This tutorial introduces the estimation of regularized partial correlation networks for psychological data. It explains how regularization techniques can be used to estimate a parsimonious and interpretable network structure. The tutorial demonstrates the method using an empirical example on post-traumatic stress disorder data and discusses the effect of the hyperparameter, handling of non-normal data, and determining the required sample size for network analysis. It also provides a checklist for potential problems in estimating regularized partial correlation networks. Partial correlation networks are estimated using regularization techniques from machine learning. These techniques help in estimating a sparse network structure, where many parameters are estimated to be exactly zero. This leads to simpler and more interpretable networks. Regularization jointly performs model selection and parameter estimation. The tutorial discusses how to estimate partial correlation networks in R, how to handle non-normal data, and how to determine the required sample size for network analysis. The tutorial also discusses the importance of replicability in psychological research and provides a priori sample size analysis to determine if the sample size is appropriate for the expected network structure. It also provides post-hoc stability analysis to assess the stability of results. The tutorial highlights the importance of choosing the correct hyperparameter for regularization and the impact of sample size on network estimation. It also discusses the interpretation of partial correlation networks and how they can be used to model unique interactions between variables, highlight multicollinearity and predictive mediation, and indicate potential causal pathways. The tutorial also discusses how clusters in the network may highlight latent variables and provides an example of a network estimated using regularized partial correlation networks.This tutorial introduces the estimation of regularized partial correlation networks for psychological data. It explains how regularization techniques can be used to estimate a parsimonious and interpretable network structure. The tutorial demonstrates the method using an empirical example on post-traumatic stress disorder data and discusses the effect of the hyperparameter, handling of non-normal data, and determining the required sample size for network analysis. It also provides a checklist for potential problems in estimating regularized partial correlation networks. Partial correlation networks are estimated using regularization techniques from machine learning. These techniques help in estimating a sparse network structure, where many parameters are estimated to be exactly zero. This leads to simpler and more interpretable networks. Regularization jointly performs model selection and parameter estimation. The tutorial discusses how to estimate partial correlation networks in R, how to handle non-normal data, and how to determine the required sample size for network analysis. The tutorial also discusses the importance of replicability in psychological research and provides a priori sample size analysis to determine if the sample size is appropriate for the expected network structure. It also provides post-hoc stability analysis to assess the stability of results. The tutorial highlights the importance of choosing the correct hyperparameter for regularization and the impact of sample size on network estimation. It also discusses the interpretation of partial correlation networks and how they can be used to model unique interactions between variables, highlight multicollinearity and predictive mediation, and indicate potential causal pathways. The tutorial also discusses how clusters in the network may highlight latent variables and provides an example of a network estimated using regularized partial correlation networks.