Ferramenta Passo a Passo

A ferramenta Passo a Passo determina os melhores preditores para incluir em um modelo entre um conjunto maior de variáveis preditoras potenciais para modelos de regressão linear, logística e outros modelos tradicionais.

There are 2 basic approaches used in implementing stepwise regression.

The first (known as backward selection) involves the use of a model that includes all variables that are thought to potentially influence the target variable, and then sequentially removes the least important variable from the original model based on a goodness-of-fit measure that adjusts for the number of variables included in the model. This process continues, with other variables being removed in subsequent backward steps, until there are no further improvements in the adjusted fit measure.

The second basic approach (known as forward variable selection) starts with a model that includes only a constant, and then adds to that model one variable out of the set of potential variables that provides the greatest improvement in the adjusted fit measure. This process is repeated to add additional variables using a set of additional forward steps, which ends when there is no further improvement in the adjusted fit measure. In the base of backward variables selection, a variable that is removed never re-enters in subsequent steps, while in forward selection a variable is never removed in later steps once it has been added. A hybrid approach can be used that starts with a large ("maximal") initial model and a first backward step, but then both forward and backward movements are evaluated in each subsequent step.

A ferramenta de regressão passo a passo do Alteryx baseada no R seleciona variáveis usando tanto a seleção backward quanto uma combinação entre as seleções backward e forward. To use the tool, first create a "maximal" regression model that includes all of the variables you believe could matter, and then use the stepwise regression tool to determine which of these variables should be removed based on an adjusted fit measure. A choice of 2 different adjusted fit measures are provided to the user, the Akaike information criterion** (or AIC) and the Bayesian information criterion*** (or BIC). These 2 measures are similar to one another, but the BIC places a larger penalty on the number of variables included in the model, typically resulting in a final model with fewer variables than is the case when the AIC is used.

Com essa ferramenta, se os dados de entrada vierem de um fluxo de dados regular do Alteryx, será usada a função open-source GLM do R para o treinamento do modelo. Se os dados de entrada vierem de uma ferramenta Saída XDF ou Entrada XDF, será usada a função RevoScaleR rxDForest para o treinamento do modelo. A vantagem de usar a função baseada em Revo ScaleR é que, com ela, é possível analisar conjuntos de dados muito maiores, mas ela tem custos extras para criar um arquivo XDF, não cria algumas das saídas de diagnóstico do modelo que estão disponíveis com as funções open-source do R e só pode gerar modelos de regressão de Poisson.

Essa ferramenta utiliza a ferramenta R. Vá para Opções Baixar ferramentas preditivas e faça login no portal de Downloads e Licenças da Alteryx para instalar o R e os pacotes usados pela ferramenta R. Visite Baixar e utilizar ferramentas preditivas.