About fama

fama · ‎01-26-2019

The data is 170 GB! Even finding the subset takes hours.. I will try thanks.. But what is wrong with the code?

fama · ‎01-26-2019

I did not try. The data is quite big and it takes time to be ran. I wanted to make sure if it is correct. What is the correct one then? Thanks

fama · ‎01-26-2019

Hi all, I have a data set like this: V1 V2 v3 1 1 2 1 2 1 1 2 5 1 1 2 1 2 2 2 2 3 2 1 6 2 1 6 3 2 1 3 4 3 3 4 3 . What I want is: For each v1 in each v2 : I want to find distinct v3 and then count them ( say we have 4 distinct value in V3 and each of them has different frequency) Then square each frequency and then sum up them Was wondering if the below code is right. Proc sql : create table X as select *, sum ( count ( distinct v3))*2 ) as want group by V1 V2; run; Thank you for your help

fama · ‎06-13-2018

Hi All, I am running the DID regression model to estimate the treatment effect. Prior to this, I have created the dataset using propensity score matching. So, I have matched pairs (each treated subject is matched to two nearest neighbors control subject). I am using below code. However, this code does not account for the matched data. Indeed, the matched pair should be the unit of analysis and I need to modify the below code to account for the matched pairs To make it clear, the below code considers all treated subjects versus all control subjects while I am looking for the differences between treated and control subject in each matched pair. Thanks in advanced /*Repeated measure linear regression*/ PROC MIXED DATA = Long; /* long format*/ CLASS A B; MODEL Y=A|B covariatesX1 X2..Xn / SOLUTION; LSMEANS A|B / DIFF; ESTIMATE 'D-I-D' A*B 1 -1 -1 1; RANDOM Int/SUBJECT= TYPE=UN ; RUN;

fama · ‎06-13-2018

Hi All, I am running the DID regression model to estimate the treatment effect. Prior to this, I have created the dataset using propensity score matching. So, I have matched pairs (each treated subject is matched to two nearest neighbours control subject). I am using below code. However, this code does not account for the matched data. Indeed, the matched pair should be the unit of analysis and I need to modify the below code to accout for the matched pairs To make it clear, the below code considers all treated subjects versus all control subjects while I am looking for the differences between treated and control subject in each matched pair. Thanks in advanced /*Repeated measure linear regression*/ PROC MIXED DATA = Long; /* long format*/ CLASS A B; MODEL Y=A|B covariatesX1 X2..Xn / SOLUTION; LSMEANS A|B / DIFF; ESTIMATE 'D-I-D' A*B 1 -1 -1 1; RANDOM Int/SUBJECT= TYPE=UN ; RUN;

fama · ‎03-21-2018

Thanks

fama · ‎03-21-2018

Hi every one, I have a question regarding DID estimation model. I created a data set using propensity score matching (psm) for observations that a same treatment happened to them in different period of time. If the treatment happened in period 2 we compare outcome of period 3 and 1 in treated and matched control groups. recall treatment only happened in period2, 3 and 4. Now i want to use DID model using proc glm or proc mixed etc to investigate the effect of treatment on outcome. your help will be appreciated. Thanks OBS perid1 period2 period3 period 4 period 5 treatment MatchID outcomes for all periods and other covariates 1 1 2 2 . . yes 2 1 1 1 N

fama · ‎03-21-2018

Hi every one, I have a question regarding DID estimation model. I created a data set using propensity score matching (psm) for observations that a same treatment happened to them in different period of time. If the treatment happened in period 2 we compare outcome of period 3 and 1 in treated and matched control groups. recall treatment only happened in period2, 3 and 4. Now i want to use DID model using proc glm or proc mixed etc to investigate the effect of treatment on outcome. your help will be appreciated. Thanks OBS perid1 period2 period3 period 4 period 5 treatment MatchID outcomes for all periods and other covariates 1 1 2 2 . . yes 2 1 1 1 NO 3 . .

fama · ‎10-31-2017

Hi all, I am using if- then in SAS. I want to have some classifications like below groups1: all variables from 1 to 7 should have the value under 7 (if they are not null), it means only observation 3 should be labelled as gropu1 (based on what is shown) group2: all variables should be under 15( some can be under 7 some avove). this means it should be obs 1 gropu3: all variables above 15 which is obs4.. I know I might lose some observations (like obs 2)but it is not important my goal is having the clear and right groups (1,2,3) My code: if var1<7 or obs var1 var2 var3 ....var7 1 2 4 2 13 2 3 1 17 2 3 2 4 6 5 4 16 21 22 18 your help is appreciated.

fama · ‎10-05-2017

Thanks a lot Ksharp, The code worked well, although I need to figure out how it works 🙂

fama · ‎10-04-2017

Hi all, I am working with sas and I have a question. I will try to explain the question properly: I really appreciate your help and suggestions. There is a variable in my table that have 5 phases for each observation. Some of the observations such as OBS 1 covers all 5 phases, however some of them do not. For instance obs 2 does not cover phases 2 and 4. I want to alter the table and create the phases( all 5 phrases) for all obs with the value of 0. Current tabel wanted table obs Var value obs Var value 1 1 10 1 1 10 1 2 20 1 2 20 1 3 12 1 3 12 1 4 11 1 4 11 1 5 10 1 5 10 2 1 12 2 1 12 2 3 23 2 2 0 2 5 23 2 3 23 2 4 0 2 5 23 3 1 21 3 1 21 3 3 11 3 2 0 3 4 50 3 3 11 3 4 50 3 5 0

fama · ‎06-15-2017

Thanks for your help. it did not work. still shows undesired observations.

fama · ‎06-15-2017

it worked well. really appreciate it. thanks 🙂

fama · ‎06-15-2017

Hi all, I am pretty new in SAS programming and do need your help. thx i have a data set like this ( 5 variabes and too many observations) num a b c d e 1 . 3 4 . . 2 . 5 . 6 . 3 1 2 2 . . 4 2 . . . 4 desired result num a b c d e 1 . 3 4 . . 2 1 2 2 . . Indeed, i want to have just those rows that contain 2 consecutive different values. i do appreciate your help

fama · ‎06-13-2017

Hello This code worked for me as well.Thank you but the problem is that it counted the missing value as well. for instance, for the row like 4 5 4 . it showed 3. how can i modify the code to solve this? thanks a lot

Online Status	Offline
Date Last Visited	‎12-17-2019 01:05 AM

How to find the week of the date

Re: Applyig loop and create a new variable

Re: Applyig loop and create a new variable

Applyig loop and create a new variable

Re: Creating a table using SQL

Re: Creating a table using SQL

Re: Creating a table using SQL

Re: Creating a table using SQL

Re: Creating a table using SQL

Re: Creating a table using SQL

Re: finding consecutive different values across variables

Re: finding consecutive different values across variables

Re: Creating a table using SQL

Re: Creating a table using SQL

Creating a table using SQL

Difference_in_difference model(DID) with matched pair

Difference_in_difference model(DID) with matched pair

Re: Difference-in-difference with different pre - and post - periods

difference in difference model with difference pre and post periods

Difference-in-difference with different pre - and post - periods

if-then

Re: how to balance the number of values of a variable

how to balance the number of values of a variable

Re: finding consecutive different values across variables

Re: finding consecutive different values across variables

finding consecutive different values across variables

Re: count unique variable values across columns (within same row)