About SASNovice2014

SASNovice2014 · ‎07-24-2018

Hello, I have an unbalanced panel dataset across 10 years as follows. Here are my variables: Y= dependent variable x1= predictor x1_2 = predictor (squared) x3 = moderator name time gvkey y x1 x1_2 x3 abc 1 10553 0.95 -0.20 0.04 0.34 abc 2 10553 1.20 abc 3 10553 1.29 -0.45 0.20 0.44 abc 4 10553 1.62 -0.32 0.10 0.23 … xyz 1 7435 1.97 -1.09 1.19 xyz 2 7435 1.86 -0.69 0.48 0.41 xyz 3 7435 1.90 -0.70 0.49 0.42 xyz 4 7435 1.94 -1.90 3.62 2.67 Here's SAS codes to run regression where x3 has been split into high sample: proc panel data=test_xlag ; inst depvar exogenous=( x3_high ) pred=(x1 x1_2) ; model y_high = x3_high x1 x1_2 / gmm twostep maxband=1 time robust ; id gvkey time; run; Here's SAS codes to run regression where x3 has been split into low sample: proc panel data=test_xlag ; inst depvar exogenous=( x3_low ) pred=(x1 x1_2) ; model y_low = x3_low x1 x1_2 / gmm twostep maxband=1 time robust ; id gvkey time; run; Here's SAS codes to run both regressions in a DO LOOP: data test_xlag; do X1 = -3.0 to 0 by 0.1; y_high = 0.136544 + (-0.04991)*X1 + (-0.00773)*X1*X1 ; y_low = 0.152363 + (-0.05342)*X1 + (-0.00836)*X1*X1 ; output; end; run; Let's assume I've created the ANNOTATE dataset and produce the plot in the attached file. The plot is an inverse U-shaped curve. It has 2 parallel curvilinear lines (red curve = depicts regression based on high sample, blue curve = depicts regression based on low sample). In the plot, x axis is range of x1 values, and y axis is range of y values. Here are my questions: (1) How do create a DO LOOP in SAS 9.3 that would allow me to statistically compare the red line to the blue line for x1 ranging from -0.1 to -1.0 at increments of 0.1? How do I test whether the red line is statistically different from the blue line at each specified values of x1? I would need chi-square values and p-values for each set of red/blue comparisons at each of the ten x1 values. (2) How do I generate marginal effects and standard errors for each of blue line and red line at each of the 10 specified x1 values (for a total of 20 values)? What SAS procedure do I use? Below are the STATA codes to generate what I need for (1) and (2). Can someone help me translate these STATA codes into SAS codes? margins, at(x1 = (-0.1 (0.1) -1.0) x3_high=(0 1 )) post margins, coeflegend forvalues i = 1(2)20 { loc j = `i' +1 test _b[`i'._at] = _b[`j'._at] } Thanks in advance!

SASNovice2014 · ‎07-24-2018

Hello, I have an unbalanced panel dataset across 10 years as follows. Here are my variables: Y= dependent variable x1= predictor x1_2 = predictor (squared) x3 = moderator name time gvkey y x1 x1_2 x3 abc 1 10553 0.95 -0.20 0.04 0.34 abc 2 10553 1.20 abc 3 10553 1.29 -0.45 0.20 0.44 abc 4 10553 1.62 -0.32 0.10 0.23 … xyz 1 7435 1.97 -1.09 1.19 xyz 2 7435 1.86 -0.69 0.48 0.41 xyz 3 7435 1.90 -0.70 0.49 0.42 xyz 4 7435 1.94 -1.90 3.62 2.67 Here's SAS codes to run regression where x3 has been split into high sample: proc panel data=test_xlag ; inst depvar exogenous=( x3_high ) pred=(x1 x1_2) ; model y_high = x3_high x1 x1_2 / gmm twostep maxband=1 time robust ; id gvkey time; run; Here's SAS codes to run regression where x3 has been split into low sample: proc panel data=test_xlag ; inst depvar exogenous=( x3_low ) pred=(x1 x1_2) ; model y_low = x3_low x1 x1_2 / gmm twostep maxband=1 time robust ; id gvkey time; run; Here's SAS codes to run both regressions in a DO LOOP: data test_xlag; do X1 = -3.0 to 0 by 0.1; y_high = 0.136544 + (-0.04991)*X1 + (-0.00773)*X1*X1 ; y_low = 0.152363 + (-0.05342)*X1 + (-0.00836)*X1*X1 ; output; end; run; Let's assume I've created the ANNOTATE dataset and produce the plot in the attached file. The plot is an inverse U-shaped curve. It has 2 parallel curvilinear lines (red curve = depicts regression based on high sample, blue curve = depicts regression based on low sample). In the plot, x axis is range of x1 values, and y axis is range of y values. Here are my questions: (1) How do create a DO LOOP in SAS 9.3 that would allow me to statistically compare the red line to the blue line for x1 ranging from -0.1 to -1.0 at increments of 0.1? How do I test whether the red line is statistically different from the blue line at each specified values of x1? I would need chi-square values and p-values for each set of red/blue comparisons at each of the ten x1 values. (2) How do I generate marginal effects and standard errors for each of blue line and red line at each of the 10 specified x1 values (for a total of 20 values)? What SAS procedure do I use? Below are the STATA codes to generate what I need for (1) and (2). Can someone help me translate these STATA codes into SAS codes? margins, at(x1 = (-0.1 (0.1) -1.0) x3_high=(0 1 )) post margins, coeflegend forvalues i = 1(2)20 { loc j = `i' +1 test _b[`i'._at] = _b[`j'._at] } Thanks in advance!

