About orchid_sugar

orchid_sugar · ‎04-16-2024

I have a dataset with labels that I want to export to excel, but the label statement won't turn blue or export the label. 'About SAS 9' indicates I have SAS 9.4 TS Level 1M5, so the label statement should work... putnames doesn't work either. I tried to rename the variable itself, but they contain special characters (e.g. #). How can I export the dataset to excel with labels? proc export data=missingReport outfile="C:location\filename.xlsx" dbms=xlsx label replace; sheet="missingFacilities"; run;

orchid_sugar · ‎11-10-2023

I did my analysis using proc genmod with repeated subject by the organization ID (hierarchical regression). I am trying to create a odds ratio figure like below image where each variable's category is showing: 1) Does below code still work for hierarchical regression? proc logistic data=test plots(only)=oddsratio(logbase=10); class orgID / param=glm; model event(event="1") = homeless pay_cat pls_abbr race_grp HPI_pt_cat HPI_hpl_cat /link=logit clodds=wald; run; 2) How can I make the figure like above? proc logistic doesn't seem to be working

orchid_sugar · ‎11-10-2023

I have a percentile score of how good a hospital is (could be continuous variable, but I categorized it into 5. 0-20%, 21-40%, 41-60%...) and a sensitivity result of how accurately a hospital reports an event (0 to 1, which can also be a percent if x100). I was told since it is not uniformly distributed, we have to use nonparametric analysis, which my graduate program did not go over much. What test would you do for above analysis (for if percentile score of how good a hospital is continuous and categorical)? Can the Wilcoxon rank sum test be used when a variable has 5 categories and another variable continuous? If yes, how can I interpret it? So far the internet is mainly showing 2x2. Can Spearman be used with the above variables?

orchid_sugar · ‎09-12-2023

x is text and y is numeric

orchid_sugar · ‎09-12-2023

I really like the image you posted, but the code didn't work for me: ods graphics on / width=10in height=5in; proc sgplot data=ratio_long; vbox y / category = x group = FacilityType groupdisplay=cluster clusterwidth=1 whiskerattrs=(thickness=0)nooutliers nomean fillattrs=(transparency=0.7) medianattrs=(thickness=5) name='x'; scatter x=x y=y/group=FacilityType2019 groupdisplay=cluster clusterwidth=1 jitter markerattrs=(symbol=CircleFilled size=4) transparency = 0.5; keylegend 'x'/ title = 'Facility Type' position=bottom; yaxis grid values=(0 to 1.1 by 0.1); xaxis display=(nolabel) colorbands=odd; refline 1 / axis=y lineattrs=(pattern=shortdash color=green); run; Adjusting the jitterwidth helped but it is off center for some reason: ods graphics on / width=10in height=5in; proc sgplot data=ratio_long; vbox y / category = x group = FacilityType groupdisplay=cluster whiskerattrs=(thickness=0)nooutliers nomean fillattrs=(transparency=0.7) medianattrs=(thickness=5); scatter x=x y=y /group=FacilityType groupdisplay=cluster jitterwidth=0.2 jitter markerattrs=(symbol=CircleFilled size=4) transparency = 0.5; keylegend / title = 'Facility Type' position=bottom; yaxis grid values=(0 to 1.1 by 0.1); xaxis display=(nolabel); *colorbands=odd; refline 1 / axis=y lineattrs=(pattern=shortdash color=green); run;

orchid_sugar · ‎09-11-2023

Type=DISCRETE unfortunately didn't work. I wish the jitter would look like proc sgpanel: Where would the style statement be under? Example code would be appreciated. Thank you.

orchid_sugar · ‎09-11-2023

How can I make jitter look more within boxplot area on proc sgplot? I can see some data points are going into the other group. Also, is there a way to change the color of boxplot to color blind friendly palette? proc sgplot data=ratio_long; vbox ratio / category = x group = FacilityType whiskerattrs=(thickness=0)nooutliers nomean fillattrs=(transparency=0.7) medianattrs=(thickness=5); scatter x=x y=y/group=FacilityType groupdisplay=cluster jitter markerattrs=(symbol=CircleFilled size=4) transparency = 0.5; keylegend / title = 'Facility Type' position=bottom; yaxis grid values=(0 to 1.1 by 0.1); xaxis display=(nolabel); refline 1 / axis=y lineattrs=(pattern=shortdash color=green); run;

