BUG: scipy.stats.Pearson3 ppf function uses right tail probability instead of left

[dmkeijzer]

Describe your issue.

I had been using the Percent Point Function (ppf) in my optimization code. One of my distributions ended up being a pearson3, when I ended up comparing it to the CDF, the values had a large discrepancy with the ppf function. I proceeded to check the documentation and found the following

This however, is not true when I run it in my own environment see below.

Reproducing Code Example

from scipy.stats import pearson3

skew = -2

vals = pearson3.ppf([0.001, 0.5, 0.999], skew)
check = pearson3.cdf(vals, skew)
print(f"check = {check}")
print(f"vals = {vals}")
print(np.allclose([0.001, 0.5, 0.999], check))

Error message

check = [0.999 0.5   0.001]
vals = [ 0.9989995   0.30685282 -5.90775528]
False

SciPy/NumPy/Python version and system information

1.7.3 1.21.5 sys.version_info(major=3, minor=10, micro=4, releaselevel='final', serial=0)
lapack_mkl_info:
    libraries = ['mkl_rt']
    library_dirs = ['C:/Users/damie/anaconda3/envs/geo\\Library\\lib']
    define_macros = [('SCIPY_MKL_H', None), ('HAVE_CBLAS', None)]
    include_dirs = ['C:\\Program Files (x86)\\IntelSWTools\\compilers_and_libraries_2019.0.117\\windows\\mkl', 'C:\\Program Files (x86)\\IntelSWTools\\compilers_and_libraries_2019.0.117\\windows\\mkl\\include', 'C:\\Program Files (x86)\\IntelSWTools\\compilers_and_libraries_2019.0.117\\windows\\mkl\\lib', 'C:/Users/damie/anaconda3/envs/geo\\Library\\include']
lapack_opt_info:
    libraries = ['mkl_rt']
    library_dirs = ['C:/Users/damie/anaconda3/envs/geo\\Library\\lib']
    define_macros = [('SCIPY_MKL_H', None), ('HAVE_CBLAS', None)]
    include_dirs = ['C:\\Program Files (x86)\\IntelSWTools\\compilers_and_libraries_2019.0.117\\windows\\mkl', 'C:\\Program Files (x86)\\IntelSWTools\\compilers_and_libraries_2019.0.117\\windows\\mkl\\include', 'C:\\Program Files (x86)\\IntelSWTools\\compilers_and_libraries_2019.0.117\\windows\\mkl\\lib', 'C:/Users/damie/anaconda3/envs/geo\\Library\\include']
blas_mkl_info:
    libraries = ['mkl_rt']
    library_dirs = ['C:/Users/damie/anaconda3/envs/geo\\Library\\lib']
    define_macros = [('SCIPY_MKL_H', None), ('HAVE_CBLAS', None)]
    include_dirs = ['C:\\Program Files (x86)\\IntelSWTools\\compilers_and_libraries_2019.0.117\\windows\\mkl', 'C:\\Program Files (x86)\\IntelSWTools\\compilers_and_libraries_2019.0.117\\windows\\mkl\\include', 'C:\\Program Files (x86)\\IntelSWTools\\compilers_and_libraries_2019.0.117\\windows\\mkl\\lib', 'C:/Users/damie/anaconda3/envs/geo\\Library\\include']
blas_opt_info:
    libraries = ['mkl_rt']
    library_dirs = ['C:/Users/damie/anaconda3/envs/geo\\Library\\lib']
    define_macros = [('SCIPY_MKL_H', None), ('HAVE_CBLAS', None)]
    include_dirs = ['C:\\Program Files (x86)\\IntelSWTools\\compilers_and_libraries_2019.0.117\\windows\\mkl', 'C:\\Program Files (x86)\\IntelSWTools\\compilers_and_libraries_2019.0.117\\windows\\mkl\\include', 'C:\\Program Files (x86)\\IntelSWTools\\compilers_and_libraries_2019.0.117\\windows\\mkl\\lib', 'C:/Users/damie/anaconda3/envs/geo\\Library\\include']
Supported SIMD extensions in this NumPy install:
    baseline = SSE,SSE2,SSE3
    found = SSSE3,SSE41,POPCNT,SSE42,AVX,F16C,FMA3,AVX2
    not found = AVX512F,AVX512CD,AVX512_SKX,AVX512_CLX,AVX512_CNL

[WarrenWeckesser]

Thanks for reporting the issue, @dmkeijzer. You are using SciPy version 1.7.3. According to gh-17055, the problem was fixed in version 1.9.2. Your best option is to upgrade your installed version of SciPy.