Using confidence intervals for graphically based data interpretation.

By M. Masson. Canadian journal of experimental psychology = Revue canadienne de psychologie experimentale, 2003

805 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Developmental and Educational Psychology, Food Science

View Paper: https://www.semanticscholar.org/paper/52e0235e4f99eae43b3b360535cb7d7679250d27

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Developmental and Educational Psychology

In Food Science

Citations in the corpus

Language‐dependent memory in bilingual learning (2006, methodology): “Broken lines represent a 95% confidence interval, computed following the Masson and Loftus (2003) method for repeatedmeasures comparisons”
A content-addressable pointer mechanism underlies comprehension of verb-phrase ellipsis (2008, methodology): “we report 95% confidence intervals calculated using the interaction error term from the ANOVA ( Masson & Loftus, 2003 ).”
Bayesian t tests for accepting and rejecting the null hypothesis (2009, background): “Masson and Loftus (2003) , and Kline (2004), among many others, have recommended using CIs for inference.”
Relationships between value orientations, self-determined motivational types and pro-environmental behavioural intentions (2010, methodology): “We consider the squared multiple correlation-values of regression models to be significantly different when the confidence intervals around the R2 of these regression models overlap no more than half of the distance of one side on a confidence interval (see Masson & Loftus, 2003).”
The representation of lexical and syntactic information in bilinguals: Evidence from syntactic priming (2007, neutral): “Note that the prepositional-object and doubleobject combinatorial nodes correspond to Pickering and Branigan’s (1998) NP,PP and NP,NP nodes, respectively.”
Bayesian alternatives to null-hypothesis significance testing for repeated-measures designs (2016, background): “There is a growing literature on computing confidence intervals for designs that include repeated-measures factors that provides good support for this enterprise (e.g., Franz & Loftus, 2012; Hollands & Jarmasz, 2010; Loftus & Masson, 1994 and Masson & Loftus, 2003).”
On the use of verb-based implicit causality in sentence comprehension : Evidence from self-paced reading and eye tracking (2006, background): “Mean reading times (in ms) for the consistent and inconsistent condition in Experiment 1 (error bars indicate one side of a 95% confidence interval based on the MSE-value; see Masson and Loftus, 2003). A.W. Koornneef, J.J.A. Van Berkum / Journal of Memory and Language 54 (2006) 445–465 451”
State-Denoised Recurrent Neural Networks (2018, methodology): “Error bars indicate ±1 SEM, based on a correction for confidence intervals with matched comparisons [Masson and Loftus, 2003]”
Neural language models as psycholinguistic subjects: Representations of syntactic state (2019, methodology): “In this and all other figures, unless otherwise noted, error bars represent 95% confidence intervals of the contrasts between conditions shown, computed from the standard error of the by-item and by-condition mean surprisals after subtracting out the by-item means (Masson and Loftus, 2003).”
Automatic activation of orthography in spoken word recognition: Pseudohomograph priming (2008, methodology): “This approach differs from procedures that use only an estimated square error to calculate confidence intervals (e.g., Masson & Loftus, 2003).”
RNNs as psycholinguistic subjects: Syntactic state and grammatical dependency (2018, methodology): “In this and all other figures, unless otherwise noted, error bars represent 95% confidence intervals of the contrasts between conditions, computed from the standard error of the by-item and by-condition mean surprisals after subtracting out the by-item means (Masson and Loftus, 2003).”
The status of subject-object reanalyses in the language comprehension architecture (2008, methodology): “For all significant effects, we report 95% confidence intervals (CI) for the differences between condition means computed using the mean square error terms from the analysis by participants (Loftus & Masson, 1994; Masson & Loftus, 2003).”
Abstract sentence representations in 3-year-olds: Evidence from language production and comprehension (2008, methodology): “For differences between means, we report the 95% confidence intervals (CIs) taking the mean squared errors from the participants analyses (Masson & Loftus, 2003).”
Morphology, agreement and working memory retrieval in sentence production : Evidence from gender and case in Slovak (2007, methodology): “For direct means compari - sons we also report 95% confidence intervals ( CIs ) around differences between means computed on by - sub - ject proportion means ( Masson & Loftus , 2003 ) .”
General Antecedents of Personal Norms, Policy Acceptability, and Intentions: The Role of Values, Worldviews, and Environmental Concern (2011, methodology): “We consider the R 2 values of regression models to be significantly different when the confidence intervals around the squared multiple correlation of these regression models overlap no more than half of the distance of one side on a confidence interval (see Masson and Loftus 2003 ).”