cancel
Turn on suggestions
Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.
Showing results for 
Search instead for 
Did you mean: 
CalebN
‎06-26-2019
  • 10 Posts
  • 1 Likes Given
  • 0 Solutions
  • 0 Likes Received

Re: Data manipulation - do loops

by Calcite | Level 5 in New SAS User
‎06-26-2019 04:03 PM
‎06-26-2019 04:03 PM
This code works for me! Thanks for your help! ... View more

Re: Data manipulation - do loops

by Calcite | Level 5 in New SAS User
‎06-26-2019 04:02 PM
‎06-26-2019 04:02 PM
Thanks for your reply. Not sure why the file is showing you only 100 days but the .csv I uploaded has a few years with 365 days for each year. When I ran your code, frost did = 1 on the day of the first frost in 1989 but then frost remained 1 for the rest of the days in following years. Not sure why. Thanks ... View more

Re: Data manipulation - do loops

by Calcite | Level 5 in New SAS User
‎06-26-2019 02:02 PM
‎06-26-2019 02:02 PM
I think that code would work for one year however, when the next year starts then frost would not equal zero. How can we make the code "reset" for the next year? ... View more

Re: Data manipulation - do loops

by Calcite | Level 5 in New SAS User
‎06-26-2019 02:00 PM
‎06-26-2019 02:00 PM
Thanks for your responses. I have attached a sample of my data to the original post. I have one temperature observation per day and multiple years. ... View more

Data manipulation - do loops

by Calcite | Level 5 in New SAS User
‎06-26-2019 01:21 PM
‎06-26-2019 01:21 PM
Hello,  I'm doing some data manipulation in SAS 9.4 before further analysis. I have several years of temperature data and want to do further calculations if there has been no killing frost in the fall yet. I wrote the following statements  to make frost =1 on days where the temperature was less than 2 degrees.   if temp<-2 and day>180 then frost=1; else frost=0;   Is there a way to make frost =1 for the rest of the days following the first frost in that year, and then reset for the next year? I was exploring do loops but I'm not sure if that would fit what I'm looking for or not.   Thanks for your help. ... View more

Re: Covariates in Proc GLIMMIX and Lsmeans

by Calcite | Level 5 in Statistical Procedures
‎11-24-2018 11:16 AM
‎11-24-2018 11:16 AM
Thanks for your help, I have some resources at my institution that might be able to help me further.   ... View more

Re: Covariates in Proc GLIMMIX and Lsmeans

by Calcite | Level 5 in Statistical Procedures
‎11-23-2018 05:11 PM
‎11-23-2018 05:11 PM
Sorry, I think I understand what you were saying now. I would like to use either date, or GDD as my covariate, whichever explains more variation. So the code I've tried is  proc glimmix; class rot main till year rep; model NO3=rot|till|year GDD/ddfm=kr; random int Main(rot)/subject=rep; Random year/residual subject=main(rep*rot*till) type=cs; lsmeans rot|till year/pdiff=all lines; run; or  proc glimmix; class rot main till year rep; model NO3=rot|till|year date/ddfm=kr; random int Main(rot)/subject=rep; Random year/residual subject=main(rep*rot*till) type=cs; lsmeans rot|till year/pdiff=all lines; run; Here's a bit more detail on my experimental design since I don't think I was specific enough. Soil NO3 samples were taken from each "MAIN" every four years and there are 2 "MAIN" for each ROT and TILL which are offset by 2 years in a 4 year crop rotation (ROT). This means every 2 years there is a measure of NO3 in every ROT and TILL but the repeated measure is only in every MAIN.  NO3 is in theory supposed to be measured at the same time each year, but is sometimes a bit earlier or later depending on field conditions. DATE is the Julian date of NO3 sampling and GDD is an accumulation of temperature that year up until the sample date. All NO3 values have the same DATE and GDD value for each year. I suspect higher DATE and GDD will result in higher NO3 and would like to account for this using one of these 2 variables.  Hopefully this is more clear. Thanks again. ... View more

Re: Covariates in Proc GLIMMIX and Lsmeans

by Calcite | Level 5 in Statistical Procedures
‎11-23-2018 12:08 PM
‎11-23-2018 12:08 PM
Hello Paige, I am just putting the covaraites in the model statement. I'm not sure if that's correct or not though. I had bolded date which is all I have done to include that covariate. When date or GDD is not included in this code, I get all my lsmeans correctly. I included the output of  Proc Freq for ROT, TILL, GDD, and DATE. DATE has some which have higher frequency because the date was the same for two years. Thanks again! proc glimmix; *output out=second; class rot main till year rep; model NO3=rot|till|year date/ddfm=kr; random int Main(rot)/subject=rep; Random year/residual subject=main(rep*rot*till) type=cs; lsmeans rot|till year/pdiff=all lines; run;   ... View more

Covariates in Proc GLIMMIX and Lsmeans

by Calcite | Level 5 in Statistical Procedures
‎11-23-2018 11:37 AM
‎11-23-2018 11:37 AM
Hello, I am using SAS 9.4 and trying to include covariates in my analysis. See my code below.  My response variable is NO3, my treatment is rot, my subplot is till, and there are repeated measures. I have two covariates I would like to add to the model, GDD and date. When I add one of these covaraites to the model statement, I get the following error. "ERROR: LINES display is not produced for the year effect because p-values are not available for all least-squares means differences."   proc glimmix; class rot main till year rep; model NO3=rot|till|year date/ddfm=kr; random int Main(rot)/subject=rep; Random year/residual subject=main(rep*rot*till) type=cs; lsmeans rot|till year/pdiff=all lines; run; What are some potential causes of this error? Am I entering the covariates in the model correctly? Thanks for your help!   ... View more

Creating multiple sums of a variable with overlapping time periods

by Calcite | Level 5 in SAS Programming
‎01-31-2018 12:35 PM
‎01-31-2018 12:35 PM
Hello, I'm new to sas using the university edition  and having trouble getting multiple sums of a variable. I have rainfall data from 1975 to the present with each day a numeric day of the year (365 or 366 if it's a leap year). I want to make sums of many overlapping time periods. See my code below for what I've tried.   data rainfallsummary; set work.import; *this determines leap year; if (mod(year,4)=0 and(mod(year,100) ne 0 or(mod(year,100)=0 and (mod(year,400)=0)))) then leap=1; else leap=0; *may; if ((leap=0) and ((day>=121)and (day<=151)) )then month=5; if ((leap=1) and ((day>=122)and (day<=152)) )then month=5; *june; if ((leap=0) and ((day>=152)and (day<=181)) )then month=6; if ((leap=1) and ((day>=153)and (day<=182)) )then month=6; *july; if ((leap=0) and ((day>=182)and (day<=212)) )then month=7; if ((leap=1) and ((day>=183)and (day<=213)) )then month=7; *august; if ((leap=0) and ((day>=213)and (day<=243)) )then month=8; if ((leap=1) and ((day>=214)and (day<=244)) )then month=8; *june 15 to july 15; *if ((leap=0) and ((day>=166)and (day<=196)) )then month=6.5; *if ((leap=1) and ((day>=167)and (day<=197)) )then month=6.5; run; proc means data=rainfallsummary; class year month; var rain; output out=work.rainTotals sum=sum; run;   I want to be able to get the sum of the rain during days 166 to 196 but this doesn't work with my code since I have more than one "month" for days 166 to 196.  Is there any way to solve this? Thanks! ... View more
Contact Me
Online Status
Offline
Date Last Visited
‎06-26-2019 05:26 PM
Likes given to
View All
Quick links