70 cases deleted message :(
Locked
 
|
Hi, someone pls help me. I am trying to run a mediation and moderation but am
getting the message below saying it has deleted 70 cases due to missing values. I have checked and rechecked the data and there is nothing missing. Of course it is going to be insignificant if its only looking at 7 :( Run MATRIX procedure: **************** PROCESS Procedure for SPSS Release 2.041 **************** Written by Andrew F. Hayes, Ph.D. http://www.afhayes.com ************************************************************************** Model = 4 Y = ptsdonly X = neuroonl M = observe Sample size 77 ************************************************************************** Outcome: observe Model Summary R R-sq F df1 df2 p .2700 .0729 4.5231 1.0000 75.0000 .0367 Model coeff se t p LLCI ULCI constant 4.0255 .3321 12.1219 .0000 3.3639 4.6870 neuroonl -.2316 .1089 -2.1268 .0367 -.4485 -.0147 ************************************************************************** Outcome: ptsdonly Model Summary R R-sq F df1 df2 p .1002 .0100 .1894 2.0000 74.0000 .8279 Model coeff se t p LLCI ULCI constant .7684 .6963 1.1036 .2733 -.6190 2.1558 observe -.0733 .1200 -.6111 .5430 -.3125 .1658 neuroonl -.0537 .1085 -.4945 .6224 -.2699 .1626 ******************** DIRECT AND INDIRECT EFFECTS ************************* Direct effect of X on Y Effect SE t p LLCI ULCI -.0537 .1085 -.4945 .6224 -.2699 .1626 Indirect effect of X on Y Effect Boot SE BootLLCI BootULCI observe .0170 .0254 -.0247 .0779 Partially standardized indirect effect of X on Y Effect Boot SE BootLLCI BootULCI observe .0290 .0452 -.0499 .1253 Completely standardized indirect effect of X on Y Effect Boot SE BootLLCI BootULCI observe .0240 .0367 -.0396 .1060 Ratio of indirect to total effect of X on Y Effect Boot SE BootLLCI BootULCI observe -.4630 6.5527 -43.7991 -.0033 Ratio of indirect to direct effect of X on Y Effect Boot SE BootLLCI BootULCI observe -.3165 4.9203 -48.6823 .1019 R-squared mediation effect size (R-sq_med) Effect Boot SE BootLLCI BootULCI observe -.0027 .0089 -.0361 .0052 Preacher and Kelley (2011) Kappa-squared Effect Boot SE BootLLCI BootULCI observe .0233 .0251 .0006 .0866 Normal theory tests for indirect effect Effect se Z p .0170 .0317 .5352 .5925 ******************** ANALYSIS NOTES AND WARNINGS ************************* Number of bootstrap samples for bias corrected bootstrap confidence intervals: 2000 Level of confidence for all confidence intervals in output: 95.00 NOTE: Some cases were deleted due to missing data. The number of such cases was: 70 NOTE: All standard errors for continuous outcome models are based on the HC3 estimator ------ END MATRIX ----- -- Sent from: http://spssx-discussion.1045642.n5.nabble.com/ ===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD |
Re: 70 cases deleted message :(
|
|
Have you run descriptives on each variable in the analysis? And is the N for each variable the same and does that number match the number of cases in the analysis file?
Or, Have you used the nvalid function to count the number of variables in the analysis with valid values and does a frequencies run of that result have a single value equal to the number of variables in the analysis and a frequency value equal to the number of cases in the analysis file? Gene Maguin -----Original Message----- From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of sara Sent: Monday, October 9, 2017 2:10 AM To: [hidden email] Subject: 70 cases deleted message :( Hi, someone pls help me. I am trying to run a mediation and moderation but am getting the message below saying it has deleted 70 cases due to missing values. I have checked and rechecked the data and there is nothing missing. Of course it is going to be insignificant if its only looking at 7 :( Run MATRIX procedure: **************** PROCESS Procedure for SPSS Release 2.041 **************** Written by Andrew F. Hayes, Ph.D. http://www.afhayes.com ************************************************************************** Model = 4 Y = ptsdonly X = neuroonl M = observe Sample size 77 ************************************************************************** Outcome: observe Model Summary R R-sq F df1 df2 p .2700 .0729 4.5231 1.0000 75.0000 .0367 Model coeff se t p LLCI ULCI constant 4.0255 .3321 12.1219 .0000 3.3639 4.6870 neuroonl -.2316 .1089 -2.1268 .0367 -.4485 -.0147 ************************************************************************** Outcome: ptsdonly Model Summary R R-sq F df1 df2 p .1002 .0100 .1894 2.0000 74.0000 .8279 Model coeff se t p LLCI ULCI constant .7684 .6963 1.1036 .2733 -.6190 2.1558 observe -.0733 .1200 -.6111 .5430 -.3125 .1658 neuroonl -.0537 .1085 -.4945 .6224 -.2699 .1626 ******************** DIRECT AND INDIRECT EFFECTS ************************* Direct effect of X on Y Effect SE t p LLCI ULCI -.0537 .1085 -.4945 .6224 -.2699 .1626 Indirect effect of X on Y Effect Boot SE BootLLCI BootULCI observe .0170 .0254 -.0247 .0779 Partially standardized indirect effect of X on Y Effect Boot SE BootLLCI BootULCI observe .0290 .0452 -.0499 .1253 Completely standardized indirect effect of X on Y Effect Boot SE BootLLCI BootULCI observe .0240 .0367 -.0396 .1060 Ratio of indirect to total effect of X on Y Effect Boot SE BootLLCI BootULCI observe -.4630 6.5527 -43.7991 -.0033 Ratio of indirect to direct effect of X on Y Effect Boot SE BootLLCI BootULCI observe -.3165 4.9203 -48.6823 .1019 R-squared mediation effect size (R-sq_med) Effect Boot SE BootLLCI BootULCI observe -.0027 .0089 -.0361 .0052 Preacher and Kelley (2011) Kappa-squared Effect Boot SE BootLLCI BootULCI observe .0233 .0251 .0006 .0866 Normal theory tests for indirect effect Effect se Z p .0170 .0317 .5352 .5925 ******************** ANALYSIS NOTES AND WARNINGS ************************* Number of bootstrap samples for bias corrected bootstrap confidence intervals: 2000 Level of confidence for all confidence intervals in output: 95.00 NOTE: Some cases were deleted due to missing data. The number of such cases was: 70 NOTE: All standard errors for continuous outcome models are based on the HC3 estimator ------ END MATRIX ----- -- Sent from: http://spssx-discussion.1045642.n5.nabble.com/ ===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD ===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD |
|
|
Hi Gene, yes I re-ran the descriptives and N matches.
Kind regards Sara Stanley From: Maguin, Eugene <[hidden email]>
Sent: Tuesday, 10 October 2017 2:02:31 AM To: Sara Stanley; [hidden email] Subject: RE: 70 cases deleted message :( Have you run descriptives on each variable in the analysis? And is the N for each variable the same and does that number match the number of cases in the analysis file?
=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD
Or, Have you used the nvalid function to count the number of variables in the analysis with valid values and does a frequencies run of that result have a single value equal to the number of variables in the analysis and a frequency value equal to the number of cases in the analysis file? Gene Maguin -----Original Message----- From: SPSSX(r) Discussion [[hidden email]] On Behalf Of sara Sent: Monday, October 9, 2017 2:10 AM To: [hidden email] Subject: 70 cases deleted message :( Hi, someone pls help me. I am trying to run a mediation and moderation but am getting the message below saying it has deleted 70 cases due to missing values. I have checked and rechecked the data and there is nothing missing. Of course it is going to be insignificant if its only looking at 7 :( Run MATRIX procedure: **************** PROCESS Procedure for SPSS Release 2.041 **************** Written by Andrew F. Hayes, Ph.D. http://www.afhayes.com ************************************************************************** Model = 4 Y = ptsdonly X = neuroonl M = observe Sample size 77 ************************************************************************** Outcome: observe Model Summary R R-sq F df1 df2 p .2700 .0729 4.5231 1.0000 75.0000 .0367 Model coeff se t p LLCI ULCI constant 4.0255 .3321 12.1219 .0000 3.3639 4.6870 neuroonl -.2316 .1089 -2.1268 .0367 -.4485 -.0147 ************************************************************************** Outcome: ptsdonly Model Summary R R-sq F df1 df2 p .1002 .0100 .1894 2.0000 74.0000 .8279 Model coeff se t p LLCI ULCI constant .7684 .6963 1.1036 .2733 -.6190 2.1558 observe -.0733 .1200 -.6111 .5430 -.3125 .1658 neuroonl -.0537 .1085 -.4945 .6224 -.2699 .1626 ******************** DIRECT AND INDIRECT EFFECTS ************************* Direct effect of X on Y Effect SE t p LLCI ULCI -.0537 .1085 -.4945 .6224 -.2699 .1626 Indirect effect of X on Y Effect Boot SE BootLLCI BootULCI observe .0170 .0254 -.0247 .0779 Partially standardized indirect effect of X on Y Effect Boot SE BootLLCI BootULCI observe .0290 .0452 -.0499 .1253 Completely standardized indirect effect of X on Y Effect Boot SE BootLLCI BootULCI observe .0240 .0367 -.0396 .1060 Ratio of indirect to total effect of X on Y Effect Boot SE BootLLCI BootULCI observe -.4630 6.5527 -43.7991 -.0033 Ratio of indirect to direct effect of X on Y Effect Boot SE BootLLCI BootULCI observe -.3165 4.9203 -48.6823 .1019 R-squared mediation effect size (R-sq_med) Effect Boot SE BootLLCI BootULCI observe -.0027 .0089 -.0361 .0052 Preacher and Kelley (2011) Kappa-squared Effect Boot SE BootLLCI BootULCI observe .0233 .0251 .0006 .0866 Normal theory tests for indirect effect Effect se Z p .0170 .0317 .5352 .5925 ******************** ANALYSIS NOTES AND WARNINGS ************************* Number of bootstrap samples for bias corrected bootstrap confidence intervals: 2000 Level of confidence for all confidence intervals in output: 95.00 NOTE: Some cases were deleted due to missing data. The number of such cases was: 70 NOTE: All standard errors for continuous outcome models are based on the HC3 estimator ------ END MATRIX ----- -- Sent from: http://spssx-discussion.1045642.n5.nabble.com/ ===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD |
Administrator
|
In reply to this post by Maguin, Eugene
"I have checked and rechecked the data ".
