What is Logistic Regression? #9

No video

What is Logistic Regression? #9

Рет қаралды 3,319

Күн бұрын

Week-9
R and data files: github.com/bkrai/Statistical-...
TIMESTAMPS
00:00 Introduction & Logistic regression examples
07:13 Linear regression versus logistic regression
12:00 Logit
16:06 Log odds
19:38 Probability equation
22:11 Interpreting odds, probability
24:05 Example - student applications
25:22 Logistic regression model
26:52 Working with R
33:05 Split data
34:00 Logistic regression in R
38:00 Predicting probabilities and using probability equation for calculation
47:40 Termplot
54:37 Confusion matrix and misclassification error for training data
59:40 Confusion matrix and misclassification error for testing data
01:02:17 Predicting model essentials
01:02:46 Regression Vs classification
01:04:46 Data partitioning
01:06:18 Predictive model sequence
01:06:45 Model performance assessment & model selection
01:10:51 Model fit versus complexity
01:12:03 Some assessment strategies
01:12:33 Decision matrix or confusion matrix
01:13:36 Decision matrix or confusion matrix - training data
01:13:53 Decision matrix or confusion matrix -testing data
01:14:12 Is 80% accuracy good?
01:15:20 Two models with same accuracy
01:17:21 What is baseline rate? Calculation in R
01:19:41 Sensitivity
01:20:02 Specificity
R is a free software environment for statistical computing and graphics, and is widely used by both academia and industry. R software works on both Windows and Mac-OS. It was ranked no. 1 in a KDnuggets poll on top languages for analytics, data mining, and data science. RStudio is a user friendly environment for R that has become popular.
#LogisticRegression #LogOdds #MachineLearning

Пікірлер: 27

@ishwarshrestha2965 3 ай бұрын

I like your teaching very much here in Nepal. You are excellent!

@bkrai 3 ай бұрын

Thanks for your comments!

@rajpopat2099 Жыл бұрын

Very insightful video

@bkrai Жыл бұрын

Thanks for comments!

@andresg3110 2 жыл бұрын

We love you here in Colombia! You are the best!

@bkrai 2 жыл бұрын

Thanks for comments!

@arunjohn492 2 жыл бұрын

The Legend is Back !! Will watch it sir !!

@bkrai 2 жыл бұрын

:) Thanks!

@dimplekashyap1 2 жыл бұрын

Very informative 👌🏼👌🏼

@bkrai 2 жыл бұрын

Thanks 😊

@sarojrai9326 2 жыл бұрын

Keep uploading thank you sir

@bkrai 2 жыл бұрын

You are welcome!

@flamboyantperson5936 2 жыл бұрын

Sir I have been watching your videos since 2017

@bkrai 2 жыл бұрын

Thanks!

@sallu.mandya1995 2 жыл бұрын

Thanks a lot sir

@bkrai 2 жыл бұрын

Most welcome!

@brazilfootball 2 жыл бұрын

Great video, thank you! I noticed that the degrees of freedom go down as more variables are added to the model. Is anything "lost" when DF are lost (is power lost)? Are there any implications when DF drop below a certain number relative to the sample size?

@tadessemelakuabegaz9615 2 жыл бұрын

Dear Rai, Thank you so much for your lecture on logistic regression. I have 1 question. I asked this question previously. I am doing a machine learning model using the RandomForest and XGBoost algorithms. My data is a survey of samples derived from a large population. My data has a sampling weight which is the number of individuals in the population each respondent in the sample is representing. How can I apply this sampling weight in my ML model? The data also contains strata and clusters. Do I have to keep the sampling weight, strata, and cluster variables with my features?

@bkrai 2 жыл бұрын

I think that should help improve model performance.