# Introduction to fastpos In fastpos: Finds the Critical Sequential Point of Stability for a Pearson Correlation

## FAQ

### What does fastpos do if the corridor of stability is not reached for a simulation study?

In this case fastpos will return an NA value for the point of stability. When calculating the quantiles, fastpos will use the maximum sample size, which is a more reasonable estimate than ignoring the specific simulation study altogether.

### Why does fastpos produce different estimates to corEvol?

If the same parameters are used, the differences are rather small. In general, differences cannot be avoided entirely due to the random nature of the whole process. Even if the same algorithm is used, the estimates will vary slightly from run to run. The other more important aspect is how studies are treated where the point of stability is not reached: corEvol ignores them, while fastpos assumes that the corridor was reached at the maximum sample size. Thus, if the parameters are the same, fastpos will tend to produce larger estimates, which is more accurate (and more conservative). But note that if the corridor of stability is not reached, then you should increase the maximum sample size. Previously, this was not feasible due to the computational demands, but with fastpos it usually can be done.

## Issues and Support

If you find any bugs, please use the issue tracker at:

https://github.com/johannes-titz/fastpos/issues

If you need answers on how to use the package, drop me an e-mail at johannes at titz.science or johannes.titz at gmail.com

## Contributing

Comments and feedback of any kind are very welcome! I will thoroughly consider every suggestion on how to improve the code, the documentation, and the presented examples. Even minor things, such as suggestions for better wording or improving grammar in any part of the package, are more than welcome.

If you want to make a pull request, please check that you can still build the package without any errors, warnings, or notes. Overall, simply stick to the R packages book: https://r-pkgs.org/

## Try the fastpos package in your browser

Any scripts or data that you put into this service are public.

fastpos documentation built on Oct. 23, 2020, 7:12 p.m.