I am never quite certain what this statement means. What have you done to 'check' the data? Please do what Gene suggested and you will confirm that there are 7 complete cases listwise. --- Maguin, Eugene wrote > Have you run descriptives on each variable in the analysis? And is the N > for each variable the same and does that number match the number of cases > in the analysis file? > Or, > Have you used the nvalid function to count the number of variables in the > analysis with valid values and does a frequencies run of that result have > a single value equal to the number of variables in the analysis and a > frequency value equal to the number of cases in the analysis file? > > Gene Maguin > > > -----Original Message----- > From: SPSSX(r) Discussion [mailto: > SPSSX-L@.UGA > ] On Behalf Of sara > Sent: Monday, October 9, 2017 2:10 AM > To: > SPSSX-L@.UGA > Subject: 70 cases deleted message :( > > Hi, someone pls help me. I am trying to run a mediation and moderation but > am getting the message below saying it has deleted 70 cases due to missing > values. I have checked and rechecked the data and there is nothing > missing. > Of course it is going to be insignificant if its only looking at 7 :( > > > > Run MATRIX procedure: > > **************** PROCESS Procedure for SPSS Release 2.041 **************** > > Written by Andrew F. Hayes, Ph.D. http://www.afhayes.com > > ************************************************************************** > Model = 4 > Y = ptsdonly > X = neuroonl > M = observe > > Sample size > 77 > > ************************************************************************** > Outcome: observe > > Model Summary > R R-sq F df1 df2 p > .2700 .0729 4.5231 1.0000 75.0000 .0367 > > Model > coeff se t p LLCI ULCI > constant 4.0255 .3321 12.1219 .0000 3.3639 4.6870 > neuroonl -.2316 .1089 -2.1268 .0367 -.4485 -.0147 > > ************************************************************************** > Outcome: ptsdonly > > Model Summary > R R-sq F df1 df2 p > .1002 .0100 .1894 2.0000 74.0000 .8279 > > Model > coeff se t p LLCI ULCI > constant .7684 .6963 1.1036 .2733 -.6190 2.1558 > observe -.0733 .1200 -.6111 .5430 -.3125 .1658 > neuroonl -.0537 .1085 -.4945 .6224 -.2699 .1626 > > ******************** DIRECT AND INDIRECT EFFECTS ************************* > > Direct effect of X on Y > Effect SE t p LLCI ULCI > -.0537 .1085 -.4945 .6224 -.2699 .1626 > > Indirect effect of X on Y > Effect Boot SE BootLLCI BootULCI > observe .0170 .0254 -.0247 .0779 > > Partially standardized indirect effect of X on Y > Effect Boot SE BootLLCI BootULCI > observe .0290 .0452 -.0499 .1253 > > Completely standardized indirect effect of X on Y > Effect Boot SE BootLLCI BootULCI > observe .0240 .0367 -.0396 .1060 > > Ratio of indirect to total effect of X on Y > Effect Boot SE BootLLCI BootULCI > observe -.4630 6.5527 -43.7991 -.0033 > > Ratio of indirect to direct effect of X on Y > Effect Boot SE BootLLCI BootULCI > observe -.3165 4.9203 -48.6823 .1019 > > R-squared mediation effect size (R-sq_med) > Effect Boot SE BootLLCI BootULCI > observe -.0027 .0089 -.0361 .0052 > > Preacher and Kelley (2011) Kappa-squared > Effect Boot SE BootLLCI BootULCI > observe .0233 .0251 .0006 .0866 > > Normal theory tests for indirect effect > Effect se Z p > .0170 .0317 .5352 .5925 > > ******************** ANALYSIS NOTES AND WARNINGS ************************* > > Number of bootstrap samples for bias corrected bootstrap confidence > intervals: > 2000 > > Level of confidence for all confidence intervals in output: > 95.00 > > NOTE: Some cases were deleted due to missing data. The number of such > cases > was: > 70 > > NOTE: All standard errors for continuous outcome models are based on the > HC3 estimator > > ------ END MATRIX ----- > > > > > -- > Sent from: http://spssx-discussion.1045642.n5.nabble.com/ > > ===================== > To manage your subscription to SPSSX-L, send a message to > LISTSERV@.UGA > (not to SPSSX-L), with no body text except the command. To leave the > list, send the command SIGNOFF SPSSX-L For a list of commands to manage > subscriptions, send the command INFO REFCARD > > ===================== > To manage your subscription to SPSSX-L, send a message to > LISTSERV@.UGA > (not to SPSSX-L), with no body text except the > command. To leave the list, send the command > SIGNOFF SPSSX-L > For a list of commands to manage subscriptions, send the command > INFO REFCARD ----- Please reply to the list and not to my personal email. Those desiring my consulting or training services please feel free to email me. --- "Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos ne forte conculcent eas pedibus suis." Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in abyssum?" -- Sent from: http://spssx-discussion.1045642.n5.nabble.com/ ===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD
Please reply to the list and not to my personal email.
