I am trying to run a mediation model using SAS Studio on Demand for Academic with three treatments repeatedly measured at four different time points.   The IV and DV are latent variables-so each contains four scaled items.   I also have a few control variables.   So, for example:   I have an IV (5 items) and DV (4 items).   I repeatedly measured both IV and DV under three different treatments or conditions four different times.   So, it would look like this:   IVCondition1/DVlCondition1 time0, IVCondition1/Condition1 time1, IVCondition1/DVCondition1 time2, IVCondition1/DVCondition1 time3                                               IVCondition2/DVlCondition2 time0, IVCondition2/Condition2 time1, IVCondition2/DVCondition2 time2, IVCondition2/DVCondition2 time3   IVCondition1/DVlCondition3 time0, IVCondition1/Condition3 time1, IVCondition1/DVCondition3 time2, IVCondition3/DVCondition3 time3   I also have control variables which I measure once.   proc calis data=work.import1 method=ml; /* Define latent variables for IV and DV */ Define: IV Latent_IV1 Latent_IV2 Latent_IV3; /* IV with three indicators */ DV Latent_DV1 Latent_DV2 Latent_DV3 Latent_DV4; /* DV with four indicators */ /* Specify measurement model for IV and DV */ model: /* Measurement model for IV */ IV =~ Latent_IV1 Latent_IV2 Latent_IV3; /* Measurement model for DV */ DV =~ Latent_DV1 Latent_DV2 Latent_DV3 Latent_DV4; /* Specify treatment effects at different time points for IV */ path: IV_T0 <-- IV_T1 <-- IV_T2 <-- IV_T3; /* Specify treatment effects at different time points for DV */ path: DV_T0 <-- DV_T1 <-- DV_T2 <-- DV_T3; /* Control variables */ FRLegitimacy1-FRLegitimacy6 UAEnational Incomelevel Educationlevel YearsUAEres; /* Structural equation model specification */ lineqs: /* Include the effect of IV at Time 0 on DV at Time 0 */ DV_T0 = b1*IV_T0; /* Include the effect of IV at Time 1 on DV at Time 1 */ DV_T1 = b2*IV_T1; /* Include the effect of IV at Time 2 on DV at Time 2 */ DV_T2 = b3*IV_T2; /* Include the effect of IV at Time 3 on DV at Time 3 */ DV_T3 = b4*IV_T3; run;   Any help would be greatly appreciated. I also tried calling SAS's customer service to speak with an expert but they were unfortunately useless as they don't offer such help for the studio version. ... View more

Hello,   I have an unbalanced cross sectional data set comprising of 3 years 2014-2016 with 2014 63926 obs 2015 23360 obs and 2016 30682 obs. I'm trying to run a fixed effects model using PROC PANEL but an error keeps appearing that says Not enough observations with non-missing values for model statement Model 1 in cross section ID=100561. I checked this ID number and it was all in order, nothing was missing.   I am using the following code: proc panel data=WORK.IMPORT; id id year; model exportcorr = entage_Z vcage_Z vcsize_z entnatvsize_Z vcedbrank_Z infecentnat_Z corupinentnat_Z vcgdp_Z year2015 year2016 loccorr_Z vcinfec_Z vccorupin_Z /fixone; run; Is there a way to tell SAS to ignore the misisng observations? My friend used the same data set and ran the model I want to run in STATA and it ran just fine. Its just really frustrating. Thanks,   ... View more

Hello,   I'm trying to create dummy variables for companies in my data set. Unfortunately the output is all zeros.   This is my code below:   DATA WORK.IMPORT; SET WORK.IMPORT; IF COMPANY = COKE THEN COKED=1; ELSE COKED = 0; IF COMPANY = KFC THEN KFCD=1; ELSE KFCD = 0; IF COMPANY = PEPSI THEN PEPSID=1; ELSE PEPSID = 0; IF COMPANY = NIKE THEN NIKED=1; ELSE NIKED = 0; IF COMPANY = STARBUCKS THEN STARBUCKSD=1; ELSE STARBUCKSD = 0; IF COMPANY = MCDONALD THEN MCDONALDD=1; ELSE MCDONALDD = 0; IF COMPANY = HARDEES THEN HARDEESD=1; ELSE HARDEESD = 0; RUN;   unfortunately the ouput for the dummy variables is all 0, so if the company is coke the output is also 0 and not 1   I don't understand what is wrong, please help.   Thanks ... View more