| Title |
On the importance of avoiding shortcuts in applying cognitive models to hierarchical data
|
|---|---|
| Published in |
Behavior Research Methods, June 2018
|
| DOI | 10.3758/s13428-018-1054-3 |
| Pubmed ID | |
| Authors |
Udo Boehm, Maarten Marsman, Dora Matzke, Eric-Jan Wagenmakers |
| Abstract |
Psychological experiments often yield data that are hierarchically structured. A number of popular shortcut strategies in cognitive modeling do not properly accommodate this structure and can result in biased conclusions. To gauge the severity of these biases, we conducted a simulation study for a two-group experiment. We first considered a modeling strategy that ignores the hierarchical data structure. In line with theoretical results, our simulations showed that Bayesian and frequentist methods that rely on this strategy are biased towards the null hypothesis. Secondly, we considered a modeling strategy that takes a two-step approach by first obtaining participant-level estimates from a hierarchical cognitive model and subsequently using these estimates in a follow-up statistical test. Methods that rely on this strategy are biased towards the alternative hypothesis. Only hierarchical models of the multilevel data lead to correct conclusions. Our results are particularly relevant for the use of hierarchical Bayesian parameter estimates in cognitive modeling. |
X Demographics
The data shown below were collected from the profiles of 5 X users who shared this research output. Click here to find out more about how the information was compiled.
Geographical breakdown
| Country | Count | As % |
|---|---|---|
| United States | 1 | 20% |
| United Kingdom | 1 | 20% |
| Unknown | 3 | 60% |
Demographic breakdown
| Type | Count | As % |
|---|---|---|
| Scientists | 3 | 60% |
| Members of the public | 1 | 20% |
| Science communicators (journalists, bloggers, editors) | 1 | 20% |
Mendeley readers
The data shown below were compiled from readership statistics for 82 Mendeley readers of this research output. Click here to see the associated Mendeley record.
Geographical breakdown
| Country | Count | As % |
|---|---|---|
| Unknown | 82 | 100% |
Demographic breakdown
| Readers by professional status | Count | As % |
|---|---|---|
| Student > Ph. D. Student | 22 | 27% |
| Researcher | 14 | 17% |
| Student > Master | 13 | 16% |
| Student > Bachelor | 6 | 7% |
| Student > Doctoral Student | 4 | 5% |
| Other | 10 | 12% |
| Unknown | 13 | 16% |
| Readers by discipline | Count | As % |
|---|---|---|
| Psychology | 35 | 43% |
| Neuroscience | 11 | 13% |
| Engineering | 3 | 4% |
| Medicine and Dentistry | 3 | 4% |
| Computer Science | 1 | 1% |
| Other | 5 | 6% |
| Unknown | 24 | 29% |
Attention Score in Context
This research output has an Altmetric Attention Score of 3. This is our high-level measure of the quality and quantity of online attention that it has received. This Attention Score, as well as the ranking and number of research outputs shown below, was calculated when the research output was last mentioned on 28 September 2020.
All research outputs
#15,094,398
of 25,653,515 outputs
Outputs from Behavior Research Methods
#1,329
of 2,564 outputs
Outputs of similar age
#177,059
of 342,339 outputs
Outputs of similar age from Behavior Research Methods
#28
of 38 outputs
Altmetric has tracked 25,653,515 research outputs across all sources so far. This one is in the 40th percentile – i.e., 40% of other outputs scored the same or lower than it.
So far Altmetric has tracked 2,564 research outputs from this source. They typically receive more attention than average, with a mean Attention Score of 8.0. This one is in the 47th percentile – i.e., 47% of its peers scored the same or lower than it.
Older research outputs will score higher simply because they've had more time to accumulate mentions. To account for age we can compare this Altmetric Attention Score to the 342,339 tracked outputs that were published within six weeks on either side of this one in any source. This one is in the 47th percentile – i.e., 47% of its contemporaries scored the same or lower than it.
We're also able to compare this research output to 38 others from the same source and published within six weeks on either side of this one. This one is in the 26th percentile – i.e., 26% of its contemporaries scored the same or lower than it.