Styjun

What is more safe for browsing the web: PC or smartphone?

Problem with estimating a sequence with intuition

What's the 2-minute timer on mobile Deutsche Bahn tickets?

Is the US ESTA (Electronic System for Travel Authorization) a visa?

Reverse ColorFunction or ColorData

Dual frame in Riemannian metrics.

How is trade in services conducted under the WTO in the absence of the Doha conclusion?

Picking a theme as a discovery writer

How did the Apollo guidance computer handle parity bit errors?

Justification of physical currency in an interstellar civilization?

How can I obtain and work with a Platonic dodecahedron?

Can I combine SELECT TOP() with the IN operator?

How long did it take Captain Marvel to travel to Earth?

Is throwing dice a stochastic or a deterministic process?

Copper as an adjective to refer to something made of copper

How to preserve a rare version of a book?

Can anyone identify this unknown 1988 PC card from The Palantir Corporation?

Why can’t you see at the start of the Big Bang?

What is a common way to tell if an academic is "above average," or outstanding in their field? Is their h-index (Hirsh index) one of them?

Playing Doublets with the Primes

Which version of the Squat Nimbleness feat is correct?

Huffman Code in C++

Why is the blank symbol not considered part of the input alphabet of a Turing machine?

Changing stroke width vertically but not horizontally in Inkscape

statsmodel logit reporting complete separation with constant

Logit estimator in `statsmodels` and `sklearn`Score Statsmodels Logitstatsmodel logit results very different from R and StataLogit Regression in StatsModels PythonMultinomial/conditional Logit Regression, Why StatsModel fails on mlogit package example?Unable to run logistic regression due to “perfect separation error”Python statsmodels logit wald test inputPython multinomial logit with statsmodels module: Change base value of mlogit regressionlogit with statsmodels with both binary and continuous independent variables

.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty height:90px;width:728px;box-sizing:border-box;

0

1

I tried to add constant into a logit model and got a response 'PerfectSeparationError: Perfect separation detected, results not available'. It is fine without constant.

The code below provide both scenarios(reproducible). Can you please explain why this is happening?

import statsmodels.api as sm

X = pd.DataFrame('x1': [2, 4, 3, 3.5, 2, 5.5, 1], 'x2': [1, 1.5, 1, 0.5, 0.5, 1, 1])
y = pd.DataFrame('y': [0, 1, 0, 1, 0, 1, 0])

logit = sm.Logit(y, X)
result = logit.fit()
print(result.summary())

Xc = sm.add_constant(X)
logit = sm.Logit(y, Xc)
result = logit.fit()
print(result.summary())

logistic-regression statsmodels

share|improve this question

asked Mar 23 at 4:45

Regi MathewRegi Mathew

5251918

add a comment | 

0

1

I tried to add constant into a logit model and got a response 'PerfectSeparationError: Perfect separation detected, results not available'. It is fine without constant.

The code below provide both scenarios(reproducible). Can you please explain why this is happening?

import statsmodels.api as sm

X = pd.DataFrame('x1': [2, 4, 3, 3.5, 2, 5.5, 1], 'x2': [1, 1.5, 1, 0.5, 0.5, 1, 1])
y = pd.DataFrame('y': [0, 1, 0, 1, 0, 1, 0])

logit = sm.Logit(y, X)
result = logit.fit()
print(result.summary())

Xc = sm.add_constant(X)
logit = sm.Logit(y, Xc)
result = logit.fit()
print(result.summary())

logistic-regression statsmodels

share|improve this question

asked Mar 23 at 4:45

Regi MathewRegi Mathew

5251918

add a comment | 

I tried to add constant into a logit model and got a response 'PerfectSeparationError: Perfect separation detected, results not available'. It is fine without constant.

The code below provide both scenarios(reproducible). Can you please explain why this is happening?

import statsmodels.api as sm

X = pd.DataFrame('x1': [2, 4, 3, 3.5, 2, 5.5, 1], 'x2': [1, 1.5, 1, 0.5, 0.5, 1, 1])
y = pd.DataFrame('y': [0, 1, 0, 1, 0, 1, 0])

logit = sm.Logit(y, X)
result = logit.fit()
print(result.summary())

Xc = sm.add_constant(X)
logit = sm.Logit(y, Xc)
result = logit.fit()
print(result.summary())

logistic-regression statsmodels

share|improve this question

asked Mar 23 at 4:45

Regi MathewRegi Mathew

5251918

import statsmodels.api as sm

X = pd.DataFrame('x1': [2, 4, 3, 3.5, 2, 5.5, 1], 'x2': [1, 1.5, 1, 0.5, 0.5, 1, 1])
y = pd.DataFrame('y': [0, 1, 0, 1, 0, 1, 0])

logit = sm.Logit(y, X)
result = logit.fit()
print(result.summary())

Xc = sm.add_constant(X)
logit = sm.Logit(y, Xc)
result = logit.fit()
print(result.summary())

share|improve this question

asked Mar 23 at 4:45

Regi MathewRegi Mathew

5251918

share|improve this question

asked Mar 23 at 4:45

Regi MathewRegi Mathew

5251918

asked Mar 23 at 4:45

Regi MathewRegi Mathew

5251918

asked Mar 23 at 4:45

Regi MathewRegi Mathew

5251918