One sample sign test

Discuss statistics related things
Post Reply
dama
Posts: 11
Joined: Wed Apr 07, 2021 5:12 pm

One sample sign test

Post by dama »

In a couple of articles* I have encountered the so called one sample sign test. To my understanding, Jamovi does not support this type of procedure!?

If I have X variables which is coded -1, 0, 1 and I would like to calculate if the mean is significantly different from 0 using Jamovi, what procedure would you recommend?

*See for an example: Bogaard, G., & Meijer, E. H. (2018). Self-Reported Beliefs About Verbal Cues Correlate with Deception-Detection Performance. Applied Cognitive Psychology, 32(1), 129-137. https://doi.org/10.1002/acp.3378
User avatar
jonathon
Posts: 2613
Joined: Fri Jan 27, 2017 10:04 am

Re: One sample sign test

Post by jonathon »

let's see if maurizio comes up with a suggestion.

jonathon
User avatar
MAgojam
Posts: 421
Joined: Thu Jun 08, 2017 2:33 pm
Location: Parma (Italy)

Re: One sample sign test

Post by MAgojam »

jonathon wrote:let's see if maurizio comes up with a suggestion.
Jonathon did you call me? :sunglasses:

Hi, guys.
I would propose to use:
Analysis> Frequencies>2 Outcomes-Binomial Test.

For a cleaner and faster analysis I suggest activating the Values are counts checkbox in order to analyze all the variables of interest in a single step, taking care to enter only the counts of -1 in the first row and the counts of 1 in the second row (or vice versa).
(I tried it with the data from TABLE 1 of the article reported, as I do for a peer review).

Greetings,
Maurizio
dama
Posts: 11
Joined: Wed Apr 07, 2021 5:12 pm

Re: One sample sign test

Post by dama »

Much appreciated.. Awesome, many thanks for the help..

In the article they also refer to an effect size that Varga and Delaney (2000)* has proposed. δ-index for stochastic difference. You wouldn't happen to know if there is a shortcut to calculate that? If not in Jamovi, perhaps somewhere else?

Once again, I sincerely appreciate your help.

*Vargha, A., & Delaney, H. D. (2000). A critique and improvement of the CL common language effect size statistics of McGraw and Wong. Journal of Educational and Behavioral Statistics, 25, 101–132.
User avatar
MAgojam
Posts: 421
Joined: Thu Jun 08, 2017 2:33 pm
Location: Parma (Italy)

Re: One sample sign test

Post by MAgojam »

dama wrote:Varga and Delaney (2000)* has proposed. δ-index for stochastic difference. You wouldn't happen to know if there is a shortcut to calculate that?
Hi, @dama.

The (-1, 0, 1) encoding for your variables makes them available as a dominance matrix, the mean of which corresponds to the effect size (Cliff's Delta).

There is a linear relationship between Cliff delta and VDA delta (Varga and Delaney, 2000) if we consider that Cliff_d ranges from -1 to 1, while VDA_d ranges from 0 to 1.
How do I get VDA_d from Cliffs_d:
VDA_d = (Cliffs_d + 1) / 2

I don't think it is important which of the two to report, I consider that it is possible to calculate one from the other.
If you ask the question, which is better, I personally prefer Cliff's delta, since it scales between -1 and 1, and if you take it as an absolute value, between 0 and 1, with 0 = no effect (overlapping data) and 1 effect stronger (no overlap between data).
It can be said that the VDA delta is calculated so that no effect produces a value of 0.50.
A value of 1 indicates the complete stochastic superiority of one group and a value of 0 indicates the complete stochastic superiority of the other group.

I hope I've answered your question, but if you want to look at some R functions to use with the Rj module you can take a look at Marco Torchiano's "effsize" package:
https://github.com/mtorchiano/effsize/tree/master/R

Cheers,
Maurizio
dama
Posts: 11
Joined: Wed Apr 07, 2021 5:12 pm

Re: One sample sign test

Post by dama »

Hey,

Many thanks for the help. I'm a beginner in the field and your help is much appreciated. Yes, you answered my question. I took a look at the effsize package and the Rj module. I could not get it to work. Most likely I am doing something wrong.

I have done a binomial test for my items. Perhaps someone can direct me to a helpful install guide for the effsize package? Or if someone has an idea where I can get my hands on a Cliff's delta calculator that works independently from Jamovi?

Once again thanks Maurizio!
Post Reply