From abhaylidbe at gmail.com Fri Mar 1 10:22:00 2019 From: abhaylidbe at gmail.com (abhaylidbe at gmail.com) Date: Thu, 28 Feb 2019 17:22:00 -0600 Subject: [Limdep Nlogit List] Portion of new variables are created as 'missing' instead of 0-1 Message-ID: <5c786d19.1c69fb81.a4f1d.1bf8@mx.google.com> Hi, I am creating new variables in NLOGIT using the following commands: create;if(hwy_cl=1) frwy=1$ create;if(hwy_cl=2) ushwy=1$ create;if(hwy_cl=3) st_rt=1$ create;if(hwy_cl=4) cnty=1$ create;if(hwy_cl=5) munci=1$ create;if(hwy_cl=6) pvt=1$ However, portion of the newly created variable values are shown as ?missing? instead of binary 0-1. This happens only for few rows (the row numbers without ?>>? symbol). What does this means and why could this happen? Here is a screenshot of the Data Editor window: Regards, Abhay Lidbe From wgreene at stern.nyu.edu Fri Mar 1 13:53:13 2019 From: wgreene at stern.nyu.edu (William Greene) Date: Thu, 28 Feb 2019 21:53:13 -0500 Subject: [Limdep Nlogit List] Portion of new variables are created as 'missing' instead of 0-1 In-Reply-To: <5c786d19.1c69fb81.a4f1d.1bf8@mx.google.com> References: <5c786d19.1c69fb81.a4f1d.1bf8@mx.google.com> Message-ID: The CREATE command operates on the current sample. The observations that do not have the >> next to them are not in the sample. Those observations become missing values in the commands below. You should precede the CREATEs with SAMPLE;All$ That will solve the problem. /Bill Greene On Thu, Feb 28, 2019 at 6:22 PM Abhay via Limdep < limdep at mailman.sydney.edu.au> wrote: > Hi, > > I am creating new variables in NLOGIT using the following commands: > > create;if(hwy_cl=1) frwy=1$ > create;if(hwy_cl=2) ushwy=1$ > create;if(hwy_cl=3) st_rt=1$ > create;if(hwy_cl=4) cnty=1$ > create;if(hwy_cl=5) munci=1$ > create;if(hwy_cl=6) pvt=1$ > > However, portion of the newly created variable values are shown as > ?missing? instead of binary 0-1. This happens only for few rows (the row > numbers without ?>>? symbol). What does this means and why could this > happen? Here is a screenshot of the Data Editor window: > > > > Regards, > Abhay Lidbe > > _______________________________________________ > Limdep site list > Limdep at mailman.sydney.edu.au > http://limdep.itls.usyd.edu.au > -- William Greene Department of Economics Stern School of Business, New York University 44 West 4 St., 7-90 New York, NY, 10012 URL: https://protect-au.mimecast.com/s/Psd2CoVzGQiArmAyC139Cy?domain=people.stern.nyu.edu Email: wgreene at stern.nyu.edu Ph. +1.212.998.0876 Editor in Chief: Journal of Productivity Analysis Editor in Chief: Foundations and Trends in Econometrics Associate Editor: Economics Letters Associate Editor: Journal of Business and Economic Statistics Associate Editor: Journal of Choice Modeling From ssingh10 at unl.edu Thu Mar 7 21:52:53 2019 From: ssingh10 at unl.edu (Sunil Kumar Singh) Date: Thu, 7 Mar 2019 10:52:53 +0000 Subject: [Limdep Nlogit List] Triangular Sim. eqn Message-ID: Hi - I wanted to check if anyone knew how to solve for triangular simultaneous equations in Limdep. My equations are as follows - Y1 = Y2? +X? +u1 (1) Y2 = X? +v2 (2) Y1 is categorical and Y2 are continuous. Correlation of (u1,v2) is not equal to 0. Thanks Sunil From wgreene at stern.nyu.edu Fri Mar 8 01:02:42 2019 From: wgreene at stern.nyu.edu (William Greene) Date: Thu, 7 Mar 2019 09:02:42 -0500 Subject: [Limdep Nlogit List] Triangular Sim. eqn In-Reply-To: References: Message-ID: Control function approach. Add generalized residual, (y2 - Xp)/sigma2 to first equation. You need exclusions from first equation to identify system. First equation is incorrect. Categorical variable is not a linear function of RHS