Set the covariance fixed in regression (LISREL)

classic Classic list List threaded Threaded
2 messages Options
Reply | Threaded
Open this post in threaded view
|

Set the covariance fixed in regression (LISREL)

sendona
Hi,

I'm trying to fit a regression model in LISREL. I want all the covariances between the independent variables to be fixed. I know that it's possible to do this in the path diagram output by right clicking on the covariance line and then set it fixed. But there are too many independent variables which makes it very difficult. I know it's possible to this via syntax, but don't know the command. The syntax I'm working on is at the end of this post. Please note that I need a command that sets all the covariances fixed in a simple line, because there are too many variables which makes it impossible to write a separate line for each possible pair of them.

Thanks in advance.



The syntax command:


Regression
Observed variables: Y X1 X2 X3 X4 X5 X6 X7 X8 X9 X10 X11 X12 X13 X14 X15 X16 X17 X18 X19
Means: 1.825838846 0.225535647 0.049116652 0.021172638 0.012274549 0.022917971 0.037820914 0.022917971 0.008139244 0.062985224 0.009640666 0.016902467 0.004882935 0.002754476 0.003505697 34.87211924 0.645234081 27.12022407 921964.5572 0.499686835


Covariance Matrix:

13285.54
-10.18 1394.04
51.28 -88.41 372.75
16.41 -38.12 -8.3 165.42
20.16 -22.1 -4.81 -2.05 96.8
-13.73 -41.27 -8.99 -3.88 -0.25 178.81
58.7 -68.11 -14.83 -6.39 -3.71 -6.92 290.58
15.15 -41.27 -8.99 -0.88 -2.25 -4.19 -6.92 178.81
5.05 -14.66 -3.19 -1.38 -0.8 -1.49 -2.46 -1.49 64.47
-14.57 -113.44 -24.71 -9.65 2.83 -4.53 -18.02 -11.53 -4.09 581.32
39.62 -17.37 -3.78 -1.63 -0.95 -1.77 -2.91 -1.77 -0.63 -2.85 76.26
35.68 -30.45 -6.63 2.14 -1.66 -3.09 -5.11 -2.09 -1.1 -8.5 -1.3 132.72
-11.72 -8.8 -1.92 -0.83 -0.48 -0.89 -1.48 0.11 -0.32 -2.46 -0.38 -0.66 38.81
4.42 -4.96 -1.08 -0.47 -0.27 -0.5 -0.83 -0.5 -0.18 -1.39 -0.21 -0.37 -0.11 21.94
0.11 -6.32 -1.38 -0.59 -0.34 -0.64 -1.06 -0.64 -0.23 0.24 -0.27 -0.47 -0.14 -0.08 27.9
-6273.17 -114.73 78.14 293.44 -167.72 -5.13 -4.91 102.87 273.77 116.12 -174.46 -42.28 35.83 -275.27 -46.53 1415192.43
70.81 0.96 -1.88 -1.97 4.94 6.91 0.04 -9.77 -2.58 7.15 -3.3 -1.25 1.13 0.02 0.07 -3715.63 743.77
2268.93 -15.16 10.62 0.26 -5.83 -30.27 -6.72 20.2 29.88 22.21 -15.23 -20.01 6.6 14.95 -24.01 10890.91 -185.05 21345.64
7250000000 53273653.56 20717239.61 -19479180.2 -13903834.96 -3262584.51 -58223387.18 -45291038.71 -13532326.38 60580153.02 -29330243.2 41118533.58 -6539372.93 -1120461.56 -19392465.8 7370000000 190000000 11000000000 1.43E+17
-189.92 -899.44 -195.88 -84.46 -48.97 -91.44 -150.91 -90.44 -32.48 -251.34 -37.47 -67.45 -19.49 -10.99 -13.99 -19.36 0.62 12.09 56466581.42 1995.75


Sample size: 7980

Equation: Y= X1 X2 X3 X4 X5 X6 X7 X8 X9 X10 X11 X12 X13 X14  X19

Path Diagram

Options: AD=OFF

End of Problem
Reply | Threaded
Open this post in threaded view
|

Re: Set the covariance fixed in regression (LISREL)

David Marso
Administrator
SPSS has not had anything to do with LISREL for over a decade.
So Please don't post LISREL questions here.
OTOH The answer is (or used to be)........

