Bring #177 up to date again (#198)

[jorpppp]

• impute(instag)only imputing missing policyvar values for cases when treatment changes within unit #181 Fix check for constant treatment value and add returns (#181 Fix check for constant treatment value and add returns #182)

• 186 error when normalizing 0 coefficient (186 error when normalizing 0 coefficient #187)

• Error when normalizing 0 coefficient #186 Fix bug when normalizing to 0 or positive

• Error when normalizing 0 coefficient #186 Propagate the fix to _eventiv

• PR for Let the window option choose a window range based on event-time limits in the data #170: let the window option choose a window range (PR for #170: let the window option choose a window range #178)

• Let the window option choose a window range based on event-time limits in the data #170 bring changes from main

• Let the window option choose a window range based on event-time limits in the data #170 implement finding max or balanced window

• Let the window option choose a window range based on event-time limits in the data #170 examples to test implementation

• Let the window option choose a window range based on event-time limits in the data #170 add examples to test file

• Let the window option choose a window range based on event-time limits in the data #170 change window description and add example in help file

• Let the window option choose a window range based on event-time limits in the data #170 wording of calculated-window message

• Let the window option choose a window range based on event-time limits in the data #170 modify description of left and right window

• Let the window option choose a window range based on event-time limits in the data #170 wording of window limits

• Let the window option choose a window range based on event-time limits in the data #170 wording of calculated-window message

• Let the window option choose a window range based on event-time limits in the data #170 check for zero words in window

• Let the window option choose a window range based on event-time limits in the data #170 rearrange parsewindow checks

• Let the window option choose a window range based on event-time limits in the data #170 wording of window-parser error messges

• Let the window option choose a window range based on event-time limits in the data #170 add to help file example about maximum window

• Let the window option choose a window range based on event-time limits in the data #170 conflict with static

• "Let the window option choose a window range based on event-time limits in the data #170 revert previous commit"

This reverts commit c6d98aa.

• Let the window option choose a window range based on event-time limits in the data #170 parse window only when it is non-empty

• Let the window option choose a window range based on event-time limits in the data #170 window in cmdline parser

• Let the window option choose a window range based on event-time limits in the data #170 Delete issue170 special directory

• Let the window option choose a window range based on event-time limits in the data #170 wording of string window message

• Let the window option choose a window range based on event-time limits in the data #170 let max or balanced only if impute is specified

• Let the window option choose a window range based on event-time limits in the data #170 wording of error message

• Let the window option choose a window range based on event-time limits in the data #170 restructure checks for staggered adoption

• Let the window option choose a window range based on event-time limits in the data #170 restructure for IV case

• Let the window option choose a window range based on event-time limits in the data #170 informative window message and error message for balanced

• "Let the window option choose a window range based on event-time limits in the data #170 revert previous commit"

This reverts commit fc197a9.

• Let the window option choose a window range based on event-time limits in the data #170 informative window message and error message for balanced

• Let the window option choose a window range based on event-time limits in the data #170 paragraph for max balanced

• Let the window option choose a window range based on event-time limits in the data #170 check trend outside window for max and balanced

• Let the window option choose a window range based on event-time limits in the data #170 remove comment

• Let the window option choose a window range based on event-time limits in the data #170 trend specification if window is max or balanced

• Let the window option choose a window range based on event-time limits in the data #170 clear message about treatment time

• Let the window option choose a window range based on event-time limits in the data #170 check leads in proxyiv are in estimation window

• Let the window option choose a window range based on event-time limits in the data #170 wording of message about calculated window

• PR for #170: let the window option choose a window range #178 Minor change to calculated window message

• Let the window option choose a window range based on event-time limits in the data #170 mark non-missing obs in varlist

• Let the window option choose a window range based on event-time limits in the data #170 examples to test implementation

• Let the window option choose a window range based on event-time limits in the data #170 pass marker and revert syntax of eventgenvars

• Let the window option choose a window range based on event-time limits in the data #170 Add marked sample to variables to keep when repeatedcs

• Let the window option choose a window range based on event-time limits in the data #170 Delete issue170 directory

• PR for #170: let the window option choose a window range #178 Edits to helpfile

---

Co-authored-by: jorpppp jorpppp@gmail.com

• PR for Check behavior of the cohort and control_cohort options and allow automatic generation #179 Check behavior of the cohort and control_cohort options and allow automatic generation (PR for #179 Check behavior of the cohort and control_cohort options and allow automatic generation #185)

• Check behavior of the cohort and control_cohort options and allow automatic generation #179 Create cohort_consistency.do