variables. Use a discrete choice model for y1. Probability that y1 equals values is the function modeled. There is also a FIML approach if (u1,v2) joint normal, but you need to specify equation properly, as noted. /B. Greene On Thu, Mar 7, 2019 at 5:53 AM Sunil Kumar Singh via Limdep < limdep at mailman.sydney.edu.au> wrote: > Hi - I wanted to check if anyone knew how to solve for triangular > simultaneous equations in Limdep. > > My equations are as follows - > Y1 = Y2? +X? +u1 (1) > Y2 = X? +v2 (2) > Y1 is categorical and Y2 are continuous. Correlation of (u1,v2) is not > equal to 0. > > Thanks > Sunil > _______________________________________________ > Limdep site list > Limdep at mailman.sydney.edu.au > http://limdep.itls.usyd.edu.au > -- William Greene Department of Economics Stern School of Business, New York University 44 West 4 St., 7-90 New York, NY, 10012 URL: https://protect-au.mimecast.com/s/_HrlCjZrzqHz6ALgiW5xCT?domain=people.stern.nyu.edu Email: wgreene at stern.nyu.edu Ph. +1.212.998.0876 Editor in Chief: Journal of Productivity Analysis Editor in Chief: Foundations and Trends in Econometrics Associate Editor: Economics Letters Associate Editor: Journal of Business and Economic Statistics Associate Editor: Journal of Choice Modeling From ssingh10 at unl.edu Fri Mar 8 06:01:49 2019 From: ssingh10 at unl.edu (Sunil Kumar Singh) Date: Thu, 7 Mar 2019 19:01:49 +0000 Subject: [Limdep Nlogit List] Triangular Sim. eqn In-Reply-To: References: Message-ID: Thanks Dr. Greene. Appreciate the quick response. My mistake in outlining the issue. You are right. It is a discrete choice problem with endogenous right hand side continuous variable. FIML helped to resolve the issue. The technical details in the manual were helpful to comprehend the underlying analysis. I also noticed STATA uses the FIML under IVREGRESS when in reality this is not an instrument variable approach. Best Regards, Sunil -----Original Message----- From: Limdep On Behalf Of William Greene via Limdep Sent: Thursday, March 7, 2019 8:03 AM To: Limdep and Nlogit Mailing List Cc: William Greene Subject: Re: [Limdep Nlogit List] Triangular Sim. eqn Control function approach. Add generalized residual, (y2 - Xp)/sigma2 to first equation. You need exclusions from first equation to identify system. First equation is incorrect. Categorical variable is not a linear function of RHS variables. Use a discrete choice model for y1. Probability that y1 equals values is the function modeled. There is also a FIML approach if (u1,v2) joint normal, but you need to specify equation properly, as noted. /B. Greene On Thu, Mar 7, 2019 at 5:53 AM Sunil Kumar Singh via Limdep < limdep at mailman.sydney.edu.au> wrote: > Hi - I wanted to check if anyone knew how to solve for triangular > simultaneous equations in Limdep. > > My equations are as follows - > Y1 = Y2? +X? +u1 (1) > Y2 = X? +v2 (2) > Y1 is categorical and Y2 are continuous. Correlation of (u1,v2) is > not equal to 0. > > Thanks > Sunil > _______________________________________________ > Limdep site list > Limdep at mailman.sydney.edu.au > https://protect-au.mimecast.com/s/ykkMCmOxDQtV0y4yCGGC-y?domain=urldefense.proofpoint.com > du.au&d=DwIGaQ&c=Cu5g146wZdoqVuKpTNsYHeFX_rg6kWhlkLF8Eft-wwo&r=vvg1IZ4 > 69htwB6iN5rbh6Q&m=X7fZwXAqW8iLM2PLKt-zOvdcQ4fPQGDJ9yqtHxd27hQ&s=hSCOS4 > OOWQIAlLma1YU2Pw1EeWt8SKheI61mNPgxUWo&e= > -- William Greene Department of Economics Stern School of Business, New York University 44 West 4 St., 7-90 New York, NY, 10012 URL: https://protect-au.mimecast.com/s/rITACnxyErC4y9B9CJjl2o?domain=urldefense.proofpoint.com Email: wgreene at stern.nyu.edu Ph. +1.212.998.0876 Editor in Chief: Journal of Productivity Analysis