stat_sas Tracker

Re: Averaging count by two variables

stat_sas — Sun, 24 Feb 2019 22:50:24 GMT

Hi,

How about using sql?

proc sql;
select id,year(test_date) as year, avg(test_value) as avg_test_value format=8.2
from have
group by id,calculated year;
quit;

Re: How do I Bootstrap a Custom-Made Statistic??

stat_sas — Sat, 23 Feb 2019 15:32:06 GMT

Hi,

Try this

data want;
if _n_=1 then set SRM;
set sample;
run;

Re: Extracting date, month, year and time from a datetime variable

stat_sas — Sun, 17 Feb 2019 16:15:43 GMT

Hi,

Something like this?

data want;
set date;
year = substr(date,length(date)-3);
run;

Re: How do I solve the errors?

stat_sas — Sat, 16 Feb 2019 03:41:26 GMT

Hi,

Try this

proc tabulate data=clinic.admit7;
 class team;
var startweight endweight;
table team,(startweight endweight)*mean;
run;

Re: t-test after regression by year

stat_sas — Sun, 06 May 2018 23:56:36 GMT

Hi,

Check frequency distribution of variable g before t-test.

Re: Shapiro Wilk Test and ANOVA

stat_sas — Sun, 06 May 2018 21:52:05 GMT

Hi,

This provides a decision boundary to decide whether a variable is normally distributed or not using shapiro wilk based on probability of observing shapiro statistic under the null hypothesis. Same is true for ANOVA which is used to compare means of a continuous variable across different levels of a classification variable.

Re: Give the Discount to the Last column value

stat_sas — Mon, 19 Mar 2018 19:43:15 GMT

Does this work with your initial data set?

Re: Give the Discount to the Last column value

stat_sas — Mon, 19 Mar 2018 16:29:43 GMT

Hi,

Not sure, seems like you are trying to create a variable based on 20% of last populated variable value. Please try this.

data want(drop=i);
set have;
array m(*) _numeric_;
do i=1 to dim(m);
if m(i)>. then Apr=0.2*m(i);
end;
run;

Re: using proc standardize to put the missing value to zero

stat_sas — Tue, 06 Mar 2018 19:38:39 GMT

Hi,

Please try this

proc stdize data=Dataset1(drop=var12) reponly out=dataset2 missing=0;
run;

Re: Why Proc SQL left join output duplicates values?

stat_sas — Sat, 03 Mar 2018 17:58:50 GMT

For a single variable this is not a cross tab. This will be a frequency distribution of the variable id. Try this to get the freq distribution of variable id in a data set.

proc freq data=eq;
tables id;
where z ne . ;
ods output OneWayFreqs=OneWayFreqs;
run;

Re: Why Proc SQL left join output duplicates values?

stat_sas — Sat, 03 Mar 2018 17:43:29 GMT

Hi,

This is because your proc freq syntax is not creating a cross tab. In order to get a cross tabulation in a data set then you have to generate a cross tab. Please try this to see the output data set

proc freq data=eq;
tables id*y;
where z ne . ;
ods output CrossTabFreqs=CrossTabFreqs;
run;

proc print data = CrossTabFreqs;

run;

Re: Missing value

stat_sas — Sun, 04 Feb 2018 03:25:28 GMT

Hi,

I am glad you have the solution. I am also learning from @Reeza's posts

Re: Getting summary statistics without procfreq

stat_sas — Sun, 04 Feb 2018 03:17:40 GMT

Hi,

Something like this may produce the desired output.

data have;
input colx coly colz;
datalines;
0 1 0
0 1 1
0 1 0
;

data want(keep=name value);
set have;
array v(*) col:;
do i = 1 to dim(v);
name=vname(v(i));
value=v(i);
output;
end;
run;

proc sql;
select name,value,count(*) as count from want
group by name, value;
quit;

Re: Missing value

stat_sas — Sat, 03 Feb 2018 19:51:53 GMT

Hi,

Missing values can be replaced with various statistics using proc stdize. Below is an example replacing missing values with median.

Defining a cap would be based on your analysis. You can flag variables containing a certain percentage of missing values for imputation.

proc stdize data=have reponly method=median out=imputed;
var a b c; /* Assuming a, b and c are 3 numeric variables */
run;

Re: Run Regression using data in only specific rows

stat_sas — Sat, 03 Feb 2018 18:57:54 GMT

Hi,

Something like this? I am using a sample data set and you can try on the same pattern on your data set.

data have ;
input var1-var4 ;
n = _n_;
cards;
0.5 1 1.2 0.4
0.9 1 1.5 0.2
0.7 1 1.1 0.3
1 1 1 1
3 1 3 1
4 1 6 7
;
proc reg data=have(where = (n>3));
model var1=var2;
quit;

Re: How to Predict Cluster Group of New Observations

stat_sas — Sat, 03 Feb 2018 01:28:05 GMT

Hi,

This can be used but you can predict cluster membership of new observation based on it's distance from the closest cluster center..

Re: Removing a variable conditionally

stat_sas — Sun, 14 Jan 2018 18:26:47 GMT

Hi,

If you are comfortable with some statistical stuff then try this.

proc means data=have stackods var;
ods output summary=stats;
run;

proc sql;
select Variable into :drop_vars from stats
where Var=0;
quit;

data want;
set have(drop=&drop_vars);
run;

Re: Count the number of individuals with the same characteristics

stat_sas — Sun, 14 Jan 2018 17:39:11 GMT

Hi,

Something like this?

proc sql;

select *,count(*) as Count from have

group by name, c1,c2,c3;

quit;

Re: create summary percentage tables by subsets of one variables.

stat_sas — Fri, 12 Jan 2018 04:00:38 GMT

Hi,

Please try this.

proc freq data=have order=data;
table sex*age/norow nocum nofreq nopercent ;
run;

Re: fill missing values with known non-missing values

stat_sas — Thu, 04 Jan 2018 06:10:22 GMT

Hi,

Please try this.

proc sql;
create table want as
select ID, company, max(variable) as variable from have
group by id;
quit;