About Bal23

Bal23 · ‎04-19-2023

Company: Parexel Company background: Parexel is among the world’s largest clinical research organizations (CROs), providing the full range of Phase I to IV clinical development services to help life-saving treatments reach patients faster. Leveraging the breadth of our clinical, regulatory and therapeutic expertise, our team of more than 21,000 global professionals collaborates with biopharmaceutical leaders, emerging innovators and sites to design and deliver clinical trials with patients in mind, increasing access and participation to make clinical research a care option for anyone, anywhere. Our depth of industry knowledge and strong track record gained over the past 40 years is moving the industry forward and advancing clinical research in healthcare’s most complex areas, while our innovation ecosystem offers the best solutions to make every phase of the clinical trial process more efficient. With the people, insight and focus on operational excellence, we work With HeartTM every day to treat patients with dignity and continuously learn from their experiences, so every trial makes a difference. For more information, visit parexel.com. Contact: Yuwei Zhang Title: Innovative Analytics Director Country: United States Award Category: Curious Thinker Tell us how you are inspired by the work you do? I have always had a natural curiosity to explore and uncover stories from data, which I believe is in my DNA. How has SAS played a part in your journey? When my career was in a downward spiral due to lack of funding, SAS opened a new door for me. Thanks to SAS, I was able to embark on a new path that has brought me new opportunities and allowed me to expand my skillset. SAS has been a game-changer for me, enabling me to continue to growing. What products do you use and how do you use them? I use desktop SAS to analyze survey data and visualize patient journey. What is your greatest lesson learned that you'd like to share with others? Life is full of ups and downs, but it's important to never give up. By persevering through the tough times, you can open new doors and find unexpected opportunities. (Please attachment for more details)

Bal23 · ‎09-11-2018

I tried with "build models". I used a template and am not sure whether the "forest model" is similar to "random forest". From the result on variable important, I don't know why it said "train importance". Is there a place for me to look at "test importance"? And what is "important standard deviation"? One variable has ISD=0, what does it mean? Thank you

Bal23 · ‎09-11-2018

Nice work! Thank you!

Bal23 · ‎09-07-2018

Thank you for your explanation. Please share your code.

Bal23 · ‎09-06-2018

@FalkoSchulz Thank you. Would you please show me how to do it with SAS Viya? I would like to read something in written.

Bal23 · ‎08-14-2018

Sorry I haven't made it clear. I was using enterprise miner and imported data. And i saw some variables were labeled as "rejected" but didn't know why

Bal23 · ‎08-10-2018

I noticed some of variables are marked as rejected but don't know why. From the distribution, they look fine. Can anybody explain? Thank you

Bal23 · ‎07-25-2018

Proc contents data=have; Run; proc means data=have n missing; var _numeric_; run; *there is no missing value for all numerical variables; proc freq data=have; tables listofallcharvariables; run; *by copy and paste the result to an excel file, sort it by the frequency of the value, descending (that is how I get each value that most people have for each variable; actually I notice all variables could be considered as numerical, the only thing is, it has “?” when the data is missing, so when there is “?”, this variable is considered as “char”. Could we convert all character variables to numerical variables and replace “?” to “.”) data want; set have; if chav1="?" then chav1="15.0"; /*15.0 is the value that most people have for this variable, same rule applies below/ if chav2="?" then chav2="1.0"; ... (25 char variables to type with 25 mode values) /*when i tried to type these 25 variables, it takes so much time, that is why I am seeking help*/ run;

Bal23 · ‎07-25-2018

Proc freq data=have; Var listofallchar; Run; data want; set have; if chav1="?" then chav1="15.0"; if chav2="?" then chav2="1.0"; ... (25 char variables to type with 25 mode values) this is the original code but I am tried to type all these char variables with their values. Any advice to use macro or a library? Thank you

