Nadira Bag .I apologize for my delayed response. You ask a good question! I think the LPM has the advantage of being simpler to implement and more intuitive. But this can't be all there is to it :)
You can use the logic model in excel if you manually alter the equation to best fit your data by minimizing the sum of squared differences between your prodiced probabiltiy from the modle and the actual binary y outputs. its a pain to do though.... haha
You can equally use the input command in stata to enter the data manually and follow what is being done. Or rather just type directly into stata spreadsheet
I want to run a descriptive statistic before logit regression. Since I want to run logit regression, I changed my dependent variables to 0 and 1, thus when I run the descriptive, should I use the original data or 0 and 1?