Editor in Chief: Foundations and Trends in Econometrics Associate Editor: Economics Letters Associate Editor: Journal of Business and Economic Statistics Associate Editor: Journal of Choice Modeling _______________________________________________ Limdep site list Limdep at mailman.sydney.edu.au https://protect-au.mimecast.com/s/08sgCoVzGQiAo2W2tVbgHu?domain=urldefense.proofpoint.com From jwb_bos at yahoo.com Wed Mar 20 03:10:20 2019 From: jwb_bos at yahoo.com (Bos J.W.B.) Date: Tue, 19 Mar 2019 17:10:20 +0100 Subject: [Limdep Nlogit List] bootstrap LCM In-Reply-To: References: Message-ID: <41426E32-7862-4AE4-9B76-3C0608FF7136@yahoo.com> Hi Bill, Thanks! Very helpful indeed!!! A related question?. Am trying to write a procedure that would allow me to run the same model on a large number of data sets. I have in mind the following: proc do for;i=1,1000$ calc;i=1$ IMPORT;FILE="i.csv"$ regress;lhs=y;rhs=one,x$ EXPORT;FILE="output_i.csv" calc;i+1$ enddo$ endproc execute I cannot figure out how to get the import and export to work. Is it possible at all? gr, Jaap > On Feb 19, 2019, at 10:19 PM, William Greene via Limdep wrote: > > Jaap. In your regression spec in the procedure, you have RHS=one,x and > LCM=x. > This is surely overspecified - the same variables appear in the equation > and in the > class probabilities. In the specification of the model, you have ;PDS=ni, > which means > that the class specification is the same from period 1 to period n1. But, > with ;LCM=x, > you have the class probabilities changing over time. the result should be > unpredictablle. > In fact, I believe that limdep is ignoring periods 2 - ni of X in computing > the class > probabilities. But, again, the result seems to me like it might go awry. > Also, shouldn't > you be using a block bootstrap? Your data are a panel. You should have > pds=ni in the > EXEC command. Also, I don't think you want to repead > CProb=Cprob;Group=Group;keep=fitopen > 1,000 times. Do this with the original, non-bootstrapped regression. > Finally, you might want > to define BB to have 2*K cells. > Best regards, > Bill > > On Mon, Feb 18, 2019 at 8:59 AM Bos J.W.B. via Limdep < > limdep at mailman.sydney.edu.au> wrote: > >> Dear all, >> >> I?m trying to bootstrap a latent class model. As a basis for my code, I >> use the procedure described in the manual, section R15-3. >> >> Here?s my code: >> >> REGRESS;Lhs=klspe1;Rhs=one,klopen1,klopen1q,klywork$ >> >> namelist;x=klopen1,klopen1q,klywork$ >> calc;k=col(x)$ >> matrix;bb=init(k,1,0.0)$ >> PROC >> REGRESS;Lhs=klspe1;Rhs=one,klopen1,klopen1q, >> klywork;LCM=X;Pds=ni;Pts=2;algs=bfgs;maxit=2000; >> parameters;CProb=Cprob;Group=Group;keep=fitopen$ >> MATRIX;bb=b$ >> ENDPROC >> EXEC;Bootstrap=bb;N=1000$ >> >> The problem with this code is that it only bootstraps the coefficients for >> one class. Does anyone know the solution to this problem? I guess modifying >> the namelist command should do the trick, but I am not sure how?. >> >> gr, Jaap Bos >> >> _______________________________________________ >> Limdep site list >> Limdep at mailman.sydney.edu.au >> http://limdep.itls.usyd.edu.au >> > > > -- > William Greene > Department of Economics > Stern School of Business, New York University > 44 West 4 St., 7-90 > New York, NY, 10012 > URL: https://protect-au.mimecast.com/s/dpPVCyoNVrcGvPzpuZtWv6?domain=people.stern.nyu.edu > Email: wgreene at stern.nyu.edu > Ph. +1.212.998.0876 > Editor in Chief: Journal of Productivity Analysis > Editor in Chief: Foundations and Trends in Econometrics > Associate Editor: Economics Letters > Associate Editor: Journal of Business and Economic Statistics > Associate Editor: Journal of Choice Modeling > _______________________________________________ > Limdep site list > Limdep at mailman.sydney.edu.au > http://limdep.itls.usyd.edu.au > From wgreene at stern.nyu.edu Wed Mar 20 04:35:06 2019 From: wgreene at stern.nyu.edu (William Greene) Date: Tue, 19 Mar 2019 13:35:06 -0400 Subject: [Limdep Nlogit List] bootstrap LCM In-Reply-To: <41426E32-7862-4AE4-9B76-3C0608FF7136@yahoo.com> References: <41426E32-7862-4AE4-9B76-3C0608FF7136@yahoo.com> Message-ID: Hi Jaap. There are several reasons I suspect this won't work. First, you can't concatenate a number onto a character string and obtain a character string. So, calc;i=2$ then "i.csv" does not produce the character string "2.csv". Second, if it did work, your program below just imports 1.csv over and over again. The calc;i=1$ should be before the DO statement. BUT, I think you should just be using PROC$ ... ENDPROC$ EXECUTE... for this construction, not DO. Do you really have 1,000 data files. There must be an easier way to do this. If you had all that data stacked in a single file, you could import the whole thing once, than use SAMPLE;...$ inside a procedure to control which observations to be using. This would also obviate creating 1,000 output files, which will also be a pain in the neck. One last point. notwithstanding everything else, it looks like you don't have the full path to the import files in the command, so even if everything else did work, your program would probably not find the data files. Cheers Bill On Tue, Mar 19, 2019 at 12:10 PM Bos J.W.B. via Limdep < limdep at mailman.sydney.edu.au> wrote: > Hi Bill, > > Thanks! Very helpful indeed!!! > > A related question?. Am trying to write a procedure that would allow me to > run the same model on a large number of data sets. I have in mind the > following: > > proc > do for;i=1,1000$ > calc;i=1$ > IMPORT;FILE="i.csv"$ > regress;lhs=y;rhs=one,x$ > EXPORT;FILE="output_i.csv" > calc;i+1$ > enddo$ > endproc > > execute > > I cannot figure out how to get the import and export to work. Is it > possible at all? > > gr, Jaap > > > On Feb 19, 2019, at 10:19 PM, William Greene via Limdep < > limdep at mailman.sydney.edu.au> wrote: > > > > Jaap. In your regression spec in the procedure, you have RHS=one,x and > > LCM=x. > > This is surely overspecified - the same variables appear in the equation > > and in the > > class probabilities. In the specification of the model, you have > ;PDS=ni, > > which means > > that the class specification is the same from period 1 to period n1. > But, > > with ;LCM=x, > > you have the class probabilities changing over time. the result should > be > > unpredictablle. > > In fact, I believe that limdep is ignoring periods 2 - ni of X in > computing > > the class > > probabilities. But, again, the result seems to me like it might go awry. > > Also, shouldn't > > you be using a block bootstrap? Your data are a panel. You should have > > pds=ni in the > > EXEC command. Also, I don't think you want to repead > > CProb=Cprob;Group=Group;keep=fitopen > > 1,000 times. Do this with the original, non-bootstrapped regression. > > Finally, you might want > > to define BB to have 2*K cells. > > Best regards, > > Bill > > > > On Mon, Feb 18, 2019 at 8:59 AM Bos J.W.B. via Limdep < > > limdep at mailman.sydney.edu.au> wrote: > > > >> Dear all, > >> > >> I?m trying to bootstrap a latent class model. As a basis for my code, I > >> use the procedure described in the manual, section R15-3. > >> > >> Here?s my code: > >> > >> REGRESS;Lhs=klspe1;Rhs=one,klopen1,klopen1q,klywork$ > >> > >> namelist;x=klopen1,klopen1q,klywork$ > >> calc;k=col(x)$ > >> matrix;bb=init(k,1,0.0)$ > >> PROC > >> REGRESS;Lhs=klspe1;Rhs=one,klopen1,klopen1q, > >> klywork;LCM=X;Pds=ni;Pts=2;algs=bfgs;maxit=2000; > >> parameters;CProb=Cprob;Group=Group;keep=fitopen$ > >> MATRIX;bb=b$ > >> ENDPROC > >> EXEC;Bootstrap=bb;N=1000$ > >> > >> The problem with this code is that it only bootstraps the coefficients > for > >> one class. Does anyone know the solution to this problem? I guess > modifying > >> the namelist command should do the trick, but I am not sure how?. > >> > >> gr, Jaap Bos > >> > >> _______________________________________________ > >> Limdep site list > >> Limdep at mailman.sydney.edu.au > >> http://limdep.itls.usyd.edu.au > >> > > > > > > -- > > William Greene > > Department of Economics > > Stern School of Business, New York University > > 44 West 4 St., 7-90 > > New York, NY, 10012 > > URL: https://protect-au.mimecast.com/s/ae2TCvl0PoCJmxDQFQ92Ar?domain=people.stern.nyu.edu > > Email: wgreene at stern.nyu.edu > > Ph. +1.212.998.0876 > > Editor in Chief: Journal of Productivity Analysis > > Editor in Chief: Foundations and Trends in Econometrics > > Associate Editor: Economics Letters > > Associate Editor: Journal of Business and Economic Statistics > > Associate Editor: Journal of Choice Modeling > > _______________________________________________ > > Limdep site list > > Limdep at mailman.sydney.edu.au > > http://limdep.itls.usyd.edu.au > > > > _______________________________________________ > Limdep site list > Limdep at mailman.sydney.edu.au > http://limdep.itls.usyd.edu.au > > -- William Greene Department of Economics Stern School of Business, New York University 44 West 4 St., 7-90 New York, NY, 10012 URL: https://protect-au.mimecast.com/s/ae2TCvl0PoCJmxDQFQ92Ar?domain=people.stern.nyu.edu Email: wgreene at stern.nyu.edu Ph. +1.212.998.0876 Editor in Chief: Journal of Productivity Analysis Editor in Chief: Foundations and Trends in Econometrics Associate Editor: Economics Letters Associate Editor: Journal of Business and Economic Statistics Associate Editor: Journal of Choice Modeling From jwb_bos at yahoo.com Wed Mar 20 05:17:04 2019 From: jwb_bos at yahoo.com (Bos J.W.B.) Date: Tue, 19 Mar 2019 19:17:04 +0100 Subject: [Limdep Nlogit List] bootstrap LCM In-Reply-To: References: <41426E32-7862-4AE4-9B76-3C0608FF7136@yahoo.com> Message-ID: <488C2CB2-DBCB-44C7-B608-8FB195D6098E@yahoo.com> Thanks Bill! > On Mar 19, 2019, at 6:35 PM, William Greene via Limdep wrote: > > Hi Jaap. There are several reasons I suspect this won't work. First, you > can't concatenate > a number onto a character string and obtain a character string. So, > calc;i=2$ then "i.csv" does > not produce the character string "2.csv". Second, if it did work, your > program below just imports > 1.csv over and over again. The calc;i=1$ should be before the DO > statement. BUT, I think you > should just be using PROC$ ... ENDPROC$ EXECUTE... for this construction, > not DO. Do you > really have 1,000 data files. There must be an easier way to do this. If > you had all that data > stacked in a single file, you could import the whole thing once, than use > SAMPLE;...$ inside a > procedure to control which observations to be using. This would also > obviate creating 1,000 > output files, which will also be a pain in the neck. One last point. > notwithstanding everything else, > it looks like you don't have the full path to the import files in the > command, so even if everything > else did work, your program would probably not find the data files. > Cheers > Bill > > On Tue, Mar 19, 2019 at 12:10 PM Bos J.W.B. via Limdep < > limdep at mailman.sydney.edu.au> wrote: > >> Hi Bill, >> >> Thanks! Very helpful indeed!!! >> >> A related question?. Am trying to write a procedure that would allow me to >> run the same model