Bal23 · ‎11-16-2017

'23','357','abc','apc11' SYMBOLGEN: Macro variable MULTivisit resolves to "apc11 ","apc11 ","357 ","apc11 ","apc11 ","357 ","357 ","apc11 ","23 ","apc11 ","apc11 ","357 ","apc11 ","357 ","apc11 ","239 ","357 ","apc11 ","46 ","46 ","357 ","apc11 ","357 ","apc11 ","305 ","apc11 ","apc11 ","357 ","apc11 ","357 ","357 ","apc11 ","357 ","apc11 ","apc11 ","371 ","apc11 ","357 ","apc11," I compared two datasets generated and they are different. From the log above, you can see, with the macro variable, multivisit, with "into", it generates a list of macro variables, but with "call symputx", it generates duplicates, and you can see, the "," is generated differently

Bal23 · ‎11-13-2017

Thank you. if I need to use two where statements for two variables, should it be: data _NULL_; set lib1.have(where=(multivisit=1)) end=eof; length readmi $500; /* length to hold the full created list */ retain readmi; if _N_ = 1 then readmi = quote(patiend_id); else readmi = catx(',',readmi,quote(patient_id)); if eof then cal symputx('readmi',readmi); data _null_; set lib1.have(where=(multibirth=1)) end=eof; length highrisk $500; retain highrisk; if _N_ = 1 then highrisk= quote(patiend_id); else highrisk= catx(',',highrisk,quote(patient_id)); if eof then cal symputx('highrisk',highrisk); and then to merge these two datasets??

Bal23 · ‎11-13-2017

I am sorry. I notice the code is proc sql noprint; select distinct cats("'",compress(patient_id),"'") into :readmi separated by "," from lib1.have where multivisit = 1; (instead of numerofvisit gt 1) quit;%put &readmi; Or should I use another step to change the code, add the variable, numberofvist and use your code? Or is there one step given the code with the variable multivisit instead of numberofvisit

Bal23 · ‎11-12-2017

Data want; Set sashelp.class; CALL SYMPUT('name'||right(PUT(1, 3.)), '-'); CALL SYMPUT('name'||right(PUT(1, 15.)), '-'); run; Is it like that? Would you please correct if it is wrong? Thank you

Bal23 · ‎11-12-2017

proc sql noprint; select distinct cats("'",compress(patient_id),"'") into :readmi separated by "," from lib1.have where numberofvisit gt 1; quit; I want to learn more about "CALL SYMPUTX":, so I guess it is a good idea to replace "into" with "call symputx". Any advice how to do that? Thank you

Bal23 · ‎11-01-2017

Thank you. Would you please provide sample code?

Online Status	Offline
Date Last Visited	‎05-01-2023 12:04 PM

2023 Customer Awards: Parexel - Curious Thinker

build models

Re: Atlantic hurricanes - (United) States at risk

Re: Atlantic hurricanes - (United) States at risk

Re: Atlantic hurricanes - (United) States at risk

Re: What are criteria to reject a variable?

What are criteria to reject a variable?

Re: how can i replace all missing values of all char variables in a da...

how can i replace all missing values of all char variables in a data s...

Re: how to replace into with "symptux"

Re: how to replace those numbers with macro or do loop

Re: Can "let id2=1233 " be replaced with "let id2 in ("1233","1234&quo

Re: Can "let id2=1233 " be replaced with "let id2 in ("1233","1234&amp

Re: how do I replace numbers with do loop macro

Re: how do I replace numbers with do loop macro

2023 Customer Awards: Parexel - Curious Thinker

Re: how to replace those numbers with macro or do loop

Re: how to count the frequency of variables that I have generated

2023 Customer Awards: Parexel - Curious Thinker

build models

Re: Atlantic hurricanes - (United) States at risk

Re: Atlantic hurricanes - (United) States at risk

Re: Atlantic hurricanes - (United) States at risk

Re: What are criteria to reject a variable?

What are criteria to reject a variable?

Re: how can i replace all missing values of all char variables in a da...

how can i replace all missing values of all char variables in a data s...

Re: how to replace into with "symptux"

Re: how to replace into with "symptux"

Re: how to replace into with "symptux"

Re: how to replace into with "symptux"

how to replace into with "symptux"

Re: mfile error