+ Reply to Thread
Results 1 to 9 of 9

Thread: SPSS is kicking out my variables [regression]

  1. #1
    Points: 533, Level: 10
    Level completed: 66%, Points required for next Level: 17

    Posts
    50
    Thanks
    20
    Thanked 0 Times in 0 Posts

    SPSS is kicking out my variables [regression]




    So I am doing a multiple regression, with some independent variables. For control variables, I created dummies for the years. I have five years (hypothetical 2017 2018 2019 2020 2021).

    > When I put them all in and run the regression excludes one of the years.

    > Also I want 2017 as the base (which shouldn't appear in the output), but it's there in the ouput as well. Sometimes SPSS excludes it, sometimes it doesn't

    I used the following code:

    RECODE YEAR (2017=1) (ELSE=0) INTO Year2017.
    EXECUTE.
    RECODE YEAR (2018=1) (ELSE=0) INTO Year2018.
    EXECUTE.
    etc.


    All I can think of why SPSS would exclude variables in my regression is, if they are highly correlated, but they aren't

  2. #2
    TS Contributor
    Points: 14,811, Level: 78
    Level completed: 91%, Points required for next Level: 39
    Miner's Avatar
    Location
    Greater Milwaukee area
    Posts
    1,171
    Thanks
    34
    Thanked 405 Times in 363 Posts

    Re: SPSS is kicking out my variables [regression]

    That is normal. While I am not an SPSS user, the software I have used does the same. The year that is kicked out is being used as the base and the remaining years are compared to it. You should be able to specify which year is used as the base. Again, I am not an SPSS user, but try omitting 2017 when you specify the model.

    This link describes how to specify which category is used as the reference.
    Last edited by Miner; 03-21-2017 at 02:17 PM. Reason: Added link.

  3. #3
    Points: 533, Level: 10
    Level completed: 66%, Points required for next Level: 17

    Posts
    50
    Thanks
    20
    Thanked 0 Times in 0 Posts

    Re: SPSS is kicking out my variables [regression]

    Quote Originally Posted by Miner View Post
    That is normal. While I am not an SPSS user, the software I have used does the same. The year that is kicked out is being used as the base and the remaining years are compared to it. You should be able to specify which year is used as the base. Again, I am not an SPSS user, but try omitting 2017 when you specify the model.

    This link describes how to specify which category is used as the reference.
    Ohh so if I understood correctly I can omit 2017 by not putting it in the regression and it will automatically take it as base year?

    I will check the link out! Thank you

  4. #4
    Omega Contributor
    Points: 38,374, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    6,998
    Thanks
    398
    Thanked 1,186 Times in 1,147 Posts

    Re: SPSS is kicking out my variables [regression]

    I only used SPSS a couple of times long ago and have not looked at the link but typically yes you give Year2010 = 1 if in that year,...,etc, and ignore using the Year2017 variable, since that information is already indirectly in the model. The example I use is if I pass out a deck of cards to 3 people, I only need to see the cards of two people to figure out what the third person has, looking the the third hand can be solved with out seeing it and that is how the dummy coding works.
    Stop cowardice, ban guns!

  5. The Following User Says Thank You to hlsmith For This Useful Post:

    ondansetron (03-24-2017)

  6. #5
    Super Moderator
    Points: 13,151, Level: 74
    Level completed: 76%, Points required for next Level: 99
    Dragan's Avatar
    Location
    Illinois, US
    Posts
    2,014
    Thanks
    0
    Thanked 223 Times in 192 Posts

    Re: SPSS is kicking out my variables [regression]

    Did you try running the regression with models (i) 2017, model (ii) 2017 and 2018, model (iii) 2017, 2018, and 2019, model (iv) 2017, 2018, 2019, 2020, and finally (v) 2017, 2018, 2019, 2020, and 2021. You might also want to the get the F change statistics as well if you do this.

  7. #6
    Points: 533, Level: 10
    Level completed: 66%, Points required for next Level: 17

    Posts
    50
    Thanks
    20
    Thanked 0 Times in 0 Posts

    Re: SPSS is kicking out my variables [regression]

    Quote Originally Posted by hlsmith View Post
    I only used SPSS a couple of times long ago and have not looked at the link but typically yes you give Year2010 = 1 if in that year,...,etc, and ignore using the Year2017 variable, since that information is already indirectly in the model. The example I use is if I pass out a deck of cards to 3 people, I only need to see the cards of two people to figure out what the third person has, looking the the third hand can be solved with out seeing it and that is how the dummy coding works.
    Very clear example haha thank you

  8. #7
    Points: 533, Level: 10
    Level completed: 66%, Points required for next Level: 17

    Posts
    50
    Thanks
    20
    Thanked 0 Times in 0 Posts

    Re: SPSS is kicking out my variables [regression]

    Quote Originally Posted by Dragan View Post
    Did you try running the regression with models (i) 2017, model (ii) 2017 and 2018, model (iii) 2017, 2018, and 2019, model (iv) 2017, 2018, 2019, 2020, and finally (v) 2017, 2018, 2019, 2020, and 2021. You might also want to the get the F change statistics as well if you do this.
    No I haven't nor did I think about this. I will try it out thank you

  9. #8
    Points: 1,741, Level: 24
    Level completed: 41%, Points required for next Level: 59

    Posts
    230
    Thanks
    37
    Thanked 68 Times in 59 Posts

    Re: SPSS is kicking out my variables [regression]

    Quote Originally Posted by hlsmith View Post
    I only used SPSS a couple of times long ago and have not looked at the link but typically yes you give Year2010 = 1 if in that year,...,etc, and ignore using the Year2017 variable, since that information is already indirectly in the model. The example I use is if I pass out a deck of cards to 3 people, I only need to see the cards of two people to figure out what the third person has, looking the the third hand can be solved with out seeing it and that is how the dummy coding works.
    I'll only add a couple things-- this is how the dummy coding works in a multiple linear regression and logistic regression, assuming an intercept is fit. In a Cox regression, the intercept is absorbed, but the coding works the same. In an MLR or logistic regression, if you don't fit an intercept, you'll need a dummy for each group since there is no intercept to represent the mean of the reference group (to which you add differences to arrive at the mean of other groups). Keep in mind that when an intercept is fit, the non-intercept coefficients for the dummies represent a difference in the mean dependent variable between one group and the reference. When you don't fit an intercept, the dummy coefficients represent the mean DV for that group.

  10. The Following 2 Users Say Thank You to ondansetron For This Useful Post:

    hlsmith (03-24-2017), Miner (03-24-2017)

  11. #9
    Omega Contributor
    Points: 38,374, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    6,998
    Thanks
    398
    Thanked 1,186 Times in 1,147 Posts

    Re: SPSS is kicking out my variables [regression]


    Yup, good point ondansetron. Since we cannot assume anything about what the OP is doing without seeing code and output!
    Stop cowardice, ban guns!

+ Reply to Thread

           




Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts






Advertise on Talk Stats