semopy 2: A Structural Equation Modeling Package with Random Effects in Python. Meshcheryakov, G., Igolkina, A. A., & Samsonova, M. G. arXiv:2106.01140 [cs, stat], June, 2021. arXiv: 2106.01140![semopy 2: A Structural Equation Modeling Package with Random Effects in Python [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper abstract bibtex Structural Equation Modeling (SEM) is an umbrella term that includes numerous multivariate statistical techniques that are employed throughout a plethora of research areas, ranging from social to natural sciences. Until recently, SEM software was either commercial or restricted to niche languages, and the lack of SEM packages compatible with more mainstream programming languages was dire. To combat that, we introduced a Python package semopy 1 that surpassed other state-of-the-art software in terms of performance and estimation accuracy. Yet, it was lacking in functionality and its usage was burdened with unnecessary boilerplate code. Here, we introduce a complete overhaul of semopy that improves upon the previous results and comes with lots of new capabilities. Furthermore, we propose a novel SEM model that combines in itself a notion of random effects from linear mixed models (LMMs) to model numerous phenomena, such as spatial data, time series or population stratification in genetics.
@article{meshcheryakov_semopy_2021,
title = {semopy 2: {A} {Structural} {Equation} {Modeling} {Package} with {Random} {Effects} in {Python}},
shorttitle = {semopy 2},
url = {http://arxiv.org/abs/2106.01140},
abstract = {Structural Equation Modeling (SEM) is an umbrella term that includes numerous multivariate statistical techniques that are employed throughout a plethora of research areas, ranging from social to natural sciences. Until recently, SEM software was either commercial or restricted to niche languages, and the lack of SEM packages compatible with more mainstream programming languages was dire. To combat that, we introduced a Python package semopy 1 that surpassed other state-of-the-art software in terms of performance and estimation accuracy. Yet, it was lacking in functionality and its usage was burdened with unnecessary boilerplate code. Here, we introduce a complete overhaul of semopy that improves upon the previous results and comes with lots of new capabilities. Furthermore, we propose a novel SEM model that combines in itself a notion of random effects from linear mixed models (LMMs) to model numerous phenomena, such as spatial data, time series or population stratification in genetics.},
urldate = {2021-06-07},
journal = {arXiv:2106.01140 [cs, stat]},
author = {Meshcheryakov, Georgy and Igolkina, Anna A. and Samsonova, Maria G.},
month = jun,
year = {2021},
note = {arXiv: 2106.01140},
keywords = {mathematical software, statistics, uses sympy},
}
Downloads: 0
{"_id":"ZAp5GYPQTFYoceS29","bibbaseid":"meshcheryakov-igolkina-samsonova-semopy2astructuralequationmodelingpackagewithrandomeffectsinpython-2021","author_short":["Meshcheryakov, G.","Igolkina, A. A.","Samsonova, M. G."],"bibdata":{"bibtype":"article","type":"article","title":"semopy 2: A Structural Equation Modeling Package with Random Effects in Python","shorttitle":"semopy 2","url":"http://arxiv.org/abs/2106.01140","abstract":"Structural Equation Modeling (SEM) is an umbrella term that includes numerous multivariate statistical techniques that are employed throughout a plethora of research areas, ranging from social to natural sciences. Until recently, SEM software was either commercial or restricted to niche languages, and the lack of SEM packages compatible with more mainstream programming languages was dire. To combat that, we introduced a Python package semopy 1 that surpassed other state-of-the-art software in terms of performance and estimation accuracy. Yet, it was lacking in functionality and its usage was burdened with unnecessary boilerplate code. Here, we introduce a complete overhaul of semopy that improves upon the previous results and comes with lots of new capabilities. Furthermore, we propose a novel SEM model that combines in itself a notion of random effects from linear mixed models (LMMs) to model numerous phenomena, such as spatial data, time series or population stratification in genetics.","urldate":"2021-06-07","journal":"arXiv:2106.01140 [cs, stat]","author":[{"propositions":[],"lastnames":["Meshcheryakov"],"firstnames":["Georgy"],"suffixes":[]},{"propositions":[],"lastnames":["Igolkina"],"firstnames":["Anna","A."],"suffixes":[]},{"propositions":[],"lastnames":["Samsonova"],"firstnames":["Maria","G."],"suffixes":[]}],"month":"June","year":"2021","note":"arXiv: 2106.01140","keywords":"mathematical software, statistics, uses sympy","bibtex":"@article{meshcheryakov_semopy_2021,\n\ttitle = {semopy 2: {A} {Structural} {Equation} {Modeling} {Package} with {Random} {Effects} in {Python}},\n\tshorttitle = {semopy 2},\n\turl = {http://arxiv.org/abs/2106.01140},\n\tabstract = {Structural Equation Modeling (SEM) is an umbrella term that includes numerous multivariate statistical techniques that are employed throughout a plethora of research areas, ranging from social to natural sciences. Until recently, SEM software was either commercial or restricted to niche languages, and the lack of SEM packages compatible with more mainstream programming languages was dire. To combat that, we introduced a Python package semopy 1 that surpassed other state-of-the-art software in terms of performance and estimation accuracy. Yet, it was lacking in functionality and its usage was burdened with unnecessary boilerplate code. Here, we introduce a complete overhaul of semopy that improves upon the previous results and comes with lots of new capabilities. Furthermore, we propose a novel SEM model that combines in itself a notion of random effects from linear mixed models (LMMs) to model numerous phenomena, such as spatial data, time series or population stratification in genetics.},\n\turldate = {2021-06-07},\n\tjournal = {arXiv:2106.01140 [cs, stat]},\n\tauthor = {Meshcheryakov, Georgy and Igolkina, Anna A. and Samsonova, Maria G.},\n\tmonth = jun,\n\tyear = {2021},\n\tnote = {arXiv: 2106.01140},\n\tkeywords = {mathematical software, statistics, uses sympy},\n}\n\n\n\n\n\n\n\n","author_short":["Meshcheryakov, G.","Igolkina, A. A.","Samsonova, M. G."],"key":"meshcheryakov_semopy_2021","id":"meshcheryakov_semopy_2021","bibbaseid":"meshcheryakov-igolkina-samsonova-semopy2astructuralequationmodelingpackagewithrandomeffectsinpython-2021","role":"author","urls":{"Paper":"http://arxiv.org/abs/2106.01140"},"keyword":["mathematical software","statistics","uses sympy"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/zotero-group/nicoguaro/525293","dataSources":["YtBDXPDiQEyhyEDZC","fhHfrQgj3AaGp7e9E","qzbMjEJf5d9Lk78vE","45tA9RFoXA9XeH4MM","MeSgs2KDKZo3bEbxH","nSXCrcahhCNfzvXEY","ecatNAsyr4f2iQyGq","tpWeaaCgFjPTYCjg3"],"keywords":["mathematical software","statistics","uses sympy"],"search_terms":["semopy","structural","equation","modeling","package","random","effects","python","meshcheryakov","igolkina","samsonova"],"title":"semopy 2: A Structural Equation Modeling Package with Random Effects in Python","year":2021}