Those desiring my consulting or training services please feel free to email me. --- "Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos ne forte conculcent eas pedibus suis." Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in abyssum?" |
|
|
Here are two tricky instances that I remember, for "unexpected missing" cases.
2) Having mis-written a Select If or Match Files in code that is only used for the run-gone-wrong.
(Do your checking right after the code that produced N=7 valid cases.)
-- Rich Ulrich From: SPSSX(r) Discussion <[hidden email]> on behalf of David Marso <[hidden email]>
Sent: Monday, October 9, 2017 6:16 PM To: [hidden email] Subject: Re: 70 cases deleted message :( "I have checked and rechecked the data ".
I am never quite certain what this statement means. What have you done to 'check' the data? Please do what Gene suggested and you will confirm that there are 7 complete cases listwise. --- [snip]
|
Re: 70 cases deleted message :(
|
|
In reply to this post by sara
Hi Sara,
I’ve used the Hayes macro only a very few times so I’m not very familiar with it. But, looking through the output (Thank You!) I see that model summaries for
observe and ptsdonly show dfs of 75 and 74, which seem right given an N of 77. I take that to mean that you had no missing data for the regression models.
You can replicate parts of the macro output using just the regression command. You need three unstandardized coefficients: neuroonl predicts observe (XM); observe
predicts ptsdonly (MY); and neuroonl (XY), observe (MY2) predicts ptsdonly. First of all, you should get the same model and model summary numbers as in the output. You can also compute the indirect effect as XM*MY. The direct effect is XY. I bet your numbers
will match Hayes. However, I understand none of that explains the message. I think Hayes has a website. Look there.
Gene From: Sara Stanley [mailto:[hidden email]]
Hi Gene, yes I re-ran the descriptives and N matches. Kind regards Sara Stanley From: Maguin, Eugene <[hidden email]> Have you run descriptives on each variable in the analysis? And is the N for each variable the same and does that number match the number of cases in the analysis file? |
|
|
Thank you Gene, I realised that it was that PROCESS cannot handle copy and paste data. I went back to an earlier version and ran that with success. If you come across this sort of problem again with anyone ask if they have done the same.
Kind regards Sara Stanley From: Maguin, Eugene <[hidden email]>
Sent: Wednesday, 11 October 2017 1:18:05 AM To: Sara Stanley; [hidden email] Subject: RE: 70 cases deleted message :( Hi Sara,
I’ve used the Hayes macro only a very few times so I’m not very familiar with it. But, looking through the output (Thank You!) I see that model summaries for
observe and ptsdonly show dfs of 75 and 74, which seem right given an N of 77. I take that to mean that you had no missing data for the regression models.
You can replicate parts of the macro output using just the regression command. You need three unstandardized coefficients: neuroonl predicts observe (XM); observe
predicts ptsdonly (MY); and neuroonl (XY), observe (MY2) predicts ptsdonly. First of all, you should get the same model and model summary numbers as in the output. You can also compute the indirect effect as XM*MY. The direct effect is XY. I bet your numbers
will match Hayes. However, I understand none of that explains the message. I think Hayes has a website. Look there.
Gene From: Sara Stanley [mailto:[hidden email]]
Hi Gene, yes I re-ran the descriptives and N matches. Kind regards Sara Stanley From: Maguin, Eugene <[hidden email]> Have you run descriptives on each variable in the analysis? And is the N for each variable the same and does that number match the number of cases in the analysis file? |
| Free forum by Nabble | Edit this page |