SASNovice2014 · ‎03-08-2015

***Apologies for cross-posting*** Hi, I am interested in running the SAS equivalent of ivprobit in STATA. Let’s say I want to run a model with a binary outcome (Y), two continuous endogenous explanatory variables (p1 p2), and one continuous exogenous explanatory variable (p3). I have three instruments (z1 z2 z3). proc qlim data=a; model Y = p1 p2 p3 / discrete (dist=logit); model p1 p2 = p3 z1 z2 z3; run; Are the SAS codes above correct? I want to test the null hypothesis that the two endogenous explanatory variables (EEV) are in fact exogenous. I understand that when there are two or more EEVs, the test becomes the joint likelihood ratio test of whether corresponding correlations are 0 or not. How do I modify the SAS codes above to run this test? Recall I have three instruments (z1 z2 z3). I want to test the validity of all three of my instruments by specifying the OVERID option. How do I modify the SAS codes above to incorporate the OVERID option? I want to test the strength of all three instruments used. I understand that in 2SLS one can use the F statistic based on the Stock-Yogo recommendation. Can the F statistic be applied in this case (with binary outcome) as a test of weak instruments? If so, how do I modify the SAS codes above? Thanks in advance for any help you can render! Best, Elizabeth

SASNovice2014 · ‎09-19-2014

Hi gunce @sas, Thank you once again for a very helpful response! I really appreciate that you graciously took time to help out someone you don't know. I think I now have sufficient info to proceed with my anlysis. I will come back if I've got more questions. Regards, Elizabeth

SASNovice2014 · ‎09-10-2014

Hello gunce@sas, Thank you so much for your helpful response and the codes! I really appreciate this. I have a few follow-up questions. (1) If I use your recommended SAS codes to run, I get the error message "ERROR: No valid model," and I don't see any parameter estimates. If I remove "(DIST=LOGISTIC)" in the second stage equation, or if I use "DISCRETE(DIST=probit)," I see a display of parameter estimates but I also see the following error messages: WARNING: The Hessian matrix is singular. WARNING: The Hessian matrix is singular. ERROR: QUANEW Optimization cannot be completed. NOTE: QUANEW needs more than 200 iterations or 1000 function calls. WARNING: This is an experimental release of the PLOTS option. It seems to me the program does not like having a logit specification in the second stage. How do I modify the codes so that I can get the program to run properly while retaining the logit model? [Note that my research question suggests that I should run a logit in my equation of interest.] (2) In the second instance when I was able to get the program to produce parameter estimates despite having error messages, I see that “_Rho” is insignificant. What is “_Rho”? Is it some kind of inverse mills ratio? Does an insignificant _Rho mean that I don’t have a selection bias problem? (3) To my understanding when the HECKIT option is specified, PROC QLIM automatically reports the corrected standard errors. Are your recommended codes (without HECKIT option) producing corrected or uncorrected standard errors? If the latter, how do I modify the codes to correct for standard errors? (4) Do your codes account for heteroscedasticity as well? If not, how do I account for heteroscedasticity? Thank you in advance for your guidance! Best, Elizabeth