on a large number of data sets. I have in mind the >> following: >> >> proc >> do for;i=1,1000$ >> calc;i=1$ >> IMPORT;FILE="i.csv"$ >> regress;lhs=y;rhs=one,x$ >> EXPORT;FILE="output_i.csv" >> calc;i+1$ >> enddo$ >> endproc >> >> execute >> >> I cannot figure out how to get the import and export to work. Is it >> possible at all? >> >> gr, Jaap >> >>> On Feb 19, 2019, at 10:19 PM, William Greene via Limdep < >> limdep at mailman.sydney.edu.au> wrote: >>> >>> Jaap. In your regression spec in the procedure, you have RHS=one,x and >>> LCM=x. >>> This is surely overspecified - the same variables appear in the equation >>> and in the >>> class probabilities. In the specification of the model, you have >> ;PDS=ni, >>> which means >>> that the class specification is the same from period 1 to period n1. >> But, >>> with ;LCM=x, >>> you have the class probabilities changing over time. the result should >> be >>> unpredictablle. >>> In fact, I believe that limdep is ignoring periods 2 - ni of X in >> computing >>> the class >>> probabilities. But, again, the result seems to me like it might go awry. >>> Also, shouldn't >>> you be using a block bootstrap? Your data are a panel. You should have >>> pds=ni in the >>> EXEC command. Also, I don't think you want to repead >>> CProb=Cprob;Group=Group;keep=fitopen >>> 1,000 times. Do this with the original, non-bootstrapped regression. >>> Finally, you might want >>> to define BB to have 2*K cells. >>> Best regards, >>> Bill >>> >>> On Mon, Feb 18, 2019 at 8:59 AM Bos J.W.B. via Limdep < >>> limdep at mailman.sydney.edu.au> wrote: >>> >>>> Dear all, >>>> >>>> I?m trying to bootstrap a latent class model. As a basis for my code, I >>>> use the procedure described in the manual, section R15-3. >>>> >>>> Here?s my code: >>>> >>>> REGRESS;Lhs=klspe1;Rhs=one,klopen1,klopen1q,klywork$ >>>> >>>> namelist;x=klopen1,klopen1q,klywork$ >>>> calc;k=col(x)$ >>>> matrix;bb=init(k,1,0.0)$ >>>> PROC >>>> REGRESS;Lhs=klspe1;Rhs=one,klopen1,klopen1q, >>>> klywork;LCM=X;Pds=ni;Pts=2;algs=bfgs;maxit=2000; >>>> parameters;CProb=Cprob;Group=Group;keep=fitopen$ >>>> MATRIX;bb=b$ >>>> ENDPROC >>>> EXEC;Bootstrap=bb;N=1000$ >>>> >>>> The problem with this code is that it only bootstraps the coefficients >> for >>>> one class. Does anyone know the solution to this problem? I guess >> modifying >>>> the namelist command should do the trick, but I am not sure how?. >>>> >>>> gr, Jaap Bos >>>> >>>> _______________________________________________ >>>> Limdep site list >>>> Limdep at mailman.sydney.edu.au >>>> http://limdep.itls.usyd.edu.au >>>> >>> >>> >>> -- >>> William Greene >>> Department of Economics >>> Stern School of Business, New York University >>> 44 West 4 St., 7-90 >>> New York, NY, 10012 >>> URL: https://protect-au.mimecast.com/s/P0heC2xZYvCLqzx8hnWZ-r?domain=people.stern.nyu.edu >>> Email: wgreene at stern.nyu.edu >>> Ph. +1.212.998.0876 >>> Editor in Chief: Journal of Productivity Analysis >>> Editor in Chief: Foundations and Trends in Econometrics >>> Associate Editor: Economics Letters >>> Associate Editor: Journal of Business and Economic Statistics >>> Associate Editor: Journal of Choice Modeling >>> _______________________________________________ >>> Limdep site list >>> Limdep at mailman.sydney.edu.au >>> http://limdep.itls.usyd.edu.au >>> >> >> _______________________________________________ >> Limdep site list >> Limdep at mailman.sydney.edu.au >> http://limdep.itls.usyd.edu.au >> >> > > -- > William Greene > Department of Economics > Stern School of Business, New York University > 44 West 4 St., 7-90 > New York, NY, 10012 > URL: https://protect-au.mimecast.com/s/P0heC2xZYvCLqzx8hnWZ-r?domain=people.stern.nyu.edu > Email: wgreene at stern.nyu.edu > Ph. +1.212.998.0876 > Editor in Chief: Journal of Productivity Analysis > Editor in Chief: Foundations and Trends in Econometrics > Associate Editor: Economics Letters > Associate Editor: Journal of Business and Economic Statistics > Associate Editor: Journal of Choice Modeling > _______________________________________________ > Limdep site list > Limdep at mailman.sydney.edu.au > http://limdep.itls.usyd.edu.au > From mark.koetse at vu.nl Sat Mar 30 19:42:26 2019 From: mark.koetse at vu.nl (Koetse, M.J.) Date: Sat, 30 Mar 2019 08:42:26 +0000 Subject: [Limdep Nlogit List] Saving RPL parameters to variables Message-ID: Dear All, In saving parameters from RPL models to data area, all parameters are grouped together, instead of that they are assigned to the respondents. No problem to adjust this, but I would like to make 100% sure that the parameters are saved in the order that respondents appear in the data. Can anyone confirm this? Below is the syntax I use, for completeness. Best regards, Mark matrix; b_m=b $ matrix; bi_m=beta_i $ create; asc1_m=0;asc2_m=0;asc3_m=0;int_m=0;dur_m=0;max_m=0;noaf_m=0;addf_m=0;prem_m=0;glb_m=0 $ namelist; par_m=asc1_m,asc2_m,asc3_m,int_m,dur_m,max_m,noaf_m,addf_m,prem_m,glb_m $ From wgreene at stern.nyu.edu Sat Mar 30 21:59:03 2019 From: wgreene at stern.nyu.edu (William Greene) Date: Sat, 30 Mar 2019 06:59:03 -0400 Subject: [Limdep Nlogit List] Saving RPL parameters to variables In-Reply-To: References: Message-ID: Mark. I can confirm that the RPs are saved with their corresponding observations in the data. Regards Bill Greene On Sat, Mar 30, 2019 at 4:42 AM Koetse, M.J. via Limdep < limdep at mailman.sydney.edu.au> wrote: > Dear All, > > > In saving parameters from RPL models to data area, all parameters are > grouped together, instead of that they are assigned to the respondents. No > problem to adjust this, but I would like to make 100% sure that the > parameters are saved in the order that respondents appear in the data. Can > anyone confirm this? > > > Below is the syntax I use, for completeness. > > > Best regards, > > Mark > > > matrix; b_m=b $ > matrix; bi_m=beta_i $ > create; > asc1_m=0;asc2_m=0;asc3_m=0;int_m=0;dur_m=0;max_m=0;noaf_m=0;addf_m=0;prem_m=0;glb_m=0 > $ > namelist; > par_m=asc1_m,asc2_m,asc3_m,int_m,dur_m,max_m,noaf_m,addf_m,prem_m,glb_m $ > > _______________________________________________ > Limdep site list > Limdep at mailman.sydney.edu.au > http://limdep.itls.usyd.edu.au > > -- William Greene Department of Economics Stern School of Business, New York University 44 West 4 St., 7-90 New York, NY, 10012 URL: https://protect-au.mimecast.com/s/ZpoyCE8kz9tVQVDqfNnDoJ?domain=people.stern.nyu.edu Email: wgreene at stern.nyu.edu Ph. +1.212.998.0876 Editor in Chief: Journal of Productivity Analysis Editor in Chief: Foundations and Trends in Econometrics Associate Editor: Economics Letters Associate Editor: Journal of Business and Economic Statistics Associate Editor: Journal of Choice Modeling From david.hensher at sydney.edu.au Sat Mar 30 23:59:41 2019 From: david.hensher at sydney.edu.au (David Hensher) Date: Sat, 30 Mar 2019 12:59:41 +0000 Subject: [Limdep Nlogit List] Saving RPL parameters to variables In-Reply-To: References: , Message-ID: Nice to know the list is now working again David Sent from my iPhone 0418 433 057 David A Hensher Note: hgroup at optusnet.com.au has been cancelled so instead use hgroup at hensher.com.au David.hensher at bigpond.com David.hensher at sydney.edu.au These emails are linked so use one only On 30 Mar 2019, at 12:59 pm, William Greene via Limdep > wrote: Mark. I can confirm that the RPs are saved with their corresponding