patc3

@TarandeepKang your explanation was very useful

in Error Comment by patc3 September 26

This is likely due to having a dependent variable with a very large scale (e.g. salary in dollar amounts, or something even bigger). You could try to go in preferences and uncheck this box: https://forum.cogsci.nl/uploads/575/U9UJICY4DDRJ.png

in Error Comment by patc3 September 26

See GitHub issue here: https://github.com/jasp-stats/jasp-issues/issues/2926

in Diagnostics in Multinomial Logistic Regression Comment by patc3 September 23

Thanks I remember now. I used to know how to get to multinomial regression, but it's so weirdly located that I couldn't find it anymore. Welp you're definitely right the UI is completely unresponsible to changes in the diagnostics section. It might …

in Diagnostics in Multinomial Logistic Regression Comment by patc3 September 23

I thought JASP didn't have multinomial logistic regression? Am I misremembering?

in Diagnostics in Multinomial Logistic Regression Comment by patc3 September 23

After you've followed EJ's suggestions, if you need to, you can revert back to a previous JASP version until a fix is deployed: https://jasp-stats.org/previous-versions/

in JASP freezes when trying to open files Comment by patc3 September 20

Nice! readxl::read_excel() works extremely well

in JASP and Excel files Comment by patc3 September 19

Where can we access the data? I wanna see for myself.. Or perhaps you can show your JASP input? To rule out user error (as I don't think the book got it wrong, and I would find it unfortunate if JASP was wrong)

in Help with a textbook analysis Comment by patc3 September 6

What if you change model test in the SEM analysis (see the second screenshot)? Also what if you pick mimic/emulate Mplus?

in Robust ML for CFA or SEM Comment by patc3 August 29

That said, there's probably a couple of ways to get the t test: 1) create a new variable with two values and missing if not in either of the two conditions of interest 2) do an ANOVA with post hoc pairwise comparisons, though you might be forced to …

in How to select subgroups for a t-test procedure in a variable with more than two groups? Comment by patc3 August 29

Hmmm interesting... This looks like a bug to me

in How to select subgroups for a t-test procedure in a variable with more than two groups? Comment by patc3 August 29

CFA: https://forum.cogsci.nl/uploads/463/CITETK1B9CRF.png SEM: https://forum.cogsci.nl/uploads/925/READPHIC8Y8C.png

in Robust ML for CFA or SEM Comment by patc3 August 28

Sorry no I don't know. What I do in that situation is I either use the default, or I use the default of a software that a lot of people use in my field (SPSS).

in Percentile differences between Jasp & SPSS Comment by patc3 August 13

Duplicate the analysis by clicking the green button and do it through separate analyses instead. My guess is it's a "lack of functionality", as there are some scenarios where you want the constraints to be the same across models; this is …

in Multigroup SEM via lavaan Comment by patc3 August 12

There's several methods for calculating percentiles, and the SPSS and R defaults are not the same. (JASP uses R in the background) https://www.rdocumentation.org/packages/stats/versions/3.6.2/topics/quantile SPSS uses type 6, the default in R is ty…

in Percentile differences between Jasp & SPSS Comment by patc3 August 11

Of course the difference in residuals is due to the difference between the models, i.e. the addition of baseline as a numeric predictor. Baseline as a predictor uses up 1 degree of freedom, and if it interacts with another predictor, it uses up anot…

in Different Degrees of Freedom (ANCOVA vs ANOVA) Comment by patc3 August 9

What's your model? What's your lavaan syntax? Your question would benefit from a lot more detail... Personally I'm not sure what you're trying to achieve

in SEM condition specific constraints Comment by patc3 August 9

just means that they did group2 minus group1 and you did group1 minus group2. This is inconsequential. Same p-value, same conclusion, same difference being tested, etc.

in different t-test results with 2 researchers, same data Comment by patc3 August 6

It's in ANOVA under Nonparametrics: https://forum.cogsci.nl/uploads/567/GLTZ3GI2RZ8S.png https://forum.cogsci.nl/uploads/381/QITYTVTXL9JG.png https://forum.cogsci.nl/uploads/483/1ZHMHFMRU5X3.png https://forum.cogsci.nl/uploads/827/FAR74SD05CEM.png

in Kruskal Wallis test Comment by patc3 August 5

you can do it "manually" in the SEM analysis using lavaan syntax

in Latent Growth Modeling with multiple domains in JASP Comment by patc3 July 11

@TarandeepKang Cool! Great idea, I personally would love to see this arrive in JASP

in Cluster Analysis of Ordinal Categorical data in JASP Comment by patc3 July 9

Yes under the module Mixed Models then Linear Mixed Models, in fact all random slopes are specified by default (for better or worse): https://forum.cogsci.nl/uploads/587/CZZR8ZOUX8NV.png

in is linear mixed model with a random slope in possible in JASP? Comment by patc3 July 7

Go in the R console in JASP (you might have to add the module), and type: 1-pchisq(39.16,1)

in Confirmatory factor analysis Comment by patc3 June 24

this is an EFA (exploratory FA), not a CFA, that's why all items load on all factors. You can do this in JASP in factor > exploratory factor analysis

in JASP CFA Comment by patc3 June 19

AgeM =~ Age Price =~ PP1 PastUseM =~ PastUse at a minimum I'm guessing you have a problem with these 3 factor definitions, as these are phantom constructs, and I can't imagine this is the right syntax for them (specifically, you probably need to add…

in SEM in JASP Comment by patc3 June 18

I am aware that I could map numerical values to my categories given they are ordered and use other methods (e.g., K-means or density). What would be the limitations of this approach (any further reading appreciated) as this is a statistical questi…

in Cluster Analysis of Ordinal Categorical data in JASP Comment by patc3 June 18

I remember seeing "end of June" somewhere? maybe I'm imagining

in New Version? Comment by patc3 June 13

Can you show a bit more please

in Factor analysis: Path diagram explanation Comment by patc3 June 4

@Pedro_Rosa that's interesting. It does look like the mediation analysis simply standardizes the variables in order to obtain the standardized estimates, whereas the SEM module presumably obtains the actual standardized estimates. I'm not sure why t…

in SEM-mediation analysis: different results in JASP and R Comment by patc3 May 27

Thanks Jana, your post is very clear. Yes let's see what they say, I'm curious as well.

in Settings when running SEM Comment by patc3 May 13

Howdy, Stranger!

patc3

About

Comments