smartpls 4 lecture 4b Structural Model: Sample Size, Predictive Relevance, PLS Predict, CV PAT, BIC скачать в хорошем качестве

smartpls 4 lecture 4b Structural Model: Sample Size, Predictive Relevance, PLS Predict, CV PAT, BIC

link for the data set used in this video: https://shorturl.at/hsMP3 data set less than 100 for student version: https://shorturl.at/tCW69 In this video I discuss the fourth and fifth step of structural model analysis. Following topics are discussed: Sample size: How to determine the minimum sample size required for a structural model. Predictive relevance: How to assess the predictive relevance of a structural model. PLS Predict: A feature in SmartPLS 4 that can be used to assess the predictive relevance of a structural model. CV PAT: A statistical test that can be used to compare the predictive relevance of different structural models. BIC: A statistical criterion that can be used to compare the predictive relevance of different structural models. We will also use a real-world data set to illustrate these concepts. The target audience for this lecture is researchers who are new to structural modeling in SmartPLS 4. This lecture will provide a basic understanding of the concepts of sample size, predictive relevance, PLS Predict, CV PAT, and BIC, and how to use them in SmartPLS 4. Here are some of the key takeaways from this lecture: The minimum sample size required for a structural model depends on the number of variables in the model and the desired level of power. Predictive relevance can be assessed using a variety of methods, including PLS Predict and CV PAT. BIC is a statistical criterion that can be used to compare the predictive relevance of different structural models. I hope this summary is helpful! Let me know if you have any other questions. Here are some additional details about the topics discussed in the lecture: Sample size: The minimum sample size required for a structural model depends on the number of variables in the model and the desired level of power. The desired level of power is the probability of correctly rejecting the null hypothesis when it is false. A higher desired level of power requires a larger sample size. Predictive relevance: Predictive relevance is a measure of how well a structural model can predict the values of the dependent variable. There are a variety of methods that can be used to assess predictive relevance, including PLS Predict and CV PAT. PLS Predict: PLS Predict is a feature in SmartPLS 4 that can be used to assess the predictive relevance of a structural model. PLS Predict uses a cross-validation procedure to estimate the predictive accuracy of the model. CV PAT: CV PAT is a statistical test that can be used to compare the predictive relevance of different structural models. CV PAT uses a cross-validation procedure to estimate the predictive accuracy of each model, and then compares the results using a statistical test. BIC: BIC is a statistical criterion that can be used to compare the predictive relevance of different structural models. BIC is a measure of the relative complexity of a model, and it penalizes models that are too complex.