SASNovice2014 · ‎09-09-2014

Hi Udo, Thank you for the weblinks. I am familiar with these materials and have read them. While helpful, these materials deal with selection issues related to continuous dependent variables. For instance, in the sample selection model using the Mroz dataset, the second stage dependent variable is "lwage" which is continuous in nature. I'm looking for guidance on Heckman SAS codes where the dependent variable in the second stage is a binary variable. I have two follow up questions:- (1) I'm interestd in using PROC GENMOD to run the Heckman procedure. Are the following SAS codes correct given that I have a binary dependent variable (completed acquisition =1, abandon acquisition=0) in the outcome equation of interest? */Stage 1 Heckman test - Probit specification with self-selection /* PROC GENMOD DATA=my_filename descending; CLASS case_number company_id; model HighAcq_dum =X1*X2 X1 X2 X3 X4 CatVar Year1993 Year1994 Year1995 Year1996 Year1997 /DIST=bin LINK=probit; REPEATED subject=company_id /TYPE=ar(1) ; output out=my_filename.heck prob=pcompleted ; run; /*calculate inverse mills ratio */ data my_filename.heck ; set my_filename.heck ; IMR = pdf('NORMAL', pcompleted ) / cdf('NORMAL', pcompleted ); run; /*Stage 2 Heckman test - Include IMR into GEE logit outcome equation*/ PROC GENMOD DATA= my_filename.heck descending; CLASS case_number company_id; model completed = X1*X2 X1 X2 X3 X4 IMR Year1993 Year1994 Year1995 Year1996 Year1997 /DIST=bin LINK=logit; REPEATED subject=company_id /TYPE=ar(1) ; run; (2) Let's say I want to run the Heckman using PROC QLIM instead. Are the SAS codes below correct? If not, what needs to be changed? proc qlim data=test heckit; model HighAcq_dum = X1*X2 X1 X2 X3 X4 CatVar Year1993 Year1994 Year1995 Year1996 Year1997 / discrete;/* the selection equation--probit */ model completed = X1*X2 X1 X2 X3 X4 Year1993 Year1994 Year1995 Year1996 Year1997 / select(HighAcq_dum=1); /* the equation of interest */ run; Thanks so much for your help! Best, Elizabeth

SASNovice2014 · ‎09-07-2014

***Apologies for cross-posting*** Hello, I need some help with Heckman’s (1979) 2-stage procedure using a binary dependent variable. Let’s say I regress Y on several explanatory variables using SAS PROC GENMOD (GEE Logit). Y is a binary variable, and refers to the decision to complete or abandon an acquisition (completed=1, abandon=0). PROC GENMOD DATA=my_filename descending; CLASS case_number company_id; model completed = X1*X2 X1 X2 X3 X4 Year1993 Year1994 Year1995 Year1996 Year1997 /DIST=bin LINK=logit; REPEATED subject=company_id /TYPE=ar(1) ; run; The decision to complete or abandon an acquisition may be an endogenous one, in that firms may make the decision to complete the acquisition based on expectations of economic uncertainty, which cannot be measured and cannot be included in the regression equation. Hence, I need to control for sample selection bias (endogeneity) using the 2-stage Heckman (1979) procedure. Sartori (2003) recommends using the exclusion restriction procedure, in which an additional meaningful variable is added to the first-stage selection equation but not to the second-stage equation. In line with this, in the first-stage probit model, I included a categorical variable (CatVar) to satisfy the exclusion restriction requirement. For stage 1, I calculated high acquisition experience dummy variable (1 if the number of previous acquisitions over the past 5 years is greater than the average, 0 if it did not), which served as the dependent variable in the probit model. Since I get the error message "Error in computing the variance function" when I run the Stage 1, I removed explanatory variable X3 which appears to have high collinearity with the dependent variable (HighAcq_dum). */Stage 1 Heckman test - Probit specification with self-selection /* PROC GENMOD DATA=my_filename descending; CLASS case_number company_id; model HighAcq_dum = X1 X2 X4 CatVar Year1993 Year1994 Year1995 Year1996 Year1997 /DIST=bin LINK=probit; REPEATED subject=company_id /TYPE=ar(1) ; output out=my_filename.heck prob=pcompleted ; run; /*calculate inverse mills ratio */ data my_filename.heck ; set my_filename.heck ; IMR = pdf('NORMAL', pcompleted ) / cdf('NORMAL', pcompleted ); run; /*Stage 2 Heckman test - Include IMR into GEE logit outcome equation*/ PROC GENMOD DATA= my_filename.heck descending; CLASS case_number company_id; model completed = X1*X2 X1 X2 X3 X4 IMR Year1993 Year1994 Year1995 Year1996 Year1997 /DIST=bin LINK=logit; REPEATED subject=company_id /TYPE=ar(1) ; run; (1) Would you please let me know if the above SAS codes to execute 2-stage Heckman test are correct? If not, what needs to be changed? Thanks for your help! Best, Elizabeth

