About Siddharth123

Siddharth123 · ‎07-24-2016

Ok, I figured out, it's not complicated at all! just using a simple merge : data C; merge A B; run; KR SK

Siddharth123 · ‎07-24-2016

Hello All, I am wondering if it is possible to solve this problem in SAS. I have two datasets - A & B both having same observations. I want to add all columns from Data B to Data A (given there is no matching ID in two datasets): Data A: var1 var2 1 2 3 4 5 6 Data B: var3: 7 8 9 Data C: var1 var2 var3 1 2 7 3 4 8 5 6 9 Is this possible to do in SAS? I thought of using Proc IML? Is there any SAS Datset procedure to do this? KR SK

Siddharth123 · ‎07-23-2016

Hi All, I am stuck in a problem of creating a single column data (B) which depends on the max value in each row of original data (A). Data A is - Data A: v1 v2 v3 v4 1 2 3 4 2 3 4 1 6 7 2 4 Data B should take the max from each row of Data A and then create the corresponding column as value in Data B: Col v4 v3 v2 Is this possible to do? KR SK

Siddharth123 · ‎07-13-2016

I have a data test and I am trying to find # months it takes for an ID to change status from 1/0. For e.g. for ID= XX, I want to create M1,M2,M3,......M12 variables where M1 = # times gap = 1 in status change from last status M2 = # times gap = 2 in status change from last status and so on. Please advise. data test; input ID $2. mth1 mth2 mth3 mth4 mth5 mth6 mth7 mth8 mth9 mth10 mth11 mth12; infile datalines; datalines; XX 1 1 0 1 1 1 1 1 0 0 0 1 YY 0 0 0 1 1 1 1 0 1 0 0 0 ZZ 0 0 0 1 1 1 1 0 1 0 0 0 WW 0 0 1 1 0 0 0 0 1 0 0 0 PP 1 1 1 0 0 0 0 1 0 1 1 1 ; PROC PRINT; RUN;

Siddharth123 · ‎06-17-2016

Hello All, I am interested to learn more about the ADAPTIVE REGRESION (MARS) and LOESS. Is this something that can be applied in credit scoring? Kindly guide me with some books that I can read to get a clear understanding of these method. Kind regards Sk

Siddharth123 · ‎04-26-2016

Hi All, I am wondering if anyone has some sophisteicated ideas on generating insights from the toy data attached. What I would like to do is some sort of trend analysis and find out - 1. How many times does the Status change from 1 to 0 and vis-a-vis. The idea is the larger the number the higher the instability. What I was thinking of is to have 2 coumns - for ID 0 and ID 1. For e.g. for ID 1, ID_1 = 1 but ID_0 = 0 as Status = 1 all time, for ID 2 it would be 2 for Status 1 and 1 for Status 0 as Status 1 was twice but 0 only once. 2. How many months did the Status remain unchanged before it got changed. For example, for ID 2, Status = 0 for May15 - Sep15 (5 months = 5) before it changes to 1. Any more ideas welcome. Kind regards SK

Siddharth123 · ‎04-17-2016

Hi All, I figured out that I need to use INDEX rather than INDEXC to solve this problem. Kind regards SK

Siddharth123 · ‎04-17-2016

Hi All, I am not getting expected results when using INDEXC (please see code below). I would expect all records in the dataset UnSure rather than in For_Sure - DATA TEST; INPUT Name $50.; INFILE DATALINES; DATALINES; DREFT ESTATES LTD POTTERSLANE LTD ; RUN; DATA For_Sure UnSure; SET TEST; IF indexc(Name, "GOVERNMENT") > 0 OR indexc(Name, "COLLEGE") > 0 then OUTPUT For_Sure; ELSE OUTPUT UnSure; RUN; Any help will be greatly appreciated. Thank you SK

Siddharth123 · ‎04-05-2016

Hi All, Could anyone help me in this problem. I have a SAS Dataset created as follows - Data test; input Id a b c; infile datalines; datalines; 123 20 30 50 124 1 5 8 ; run; I want to create a new column, say 'Total', which gives me a total count for the columns a, b, c. For example for the Id 124 in table above the SAS output data should give me - Id Total 124 a 124 b 124 b 124 b 124 b 124 b 124 c 124 c 124 c 124 c 124 c 124 c 124 c 124 c Any help will be much appreciated. Kind regards SK

