Options

# "How to test the assumptions of logistic regression in RM?"

ophelie_vdp
Member Posts:

**5**Newbie
Hello ! I am getting a bit lost in my analysis and I am stuck between two steps of my methodology. I had a

However, I'd like to have between

Thank you all for your help, I'm getting a bit stressed by my incoming deadline and will appreciate all advices

**classification**problem (churn) with a dataset of*100*variables for 100 000 examples and, after removing attributes with too many missing values and those that were too correlated to others (pairs with a correlation above 75%) or with a too small variance, I have**46 attributes**and**80 000**examples in my training set.However, I'd like to have between

**10-15 attributes**approximately and to do so, I'm using a**backward elimination**. This means that I have to already**choose a predictive model**and for now, I chose either**Random Forest**or**Logistic Regression**. My first question would be: which backward elimination model choosing knowing that the results are much different whether I do it with a logistic regression or with Random Forest? Then, I have mainly 2 questions:**, if I choose this one, I am not sure how to verify the assumptions linked to this model in Rapid Miner:***1. ASSUMPTIONS BEHIND MODELS*

For logistic regression- I have no idea how to test in Rapid Miner the
**linearity between the independent variables and the log odds of the dependent variable**. I read a bit about Box-Tidwell test but can't find that on RM. Do you have any advices or help to offer? - Hypothesis of
**Little or no multicolinearity among the variables**: is it problematic as I know some are still correlated above 50%?

**Should I normalise data**in order not to violate the assumptions?**Finally, after the backward elimination, how can I choose the best model? I know I can compare their ROC, AUC or accuracy but I also need to take into account***2. CHOOSING THE MODEL - Blackbox models*

**whether the hypothesis are verified**and**whether it's easily interpretable for anyone not familiar with data science**. For example, I would like to avoid so-called "blackbox" models such as Neural Nets but would you consider Random Forest as a blackbox model?Thank you all for your help, I'm getting a bit stressed by my incoming deadline and will appreciate all advices

Tagged:

0

## Answers

3,507RM Data Scientistas a data scientist you may not be intersted if your assumptions are valid (it might be good though). You are interested in choosing the model which can optimize your quality measure (e.g. revenue). If a model like a linear regression, which is only valid for linear cases works, than i take it.

BR,

Martin

Dortmund, Germany

5NewbieOk, thanks for the reassuring reply! It's for my thesis though and I don't know how much they'll pay attention to that. My jury is not composed of statistical experts, which is nice, but I still fear that using a model that does not allow multicollinearity between variables may look bad. But I guess I'll leave the linearity issue on the side then!

Regarding independency between variables, would you consider a correlation of 50% as breaking the independency? I tried remove all pairs above that threshold.

Thanks again!

Ophélie

3,507RM Data Scientisti would just test what threshold is better and treat it as a hyperparameter of the modelling process.

Best,

Martin

Dortmund, Germany

1,635UnicornLindon Ventures

Data Science Consulting from Certified RapidMiner Experts

5Newbie1,207UnicornCHOOSING THE MODEL:

You can also explain neural networks. First thing with the dataset (Classification) is to visualize the class distributions. Try to visualize the the dataset using T-SNE in 2 or 3 dimension. This is will give you a better understanding of how your classes are distributed. As all the algorithms doesn't give us best results we can observe and hypothesize based on the distributions. For example: If the classes are plotted as small distributions here and there on the plot, neural networks and deep learning works better. This is because they are able to calculate local minima of each distribution. If the classes are linearly separated then traditional algorithms work better. For subset selection, you can use best subset selection which is computationally expensive but gives the best attributes that are significant for training and testing based on the 2^p model training. This will give you the significant attributes when you use 10 variables or 15 variables similar to step wise selection. Lasso can be used for multicollinearity problem.

Two more performance metrics that needs to be considered are Kappa(inter-rater agreement) and RMSE which gives you the performance based on individual class prediction. Accuracy cannot be good in all cases as it depends on class distribution (class imbalance).

@mschmitz correct me if there is any issue in this.

Thanks,

Varun

Varun

https://www.varunmandalapu.com/

Be Safe. Follow precautions and Maintain Social Distancing1,635UnicornLindon Ventures

Data Science Consulting from Certified RapidMiner Experts