EJ
About
- Username
- EJ
- Joined
- Visits
- 2,530
- Last Active
- Roles
- Member, Administrator, Moderator
Comments
-
You can't find it online?! EJ.Wagenmakers@gmail.com
-
The DV in logistic regression is usually a binary variable, right? JASP offers several resisual plots.
-
Hi BJ89, You say "I have been told by a supervisor that BMA is never an appropriate method to use because it is 'step-wise'" I am not sure what you mean here, because BMA is a single step method where all models are fit to the data simulta…
-
Hi Dimitri, Without knowing the details for this analysis, it is generally true that adding more components *always impoves the model's best-fit*. For instance, adding predictors in a regression can only increase the proportion of variance explaine…
-
No worries! If you still want me to take a look you could send the data to my personal email address (but don't feel pressured) E.J.
-
Dear Alejandro, That sounds like a great suggestion. Could you add it as a feature request to our GitHub page please? (for details see https://jasp-stats.org/2018/03/29/request-feature-report-bug-jasp/) Cheers, E.J.
-
OK. So first I confirm that in BayesFactor yields BF01 = 3.3 (approximately) #R code: library(BayesFactor) proportionBF(52,173,1/3) Second, the default Bayesian test in JASP gives BF01 = 7.5 (approximately). See screenshot. https://forum.cogsci.nl/u…
-
I'll look into it a bit more. E.J.
-
Hi BJ89, We discuss the impact of model priors on inclusion BFs here: https://journals.sagepub.com/doi/full/10.1177/25152459211031256#appendix I agree it is counterintuitive. If you send me the data I can have a look E.J.
-
Hi Lewend, Well, these are different models. JASP uses the test proposed by Jeffreys -- under H1, theta gets a uniform prior from 0 to 1. You can change that distribution by adjusting the a and b parameters of the beta distribution. In BayesFactor, …
-
Hi Mathieu Yes, we now have a graph editor that allows the axes to be adjusted. It does not work for all plots, but it works for most. E.J.
-
Ah I see. Was this a GitHub request already? E.J.
-
In the current 0.16.4 the test reports "Statistic" (I presume this is the H-statistic, and if so I'll have it renamed). This is what is needed? E.J.
-
Hi BJ89, What is plausible or implausible wrt priors depends very much on the application at hand. I experienced this glitch myself, but for me it was an OS overload -- too many other processes were hogging resources, and so the system could not ad…
-
Hi BJ89, If you want to use an informative prior you can check out the papers on my website on prior elicitation, and the paper by Gronau et al. (https://www.tandfonline.com/doi/full/10.1080/00031305.2018.1562983). Should you specify an informed pri…
-
In many JASP analyses you can set the seed in the analysis-specific GUI (usually under "Advanced options")
-
Hi Mark, I am not sure either. I think it is important first to identify the desired statistical approach. Also, it seems to me that expression of negative emotion by the robots prompts people to show higher comfort levels? But I am not sure why the…
-
Hi Erin, Some form of exploratory data analysis seems appropriate...maybe start by plotting the correlation matrix (plus scatterplots) and some regression analyses? Of course it is always better to go in armed with theory and some expectations... Ch…
-
I am surprised that we don't test normality of residuals -- I'll check. Most of the other suggestions refer to time series analysis. We have a time series module under development and I'll pass on your suggestions! E.J.
-
JASP implements lavaan syntax, so I think that your best course of action is to examine how the lavaan code would look (which is more of a question for a lavaan forum...) E.J.
-
(a) No, but this is a popular misconception. We address it in this paper: https://psyarxiv.com/rqnu5 (b) In principle, even when you do estimation you can still take into account the fact that H0 is in play (see for instance https://journals.sagepub…
-
Dear Lewend, Can you give the specific numbers for the test? And your H0 is p = 1/3, right? Cheers, E.J.
-
JASP does not yet do propensity score matching; it would make for a good feature request on our GitHub page! (for details see https://jasp-stats.org/2018/03/29/request-feature-report-bug-jasp/) Cheers, E.J.
-
(a) the median and 95% CI indicate the strength of the effect, assuming H1 is the best model. (b) they summarize the posterior distribution (i.e., the Bayesian estimate) for standardized effect size, which is mu/sigma (i.e., the population version …
-
I'll ask the experts... E.J.
-
You'd have to add that prior model probability yourself. We have it implemented under our ANOVA posthoc tests, but that is a specific scenario that does not apply exactly here. Once you have the prior model probability p, you transform that to a pri…
-
I'll check to see whether there has been any update on this... E.J.
-
I guess we should provide a more informative error message. I suspect that one of your factors is really a variable with many "levels", can that be the case? E.J.
-
Hi Carolien, I've gone back and forth on the BIC as well. My current thinking is that *is* reasonable as a point of reference, and especially appropriate for default analyses that do not commit to a strong prior position. For instance, I assume that…
-
Hi Chris, I think you are spot-on! It is easy to specify the data that will yield the maximum evidence for H0 (t=0, n/s = 1/2, etc.) One would still need to specify an alternative, but the default choices would be fine here, because they tend to be …