Search results

  1. T

    how to restructure a dataset for discrete time survival analysis?

    I would like to develop a discrete time logit model to predict corporate bankruptcy. My sample period is between 2007 and 2013. I don't know how to code 'time to events' as 1) many firms (let's say company ID 1 in the attached file ) had already existed and were exposed to bankruptcy risk before...
  2. T

    what is the command to automatically winsorize a continuous variable?

    I know how to use the menu to winsorise a continuous variable at the 1st and 99th percentiles. If I were to use a command, what does the command look like? say, a variable called "age", and i would like to winsorise it at the 1st and 99th percentiles and create it a new variable called...
  3. T

    mixed logit model using R

    Hello, I am trying to estimate a mixed logit model on a panel dataset (for a company, up to five years observations were collected). When I estimate the model and include random intercept for company (data are clustered at the company level), does this mean that I control for interdependence of...
  4. T

    How to convert years into relative years in spss?

    I sort my data according to ID in ascending order and then according to year in descending order. firm years with the same ID belong to the same firm. Imagine a firm has got 5 year observations, 2009, 2007, 2006, 2005, 2004. I would like to transform them into a new variable called relative...