OLS fails with 1 exogenous variable

[Chang She]

In [1]: import numpy as np

In [2]: import numpy.random as rand

In [3]: x, y = rand.normal(0.5, 1.3, 1200), rand.normal(1.3, 2.5, 1200)

In [4]: from scikits.statsmodels.regression import OLS

In [5]: OLS(y, x).fit()
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)

H:\Workspace\Python\src\<ipython console> in <module>()

Q:\GAARD\Prod\Apps\PythonRuntime\1.9\lib\site-packages\scikits.statsmodels-0.1.0b1-py2.5
\statsmodels\regression.pyc in fit(self)
    226 #TODO: add a full_output keyword so that only light results needed for
    227 # IRLS are calculated?
--> 228 beta = np.dot(self.pinv_wexog, self.wendog)
    229 # should this use lstsq instead?
    230 # worth a comparison at least...though this is readable

ValueError: matrices are not aligned

In [6]: %debug
> q:\gaard\prod\apps\pythonruntime\1.6\lib\site-packages\scikits.statsmodels-0.1.0b1-py2.5.egg\scikits\statsmodels\regression.py(228)fit()
    227 # IRLS are calculated?
--> 228 beta = np.dot(self.pinv_wexog, self.wendog)
    229 # should this use lstsq instead?

ipdb> self.pinv_wexog.shape
(1200, 1)
ipdb> self.wendog.shape
(1200,)
ipdb>

[Chang She (changshe)]

nevermind

I missed the part in the notes where it assumes the design matrix contains a constant :)

[Skipper Seabold (jsseabold)]

What version are you using? The code you write should still work in the most recent release.

The assumption about the constant is only for post-estimation statistics.

[Chang She (changshe)]

Good point. It looks like I'm on 0.1.0b1.

On Sun, Aug 15, 2010 at 1:36 PM, Skipper Seabold <email address hidden>wrote:

> What version are you using? The code you write should still work in the
> most recent release.
>
> The assumption about the constant is only for post-estimation
> statistics.
>
> --
> OLS fails with 1 exogenous variable
> https://bugs.launchpad.net/bugs/618283
> You received this bug notification because you are a direct subscriber
> of the bug.
>
> Status in scikits.statsmodels: Invalid
>
> Bug description:
> In [1]: import numpy as np
>
> In [2]: import numpy.random as rand
>
> In [3]: x, y = rand.normal(0.5, 1.3, 1200), rand.normal(1.3, 2.5, 1200)
>
> In [4]: from scikits.statsmodels.regression import OLS
>
> In [5]: OLS(y, x).fit()
> ---------------------------------------------------------------------------
> ValueError Traceback (most recent call last)
>
> H:\Workspace\Python\src\<ipython console> in <module>()
>
>
> Q:\GAARD\Prod\Apps\PythonRuntime\1.9\lib\site-packages\scikits.statsmodels-0.1.0b1-py2.5
> \statsmodels\regression.pyc in fit(self)
> 226 #TODO: add a full_output keyword so that only light results needed
> for
> 227 # IRLS are calculated?
> --> 228 beta = np.dot(self.pinv_wexog, self.wendog)
> 229 # should this use lstsq instead?
> 230 # worth a comparison at least...though this is readable
>
> ValueError: matrices are not aligned
>
> In [6]: %debug
> >
> q:\gaard\prod\apps\pythonruntime\1.6\lib\site-packages\scikits.statsmodels-0.1.0b1-py2.5.egg\scikits\statsmodels\regression.py(228)fit()
> 227 # IRLS are calculated?
> --> 228 beta = np.dot(self.pinv_wexog, self.wendog)
> 229 # should this use lstsq instead?
>
> ipdb> self.pinv_wexog.shape
> (1200, 1)
> ipdb> self.wendog.shape
> (1200,)
> ipdb>
>
> To unsubscribe from this bug, go to:
> https://bugs.launchpad.net/statsmodels/+bug/618283/+subscribe
>

[Chang She (changshe)]

hi 618283 i feel like this is my calling you know you have what it takes http://t.co/q5VyCXjh