• Check behavior of the cohort and control_cohort options and allow automatic generation #179 Add consistency checks between cohort, control_cohort, and policyvar, add basic cohort variable creation

• Check behavior of the cohort and control_cohort options and allow automatic generation #179 Change cohort, control_cohort to string in xtevent

• Check behavior of the cohort and control_cohort options and allow automatic generation #179 Add bin and no reversion returns to _eventgenvars plus changes from impute(instag)only imputing missing policyvar values for cases when treatment changes within unit #181

• Check behavior of the cohort and control_cohort options and allow automatic generation #179 Enable saving created cohort variable

• Check behavior of the cohort and control_cohort options and allow automatic generation #179 Automatic generation of control_cohort

• Check behavior of the cohort and control_cohort options and allow automatic generation #179 Update help file

• Check behavior of the cohort and control_cohort options and allow automatic generation #179 Modify test file

• Check behavior of the cohort and control_cohort options and allow automatic generation #179 Delete issue folder

• Check behavior of the cohort and control_cohort options and allow automatic generation #179 PR for #179 Check behavior of the cohort and control_cohort options and allow automatic generation #185 Generate cohort in sample that ignores missings in control vars

• Check behavior of the cohort and control_cohort options and allow automatic generation #179 PR for #179 Check behavior of the cohort and control_cohort options and allow automatic generation #185 Add checks for existing cohort variables

• Check behavior of the cohort and control_cohort options and allow automatic generation #179 PR for #179 Check behavior of the cohort and control_cohort options and allow automatic generation #185 SA and proxy not allowed

• Check behavior of the cohort and control_cohort options and allow automatic generation #179 PR for #179 Check behavior of the cohort and control_cohort options and allow automatic generation #185 Fix bug in naming saved interaction variables

• Check behavior of the cohort and control_cohort options and allow automatic generation #179 PR for #179 Check behavior of the cohort and control_cohort options and allow automatic generation #185 Fix sorting bug when creating cohorts in repeatedcs setting

• PR for: Difference of averages doesn't include all coefficients #189 pre and post coefficients excluding omitted ones (PR for: #189 pre and post coefficients excluding omitted ones #190)

• Difference of averages doesn't include all coefficients #189 pre and post coefficients excluding omitted ones

• Difference of averages doesn't include all coefficients #189 PR for: #189 pre and post coefficients excluding omitted ones #190 enable diff avg in _eventiv

• Difference of averages doesn't include all coefficients #189 PR for: #189 pre and post coefficients excluding omitted ones #190 exclude endpoints from diffavg when trend is active

---

Co-authored-by: jorpppp jorpppp@gmail.com

• 188 left window of zero returns an error (188 left window of zero returns an error #194)

• Left window of zero returns an error #188 ordering when there are not pre-event dummies

• Left window of zero returns an error #188 ordering the left endpoint

• Left window of zero returns an error #188 Do not test for pretrends for plot if left window is zero

• Left window of zero returns an error #188 188 left window of zero returns an error #194 Disable smoothest path if left window

• PR for: Difference of averages doesn't include all coefficients #189 pre and post coefficients excluding omitted ones (PR for: #189 pre and post coefficients excluding omitted ones #190) (PR for: #189 pre and post coefficients excluding omitted ones (#190) #195)

• Difference of averages doesn't include all coefficients #189 pre and post coefficients excluding omitted ones

• Difference of averages doesn't include all coefficients #189 PR for: #189 pre and post coefficients excluding omitted ones #190 enable diff avg in _eventiv

• Difference of averages doesn't include all coefficients #189 PR for: #189 pre and post coefficients excluding omitted ones #190 exclude endpoints from diffavg when trend is active

---

Co-authored-by: Constantino Carreto Romero carretoromeroc@gmail.com

• Left window of zero returns an error #188 188 left window of zero returns an error #194 Fix error messages for diffavg when windows are zero

• Left window of zero returns an error #188 188 left window of zero returns an error #194 Fix lead selection and normalization when left window is zero or when many coefs are normalized

• Left window of zero returns an error #188 188 left window of zero returns an error #194 Recheck that lead instrument is in estimation window when it is changed because normalizations coincide

• Left window of zero returns an error #188 188 left window of zero returns an error #194 Do not test linear pretrend if too few pre-event coefs

---

Co-authored-by: Constantino Carreto Romero carretoromeroc@gmail.com

---

Co-authored-by: Constantino Carreto Romero carretoromeroc@gmail.com