Siddharth123 · ‎10-15-2015

Hi Patrick, Sorry that I did not mention that the Start & End Dates get populated whenever there is a break in the actual "Date" column that is why we should have 4 entries for the Id 1. Kind regards Siddharth

Siddharth123 · ‎10-15-2015

Thanks Patrick. This works but not perfectly! The solution gives me 2 entries for Start & End date for the id. What I am trying is to have the values popualted for "???" in table below. Soin final output, Id 1 should have 4 rows (but the solution you have will give me 2 rows!!) - id Date Flag start_dt end_dt 1 30/04/2013 . . 1 31/05/2013 . . 1 30/06/2013 . . 1 31/07/2013 . . 1 31/08/2013 . . 1 31/01/2013 Y 31/01/2013 . 1 28/02/2013 Y . . 1 31/03/2013 Y . ??? 1 30/09/2013 Y . ??? 1 31/10/2013 Y . . 1 30/11/2013 Y . . 1 31/12/2013 Y . 31/12/2013

Siddharth123 · ‎10-15-2015

Hello Friends, I am stuck on one problem and request for some help. Please see table below - Id Date Flag Start End 1 31/01/2013 Y 1 28/02/2013 Y 1 31/03/2013 Y 1 30/04/2013 1 31/05/2013 1 30/06/2013 1 31/07/2013 1 31/08/2013 1 30/09/2013 Y 1 31/10/2013 Y 1 30/11/2013 Y 1 31/12/2013 Y What I want to do is to create two new fields - Start_Date & End_Date which gets populated only when the Flag = "Y" something like the table below - Id Date Flag Start End 1 31/01/2013 Y 31/01/2013 1 31/03/2013 Y 31/03/2013 1 30/09/2013 Y 30/09/2013 1 31/12/2013 Y 31/12/2013 Any help will be geratly appreciated. Regards Siddharth

Siddharth123 · ‎07-31-2015

Thanks Miguel, this is really helpful. I do have Naeem Siddiqui book and familiar with vintage analysis. I understand your ideas

Siddharth123 · ‎07-25-2015

Hello All, I am running PROC LOGISTIC with dependant variable as if the customer defualted in the next 15 months. I would now like to calibrate it to 12 month PD. Could you kindly advise me how can I do it, are there any discussion forums on this or any paper that I can refer to? Kind regards Sid

Siddharth123 · ‎09-08-2014

hello Stat@stat, thank you for the help. Is there an option in SAS which puts the percntile information in the _FREQ_ column? I mean when I use - proc means data= SASHelp.Citiday n nmiss mean std min max p1 p5 p10 p25 p50 p75 p90 p95 p99; var _numeric_; ods output =test (drop=label:) ; run; This doesnt produce pernctile information (only - N, NMISS, MAX,MIN,MEAN,STD). But if I use - proc means data= SASHelp.Citiday n nmiss mean std min max p1 p5 p10 p25 p50 p75 p90 p95 p99; var _numeric_; ods output summary=_stat_temppretty(drop=label:) ; run; The problem is that even if I do get percentile the summary information gets added as a suffix to the variable name. For example, if I have a variable AMOUNT, I get AMOUNT_N, AMOUNT_NMISS, AMOUNT_P1....so on. So I cant even use a proc transpose here. Basically, my end goal is to have all missing data, percntile, min, max, median for original variables. @ksharp - the autoname does not work here. Sk

Online Status	Offline
Date Last Visited	‎11-02-2020 09:53 AM

SAS Enterprise Miner 14.1 Decision Tree node is not using all records ...

Re: SAS Base

SAS Base

Base SAS

Re: SAS Base

Re: SAS Base

Re: SAS Base

SAS Base

hpgenselect for continuous target variable

Proc Sql Cumulative Percent

Re: SAS Base

Re: SAS Base

Re: Proc Sql Cumulative Percent

Re: Proc Sql Cumulative Percent

Re: Proc Transpose

Re: Adding a column

Adding a column

Creating a column based on max values of row

Array help

Books on ADAPTIVEREG and LOESS as applied to Credit Risk

ARRAY

Re: INDEXC

INDEXC

Creating Duplicating Records based on column values

Re: Create Loop

Re: Create Loop

Create Loop

Re: Calibrating 15 month Probability of Default (PD) to 12 month PD

Calibrating 15 month Probability of Default (PD) to 12 month PD

Re: Proc means