observations in the data. Regards Bill Greene On Sat, Mar 30, 2019 at 4:42 AM Koetse, M.J. via Limdep < limdep at mailman.sydney.edu.au> wrote: Dear All, In saving parameters from RPL models to data area, all parameters are grouped together, instead of that they are assigned to the respondents. No problem to adjust this, but I would like to make 100% sure that the parameters are saved in the order that respondents appear in the data. Can anyone confirm this? Below is the syntax I use, for completeness. Best regards, Mark matrix; b_m=b $ matrix; bi_m=beta_i $ create; asc1_m=0;asc2_m=0;asc3_m=0;int_m=0;dur_m=0;max_m=0;noaf_m=0;addf_m=0;prem_m=0;glb_m=0 $ namelist; par_m=asc1_m,asc2_m,asc3_m,int_m,dur_m,max_m,noaf_m,addf_m,prem_m,glb_m $ _______________________________________________ Limdep site list Limdep at mailman.sydney.edu.au http://limdep.itls.usyd.edu.au -- William Greene Department of Economics Stern School of Business, New York University 44 West 4 St., 7-90 New York, NY, 10012 URL: https://protect-au.mimecast.com/s/JFAUCNLwM9iD2mq0imIgSs?domain=people.stern.nyu.edu Email: wgreene at stern.nyu.edu Ph. +1.212.998.0876 Editor in Chief: Journal of Productivity Analysis Editor in Chief: Foundations and Trends in Econometrics Associate Editor: Economics Letters Associate Editor: Journal of Business and Economic Statistics Associate Editor: Journal of Choice Modeling _______________________________________________ Limdep site list Limdep at mailman.sydney.edu.au http://limdep.itls.usyd.edu.au From mark.koetse at vu.nl Sun Mar 31 04:53:37 2019 From: mark.koetse at vu.nl (Koetse, M.J.) Date: Sat, 30 Mar 2019 17:53:37 +0000 Subject: [Limdep Nlogit List] Saving RPL parameters to variables In-Reply-To: References: , Message-ID: Thank you for confirming! Best regards, Mark ________________________________ Van: Limdep namens William Greene via Limdep Verzonden: zaterdag 30 maart 2019 11:59:03 Aan: Limdep and Nlogit Mailing List CC: William Greene Onderwerp: Re: [Limdep Nlogit List] Saving RPL parameters to variables Mark. I can confirm that the RPs are saved with their corresponding observations in the data. Regards Bill Greene On Sat, Mar 30, 2019 at 4:42 AM Koetse, M.J. via Limdep < limdep at mailman.sydney.edu.au> wrote: > Dear All, > > > In saving parameters from RPL models to data area, all parameters are > grouped together, instead of that they are assigned to the respondents. No > problem to adjust this, but I would like to make 100% sure that the > parameters are saved in the order that respondents appear in the data. Can > anyone confirm this? > > > Below is the syntax I use, for completeness. > > > Best regards, > > Mark > > > matrix; b_m=b $ > matrix; bi_m=beta_i $ > create; > asc1_m=0;asc2_m=0;asc3_m=0;int_m=0;dur_m=0;max_m=0;noaf_m=0;addf_m=0;prem_m=0;glb_m=0 > $ > namelist; > par_m=asc1_m,asc2_m,asc3_m,int_m,dur_m,max_m,noaf_m,addf_m,prem_m,glb_m $ > > _______________________________________________ > Limdep site list > Limdep at mailman.sydney.edu.au > http://limdep.itls.usyd.edu.au > > -- William Greene Department of Economics Stern School of Business, New York University 44 West 4 St., 7-90 New York, NY, 10012 URL: https://protect-au.mimecast.com/s/VLRXCoVzGQij7n4lH1jnOG?domain=people.stern.nyu.edu Email: wgreene at stern.nyu.edu Ph. +1.212.998.0876 Editor in Chief: Journal of Productivity Analysis Editor in Chief: Foundations and Trends in Econometrics Associate Editor: Economics Letters Associate Editor: Journal of Business and Economic Statistics Associate Editor: Journal of Choice Modeling _______________________________________________ Limdep site list Limdep at mailman.sydney.edu.au http://limdep.itls.usyd.edu.au