About fieldsa83

fieldsa83 · ‎01-09-2019

Right now I'm doing a (weighted) proc means by sex then doing a data step to subract women's avg from men's. There's also a few redundant steps. I'd like to try and do it in 1 step using maybe proc tabulate? Not sure if you have any advice. thanks!

fieldsa83 · ‎10-31-2018

I am trying to get several files that have the same layout in, but it will only keep data from the last file. (note separate folders and file extensions) Cannot figure it out! data myfile; infile "/microdata/file1.prn" lrecl=430 missover; infile "/microdata/otherfolder/file2.txt" lrecl=430 missover; infile "/microdata/anotherfolder/file3.txt" lrecl=430 missover; @119 AGE 3. /* Age of respondent */ @122 SEX $1. /* Sex of respondent. */ run;

fieldsa83 · ‎01-26-2018

I have HRLYEARN which is infiled as 6.2 So 14.65 but I would like to convert it to an 8-character variable with no decimals ie: '001465' Been trying for way too long at this point but I can't get it to work.

fieldsa83 · ‎01-09-2018

Also I completely messed up my styles trying to do this before. Is there a way to reset them all to default? I think I overwrote HTMLBLUE.

fieldsa83 · ‎01-09-2018

If I make a proc tabulate and then in the Results tab Send to Excel, the excel file is perfect! When I do it with ODS excel it is not as neatly formatted. Is there an option to make the ODS excel for proc tabulate exactly like the "Send to Excel"?

fieldsa83 · ‎08-09-2017

I can do this for difference in weighted frequencies by making the previous month's employment variable negative (-1) and the current month's employment variable positive (+1), which produces the net sample-to-sample change in the variable "employed", as well as the CV. But I don't know how to do it for ratios (for example the total rate of employment). data output.newcombined ; set output.combined; if employed=1; if sampledate in (previousmonth) then changeemployed= -1; if sampledate in (currentmonth) then changeemployed= 1; run; proc surveymeans data=output.newcombined varmethod=brr clm nobs mean median CV cvwt SUMWGT Sum CVSum CLSum alpha=0.32; var changeemployed; weight finalwt ; repweights bw1-bw1000 ; run ;

fieldsa83 · ‎07-20-2017

Using longtidunal monthly sample data. I can get the coefficient for total frequency in Month1 and Month2, but the change of the frequency between the two months has high correlation and therefore the variance of the CHANGE is not equal to the upper and lower bounds of the monthly estimates. How can I calculate the variance of the month-to-month change using bootstraps and proc surveyfreq or surveymeans?

fieldsa83 · ‎06-19-2017

Can you save the results output to a libname or something?

fieldsa83 · ‎06-09-2017

I'm trying to recode age into groups but this is not working (just takes the first number in the bracket, from what I can tell) data new; set have; if age in (15-24) then agegroup=1; else if age in (25-54) then agegroup=2; else if age >= 55 then agegroup=3; run; What is the proper way to do this? Edit: Also I know one can do it the way below, but it is very tedious, especially when there are more than 3 values being made. I'm looking for something easier, with ranges: IF 15 <= age_tabs <= 24 then agegroup_main = 1; else if 25 <= age_tabs <= 54 then agegroup_main =2; else if age_tabs >= 55 then agegroup_main =3; else agegroup_main = .

fieldsa83 · ‎06-07-2017

I have a variable for hourly earnings which respondents can answer with accuracy to the penny. So the mean is like $27, but toward the bottom there is so much small variation in reporting, so it has one person at $11.61 one person at $11.63 two people at $11.67, etc.. but when you get higher there's just clumps of people at $15.00 and $25.00. So if I graph it, the chart has many more values at the low end and it skews the chart. Is there a way to automatically recode them to all be in clumps increasing by $0.50 or something (without manually recoding hundreds of ranges)?

fieldsa83 · ‎05-26-2017

Yes, I tried doing (N/12) but that didn't work. Is there a way to do it in PROC TABULATE?

fieldsa83 · ‎05-26-2017

OK, this is great thanks; it appears to work for the most part. However, this does have a limitarion which I have observed: " a FREQ variable value is missing or is less than 1 does not use that observation to calculate statistics no alternative " For the monthly data, this is fine. But for annual averages, I've been dividing the personweight by 12, which has been working. However, for many cases this results in an annualweight of less than 1 so they appear to be excluded, and it is lowering the N by quite a bit. Any way to deak with this?

fieldsa83 · ‎05-26-2017

Perhaps it is my inexperience with different types of weights. The data I'm using is from a sample survey, and each respondent has a weight that is a proportion of the target population. So here is an example of the data structure and where the weight works with sumwgt but not with pctsum: data new; input year personid $ province $ personweight; datalines; 2016 Person1 Ontario 10 2016 Person2 Ontario 15 2016 Person3 Ontario 15 2016 Person4 Ontario 5 2016 Person5 Ontario 15 2016 Person6 Quebec 10 2016 Person7 Quebec 10 2016 Person8 Quebec 5 2016 Person9 Quebec 10 2016 Person10 Quebec 5 ;run; proc tabulate data=new; class year province; weight personweight; table province,year*personweight*(sumwgt pctsum); Title "Proper sumwgt but incorrect pctcum"; run;title;

fieldsa83 · ‎05-25-2017

Sorry I'm completely lost. If i delete the WEIGHT line, and instead put VAR ANNUALWT it actually works 100%. Is this what you're recommending--just get rid of the WEIGHT line altogether??

fieldsa83 · ‎05-25-2017

After trying a few options, I have to use SUMWGT instead of SUM (otherwise the results are completely off). The PCTSUM seems to use the 'completely off' numbers from SUM. So it's almost like I need a PCTSUMWGT (which doesn't work--I tried!).

Online Status	Offline
Date Last Visited	‎01-09-2019 08:48 AM

Calculate wage gap in one step

Reading in multiple text files (with different folders and file extens...

Convert numeric with decimal to character with leading zeros

Re: OSD Excel make style like "Results" -> "Send to Excel"

OSD Excel make style like "Results" -> "Send to Excel"

Calculate difference in ratio/proportions between two survey samples u...

Calculate variance of month-to-month change using surveyfreq or survey...

Is there a way to run proc tabulate on base SAS but view the results i...

Recode using ranges in data step?

What is it called when variable response values are unequally distribu...

Re: Convert numeric with decimal to character with leading zeros

Re: ODS Excelxp PROC TABULATE multiple sheets

Re: How do you manage many format value labels?

Re: How do you manage many format value labels?

Re: Find the maximum number within a subset of a column

How to efficiently manage large set of value format labels, and only a...

Re: Easiest way to import geography boundary files?

Using numeric variable name in macro (from transposed, using dates)

Calculate wage gap in one step

Reading in multiple text files (with different folders and file extens...

Convert numeric with decimal to character with leading zeros

Re: OSD Excel make style like "Results" -> "Send to Excel"

OSD Excel make style like "Results" -> "Send to Excel"

Calculate difference in ratio/proportions between two survey samples u...

Calculate variance of month-to-month change using surveyfreq or survey...

Is there a way to run proc tabulate on base SAS but view the results i...

Recode using ranges in data step?

What is it called when variable response values are unequally distribu...

Re: Am I going crazy? Percentages in PROC TABULATE are wrong?

Re: Am I going crazy? Percentages in PROC TABULATE are wrong?

Re: Am I going crazy? Percentages in PROC TABULATE are wrong?

Re: Am I going crazy? Percentages in PROC TABULATE are wrong?

Re: Am I going crazy? Percentages in PROC TABULATE are wrong?