PH=DI

sendona wrote
Hi,

I'm trying to fit a regression model in LISREL. I want all the covariances between the independent variables to be fixed. I know that it's possible to do this in the path diagram output by right clicking on the covariance line and then set it fixed. But there are too many independent variables which makes it very difficult. I know it's possible to this via syntax, but don't know the command. The syntax I'm working on is at the end of this post. Please note that I need a command that sets all the covariances fixed in a simple line, because there are too many variables which makes it impossible to write a separate line for each possible pair of them.

Thanks in advance.



The syntax command:


Regression
Observed variables: Y X1 X2 X3 X4 X5 X6 X7 X8 X9 X10 X11 X12 X13 X14 X15 X16 X17 X18 X19
Means: 1.825838846 0.225535647 0.049116652 0.021172638 0.012274549 0.022917971 0.037820914 0.022917971 0.008139244 0.062985224 0.009640666 0.016902467 0.004882935 0.002754476 0.003505697 34.87211924 0.645234081 27.12022407 921964.5572 0.499686835


Covariance Matrix:

13285.54
-10.18 1394.04
51.28 -88.41 372.75
16.41 -38.12 -8.3 165.42
20.16 -22.1 -4.81 -2.05 96.8
-13.73 -41.27 -8.99 -3.88 -0.25 178.81
58.7 -68.11 -14.83 -6.39 -3.71 -6.92 290.58
15.15 -41.27 -8.99 -0.88 -2.25 -4.19 -6.92 178.81
5.05 -14.66 -3.19 -1.38 -0.8 -1.49 -2.46 -1.49 64.47
-14.57 -113.44 -24.71 -9.65 2.83 -4.53 -18.02 -11.53 -4.09 581.32
39.62 -17.37 -3.78 -1.63 -0.95 -1.77 -2.91 -1.77 -0.63 -2.85 76.26
35.68 -30.45 -6.63 2.14 -1.66 -3.09 -5.11 -2.09 -1.1 -8.5 -1.3 132.72
-11.72 -8.8 -1.92 -0.83 -0.48 -0.89 -1.48 0.11 -0.32 -2.46 -0.38 -0.66 38.81
4.42 -4.96 -1.08 -0.47 -0.27 -0.5 -0.83 -0.5 -0.18 -1.39 -0.21 -0.37 -0.11 21.94
0.11 -6.32 -1.38 -0.59 -0.34 -0.64 -1.06 -0.64 -0.23 0.24 -0.27 -0.47 -0.14 -0.08 27.9
-6273.17 -114.73 78.14 293.44 -167.72 -5.13 -4.91 102.87 273.77 116.12 -174.46 -42.28 35.83 -275.27 -46.53 1415192.43
70.81 0.96 -1.88 -1.97 4.94 6.91 0.04 -9.77 -2.58 7.15 -3.3 -1.25 1.13 0.02 0.07 -3715.63 743.77
2268.93 -15.16 10.62 0.26 -5.83 -30.27 -6.72 20.2 29.88 22.21 -15.23 -20.01 6.6 14.95 -24.01 10890.91 -185.05 21345.64
7250000000 53273653.56 20717239.61 -19479180.2 -13903834.96 -3262584.51 -58223387.18 -45291038.71 -13532326.38 60580153.02 -29330243.2 41118533.58 -6539372.93 -1120461.56 -19392465.8 7370000000 190000000 11000000000 1.43E+17
-189.92 -899.44 -195.88 -84.46 -48.97 -91.44 -150.91 -90.44 -32.48 -251.34 -37.47 -67.45 -19.49 -10.99 -13.99 -19.36 0.62 12.09 56466581.42 1995.75


Sample size: 7980

Equation: Y= X1 X2 X3 X4 X5 X6 X7 X8 X9 X10 X11 X12 X13 X14  X19

Path Diagram

Options: AD=OFF

End of Problem
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?"