hi,
My name is Chang. I have run a linear regression on the relationship between a single dependent and several predictors. I have saved the output as a html. As shown in this output, this analysis produced missing values from some source variables, such as day_temp_diff in type I SS, type III SS and in the parameter estimate table. Can any one please advice on how to annotate the missing values? My gut feeling is that these variables should be removed from my linear model. But I would like to know why there are missing values there. Any comments will be highly appreciated. My codes as below. There are no error message from them. Tassui
%let suffix1= ED;
proc sort data= ED_wide_b out= ED_wide_c;
by day_type_cat;
run;
proc glm data= ED_wide_c;
class day_type_cat;
model day_EDvolume= day_type_cat day_high_temp day_low_temp day_temp_diff day_mean_temp diff_meanDayTemp diff_meanDayRH day_RH_percen day_RH_diff day_high_RH/ solution;
ods output ParameterEstimates= _reg01_dPara_&suffix1.;
ods output NObs= _reg02_dNum_&suffix1.;
ods output FitStatistics= _reg03_dRsq_&suffix1.;
run;
Have you run any diagnostics on the data such as Proc freq or univariate for the variables in question?
Also, if day_temp_diff = day_high_temp - day_low_temp then since it is determined by two other variables it likely isn't going to contribute anything to the model.
Don't miss out on SAS Innovate - Register now for the FREE Livestream!
Can't make it to Vegas? No problem! Watch our general sessions LIVE or on-demand starting April 17th. Hear from SAS execs, best-selling author Adam Grant, Hot Ones host Sean Evans, top tech journalist Kara Swisher, AI expert Cassie Kozyrkov, and the mind-blowing dance crew iLuminate! Plus, get access to over 20 breakout sessions.
Learn how use the CAT functions in SAS to join values from multiple variables into a single value.
Find more tutorials on the SAS Users YouTube channel.