orchid_sugar · ‎07-25-2023

This is my first time using PROC GENMOD or hierarchical regression: proc genmod data=Procedure descending; class asa3lev (ref="1") gender (ref="F") pay_cat (ref="01") pls_abbr (ref="ENG") race_grp (ref="1") orgID; model Event(event="1") = MedAff01 ageAtProc_10 anesthesia01 asa3lev BMI_val30 BMI_val2530 closure01 diabetes01 numBeds01 procDurationMin_10 scope01 swClass01 trauma01 gender homeless pay_cat pls_abbr race_grp HPI_hpl_percentile HPI_pt_percentile /link=logit dist=bin; repeated subject=orgID; run; I got an following error: NOTE: Class levels for some variables were not printed due to excessive size. NOTE: PROC GENMOD is modeling the probability that Event='1'. NOTE: Algorithm converged. WARNING: The generalized Hessian matrix is not positive definite. Iteration will be terminated. ERROR: Error in parameter estimate covariance computation. ERROR: Error in estimation routine. I don't know how to make this work or understand what this error means...

orchid_sugar · ‎07-23-2023

I am trying to merge HPI score based on the zip code. However, it only shows up once instead of applying the score to each row. This code worked for other part of my coding but I am not sure why it's not working for this: [prefinal_missing] orgID hplzip ... 111112 90017 111113 90017 111114 90017 [HPI_hpl] hplzip HPIscore 90017 0.026 Code: proc sort data=prefinal_missing; by hplzip; run; proc sort data=HPI_hpl; by hplzip; run; data test; merge prefinal_missing(in=in1) HPI_hpl; by hplzip; if in1; attrib _all_ label=''; run; What comes out: orgID hplzip HPIscore ... 111112 90017 0.026 111113 90017 . 111114 90017 . What I want: orgID hplzip HPIscore ... 111112 90017 0.026 111113 90017 0.026 111114 90017 0.026

orchid_sugar · ‎01-24-2023

Yes, I meant as values. I apologize for using the wrong term.

orchid_sugar · ‎01-23-2023

I have a column where all the variables have suffixes (for example, variable name: procCode. variable options: x_ratio, y_ratio, z_ratio, a_ratio...). I want the variables to be x, y, z, a and remove the suffix '_ratio'. Is there a method where I don't have to do rename = (x_ratio=x y_ratio=y .....)?

orchid_sugar · ‎10-07-2022

Please see attached as an example: *patient_id is not unique, so patient 1 from facility 123 is not the same as the patient 1 from facility 234.

orchid_sugar · ‎10-07-2022

Dataset A has total of 51 numeric and character variables: facility_ID (num), procedure_code0 - procedure_code 24 (char), procedure_date0 - procedure_date24 (num). Dataset B has only 2 character variables: code (which is same as procedure_code0... not every value in procedure_code0 etc is in the dataset B 'code') and another_code (I need to translate to). My goal is to extract the procedure_code and procedure_date based on the dataset B, so the final dataset will only have 3 columns/variables: facility ID, procedure_code_extracted, procedure_date_extracted. My pseudocode came out as below: DATA extracted; SET dataset A; ARRAY procedure_Code (25) procedure_code0 - procedure_code 24; DO i = 1 To 25; IF procedure_Code(i) = database B's code THEN procedure_code_extracted = procedureCode(i) also get the location of that matched procedureCode(i) [row, column] use that location to find procedure_date from procedure_date0 - procedure_date24 and input under procedure_date_extracted if there is several matches in a row, make a new line for the subsequent match and repeat End; I am not sure how to make this logic into actual running SAS code.

Online Status	Offline
Date Last Visited	‎04-23-2024 03:08 AM

proc export with labels, but not working with the label statement

How to create an odds ratio figure with hierarchical regression

What test to use for checking the association between a percentile and...

Re: How to make jitter look more within boxplot area on proc sgplot

Re: How to make jitter look more within boxplot area on proc sgplot

Re: How to make jitter look more within boxplot area on proc sgplot

How to make jitter look more within boxplot area on proc sgplot

PROC GENMOD Error Interpretation

One to Many Merge Issue

Re: How to remove suffix from variables in a column?

Re: How to make jitter look more within boxplot area on proc sgplot

Re: Extracting data from several columns to a column using separate da...

Re: Extracting data from several columns to a column using separate da...

proc export with labels, but not working with the label statement

How to create an odds ratio figure with hierarchical regression

What test to use for checking the association between a percentile and...

Re: How to make jitter look more within boxplot area on proc sgplot

Re: How to make jitter look more within boxplot area on proc sgplot

Re: How to make jitter look more within boxplot area on proc sgplot

How to make jitter look more within boxplot area on proc sgplot

PROC GENMOD Error Interpretation

One to Many Merge Issue

Re: How to remove suffix from variables in a column?

How to remove suffix from variables in a column?

Re: Extracting data from several columns to a column using separate da...

Extracting data from several columns to a column using separate datase...