000,
	address = {Cambridge},
	title = {The psychology of survey response},
	publisher = {Cambridge University Press},
	author = {Tourangeau, Roger and Rips, Lance J. and Rasinski, Kenneth},
	year = {2000},
	doi = {10.1017/CBO9780511819322},
}

@article{wood1968objectives,
  title={Objectives in the teaching of mathematics},
  author={Wood, R.},
  journal={Educational Research},
  volume={10},
  number={2},
  pages={83--98},
  year={1968},
  publisher={Taylor \& Francis}
}

@article{curcio1987comprehension,
  title={Comprehension of mathematical relationships expressed in graphs},
  author={Curcio, Frances},
  journal={Journal for research in mathematics education},
  volume={18},
  number={5},
  pages={382--393},
  year={1987},
  publisher={National Council of Teachers of Mathematics}
}

@article{friel2001making,
  title={Making sense of graphs: Critical factors influencing comprehension and instructional implications},
  author={Friel, Susan and Curcio, Frances and Bright, George},
  journal={Journal for Research in mathematics Education},
  volume={32},
  number={2},
  pages={124--158},
  year={2001},
  publisher={National Council of Teachers of Mathematics}
}

@article{glazer2011challenges,
  title={Challenges with graph interpretation: A review of the literature},
  author={Glazer, Nirit},
  journal={Studies in science education},
  volume={47},
  number={2},
  pages={183--210},
  year={2011},
  publisher={Taylor \& Francis}
}

@article{loyDiagnosticToolsHierarchical2013,
	title = {Diagnostic tools for hierarchical linear models},
	volume = {5},
	issn = {1939-0068},
	doi = {10.1002/wics.1238},
	pages = {48--61},
	number = {1},
	journal = {Wiley Interdisciplinary Reviews: Computational Statistics},
	author = {Loy, Adam and Hofmann, Heike},
	urldate = {2019-05-10},
	year = {2013},
	langid = {english},
}

@article{wickhamGgplot22011,
	title = {ggplot2},
	volume = {3},
	issn = {1939-0068},
	doi = {10.1002/wics.147},
	abstract = {This article discusses ggplot2, an open source R package, based on a grammatical theory of graphics. The underlying theory has been discussed in depth elsewhere so this article illustrates some of the consequences of the theory for creating new graphics, the importance of programmable graphics, and the rich ecosystem that has grown up around ggplot2. {WIREs} Comp Stat 2011 3 180--185 {DOI}: 10.1002/wics.147 This article is categorized under: Software for Computational Statistics {\textgreater} Software/Statistical Software Statistical and Graphical Methods of Data Analysis {\textgreater} Statistical Graphics and Visualization},
	pages = {180--185},
	number = {2},
	journal = {{WIRE} Computational Statistics},
	author = {Wickham, Hadley},
	urldate = {2024-09-09},
	date = {2011},
	langid = {english},
}

@article{thinkaloud,
	title = {Retrospective vs. concurrent think-aloud protocols: Testing the usability of an online library catalogue},
	volume = {22},
	doi = {10.1080/0044929031000},
	pages = {339--351},
	journal = {Behaviour \& {Information Technology}},
	author = {Haak, Maaike and De Jong, Menno and Schellens, Peter},
	date = {2003-09},
	year = 2003,
}