SASNovice2014 · ‎09-07-2014

Hello, I need some help with Heckman’s (1979) 2-stage procedure using a binary dependent variable. Let’s say I regress Y on several explanatory variables using SAS PROC GENMOD (GEE Logit). Y is a binary variable, and refers to the decision to complete or abandon an acquisition (completed=1, abandon=0). PROC GENMOD DATA=my_filename descending; CLASS case_number company_id; model completed = X1*X2 X1 X2 X3 X4 Year1993 Year1994 Year1995 Year1996 Year1997 /DIST=bin LINK=logit; REPEATED subject=company_id /TYPE=ar(1) ; run; The decision to complete or abandon an acquisition may be an endogenous one, in that firms may make the decision to complete the acquisition based on expectations of economic uncertainty, which cannot be measured and cannot be included in the regression equation. Hence, I need to control for sample selection bias (endogeneity) using the 2-stage Heckman (1979) procedure. Sartori (2003) recommends using the exclusion restriction procedure, in which an additional meaningful variable is added to the first-stage selection equation but not to the second-stage equation. In line with this, in the first-stage probit model, I included a categorical variable (CatVar) to satisfy the exclusion restriction requirement. For stage 1, I calculated high acquisition experience dummy variable (1 if the number of previous acquisitions over the past 5 years is greater than the average, 0 if it did not), which served as the dependent variable in the probit model. Since I get the error message "Error in computing the variance function" when I run the Stage 1, I removed explanatory variable X3 which appears to have high collinearity with the dependent variable (HighAcq_dum). */Stage 1 Heckman test - Probit specification with self-selection /* PROC GENMOD DATA=my_filename descending; CLASS case_number company_id; model HighAcq_dum = X1 X2 X4 CatVar Year1993 Year1994 Year1995 Year1996 Year1997 /DIST=bin LINK=probit; REPEATED subject=company_id /TYPE=ar(1) ; output out=my_filename.heck prob=pcompleted ; run; /*calculate inverse mills ratio */ data my_filename.heck ; set my_filename.heck ; IMR = pdf('NORMAL', pcompleted ) / cdf('NORMAL', pcompleted ); run; /*Stage 2 Heckman test - Include IMR into GEE logit outcome equation*/ PROC GENMOD DATA= my_filename.heck descending; CLASS case_number company_id; model completed = X1*X2 X1 X2 X3 X4 IMR Year1993 Year1994 Year1995 Year1996 Year1997 /DIST=bin LINK=logit; REPEATED subject=company_id /TYPE=ar(1) ; run; (1) Would you please let me know if the above SAS codes to execute 2-stage Heckman test are correct? If not, what needs to be changed? Thanks for your help! Best, Elizabeth

SASNovice2014 · ‎06-04-2014

Thanks, Steve! I'll check these out.

SASNovice2014 · ‎06-02-2014

Apologies for cross-posting Hello, I have run an interaction effect using logistic GEE on PROC GENMOD. I’ve used the following SAS codes to run this analysis:- PROC GENMOD DATA=my_filename descending; CLASS obs_number company_id; model completed = CAR*CEO_Pay CAR CEO_Pay covariate1 covariate2 Year1993 Year1994 Year1995 Year1996 Year1997 /DIST=bin LINK=logit; REPEATED subject=company_id /TYPE=ar(1) CORRW covb ; run; Both CAR and CEO_Pay are continuous independent variables. The dependent variable “completed” is a binary coded variable (completed acquisition=1, abandoned acquisition=0). Covariate1 is a continuous control variable. Covariate2 is a binary control variable. I need to graph the interaction between CAR and CEO_Pay (CAR*CEO_Pay) but I’m struggling to determine the correct SAS codes for graphing this interaction. I have read up many SAS articles but have not found something that meets my needs. I would really appreciate if you’d please point me in the right direction by providing a sample SAS code to graph the above interaction as well as any sources/literature that deals with this issue. I am using SAS 9.3. Thank you in advance for your assistance! Best, Elizabeth

Online Status	Offline
Date Last Visited	‎07-27-2018 09:59 PM

How to statistically compare two curvilinear lines in a single plot us...

How to statistically compare two curvilinear lines in a single plot us...

What is SAS equivalent of ivprovit in STATA?

Re: 2-stage Heckman (1979) procedure

Re: 2-stage Heckman (1979) procedure

Re: 2-stage Heckman (1979) procedure

2-stage Heckman (1979) procedure

2-stage Heckman (1979) procedure

Re: How to plot interaction effect of logistic GEE?

How to plot interaction effect of logistic GEE?

How to statistically compare two curvilinear lines in a single plot us...

How to statistically compare two curvilinear lines in a single plot us...

What is SAS equivalent of ivprovit in STATA?

Re: 2-stage Heckman (1979) procedure

Re: 2-stage Heckman (1979) procedure

Re: 2-stage Heckman (1979) procedure

2-stage Heckman (1979) procedure

2-stage Heckman (1979) procedure

Re: How to plot interaction effect of logistic GEE?

How to plot interaction effect of logistic GEE?