I am trying to develop a map of the state of Oklahoma zip codes that includes color coding to identify how many physician types are located in particular zip codes. I have attached a sample dataset of count of physician types and the corresponding zip codes for the state of Oklahoma. There are some zip codes that are not in Oklahoma, but I planned to exclude them by only keep zip codes where the state = Oklahoma.- I have been having trouble creating the appropriate files to create the exact map I am needing. The below code is what I have written so far, but I know that it is incorrect. I appreciate any help that can be given. Thank you. proc sort data=zipdata2; by zip; run; data temp (keep = zip count x y city state); merge zipdata2 sashelp.zipcode; by zip; run; data temp2; set temp; if (count ne . and x NE . and y NE .) then do;       x=atan(1)/45 * x *-1;       y=atan(1)/45 * y;       output;     end; /* put out a message for bad/missing zipcodes */ else if (count ne . and x=.) then do;      put "WARNING: Zipcode " zip " wasn't located.";     end; run; data all; set maps.states (where=(40)) temp2; run; proc gmap data=temp2 map=temp2; id state zip; choro count /anno=temp2; run; quit; ... View more

I am trying to determine if the proportion of Males over the time period of 2005 to 2010 changes significantly. Below is a breakdown of the proportions of gender over the years time period. I am having issues determining the best process to use to conclude if there is a significant change over time in the proportion of Males for my study. Thank you for any help you can provide. I FIRST CREATED A DATASET FROM THE PROC FREQ OUTPUT proc freq data=demographics; tables gender/out=gender noprint; by year; run; PERFORM A TTEST TO DETERMINE IF YEAR PROPORTIONS OF MALES DIFFER - IS THIS CORRECT? proc ttest data=gender; var percent; where gender = "M"; run; PERFORM A GLM MODELING YEAR AS MY OUTCOME - IS THIS CORRECT? proc glm data=gender; model year=percent; where gender = "M"; run; year Gender Frequency Percent of Total Count Frequency 2005 F 17248 48.6902 2005 M 18176 51.3098 2006 F 16791 49.2968 2006 M 17270 50.7032 2007 F 17027 49.6356 2007 M 17277 50.3644 2008 F 17480 49.3409 2008 M 17947 50.6591 2009 F 19291 49.2733 2009 M 19860 50.7267 2010 F 22624 49.2619 2010 M 23302 50.7381 ... View more

Below is the SAS code I have been using to run a macro of the series of data "psych_date_i". I have another date "med_date_i" that I am needing to compare each of the psych_date_i readings to. I am trying to see how many days there are between psych visits and med visits in my dataset. There are a total of 45 psych_date and 26 med_date. The macro below currently has to be run for each of the individual med_date_i dates. I do not know if there another way to do what I am doing in less datasteps by writing another macro. I am new to using macros so I am still learning of the capabilities with them. Thank you for any help you can give,. %macro med18; %do i = 1 %to 45 ; data med_psych&i; set med_psych_visits; num_day_m18_p&i = (med_date_18) - (psych_date_&i); keep mrn num_day_m18_p&i; run; %end; data med_18; merge %do i=1 %to 45; med_psych&i %end;; run; %mend; %med18; ... View more

The attached boxplot looks great, other than the fact that I have a ton of white space. I wamt wanting to make the width of the graph smaller or the width of the box plots themsevles larger. I have been trying to do this using bwidth option, but with no luck. I am needing to put this plot on a poster, but the grash produced is difficult to read. Thank you for any help you can give. Below is the SAS code used to create the box plot. proc boxplot data=resident; goptions ftext=CENTX; symbol value = dot color=red; plot percent*time/ cboxfill = ywh haxis = axis1 vaxis=axis2 ; run; ... View more

I have survey data that is unweighted and I am needing to create weights for the analysis. Unfortunately, my experience with using weighted data, is using a weighted variable that was already created and in the dataset prior to me receiving it. I have been searching for references on the how to properly weight data. I perhaps am not searching for the right subject title or something of the sort. Any advice, references or materials that you could provide would be most helpful. Thank you. The data I am looking at is collected from various day cares in the state. We have a SES indicator, urban/rural variable, gender, age, race, height, weight, city, county and day care center. ... View more

I start out with a dataset containg the following variables HPV1          HPV2          HPV3          HPV4 1                   2               1                    2 1                    2               1                    2 2                    1               1                   1 2                    1               1                    2 What I want to create is a dataset that looks as follows HPV          Percent 1          Percent 2          total N HPV1          50                    50                         4 HPV2          50                     50                         4 HPV3          100                     0                          4 HPV4          25                         75                     4         I am able to get the percentages I want using proc freq, but I cannot figure out how to create a dataset that contains the data the way I need it organized. I typically output all the individual proc freq for HPV1, HPV2, HPV3 and HPV4 then manually cut and paste and format the data the way I need, but I figured there was probably a way to do this all in SAS. Thank you for any help you can provide. HyunJee ... View more