With the following code, I get a plot how the regression was done for my data.
In the plot also vertical (error?) bars are shown.
To which number in the summary
refers the length of these bars, respectively: how can I derive the size of the bars from the summary (or from any quantity I could retrieve from the model)?
The code:
import random
random.seed(42)
import statsmodels.api as smapi
from statsmodels.formula.api import ols
import statsmodels.graphics as smgraphics
# Make data #
x = list(range(30))
y = [y*(10+random.random())+200 for y in x]
# Add outlier #
x.insert(6,15)
y.insert(6,220)
x.insert(6,16)
y.insert(6,295)
# Make fit #
regression = ols("data ~ x", data=dict(data=y, x=x)).fit()
# Find outliers #
test = regression.outlier_test()
outliers = ((x[i],y[i]) for i,t in enumerate(test.iloc[:,2]) if t < 0.5)
print(regression.summary())
figure = smgraphics.regressionplots.plot_fit(regression, 1)
figure.show()
The summary:
OLS Regression Results
==============================================================================
Dep. Variable: data R-squared: 0.913
Model: OLS Adj. R-squared: 0.910
Method: Least Squares F-statistic: 314.1
Date: Thu, 18 Apr 2019 Prob (F-statistic): 1.92e-17
Time: 10:47:19 Log-Likelihood: -150.87
No. Observations: 32 AIC: 305.7
Df Residuals: 30 BIC: 308.7
Df Model: 1
Covariance Type: nonrobust
==============================================================================
coef std err t P>|t| [0.025 0.975]
------------------------------------------------------------------------------
Intercept 193.8136 9.880 19.618 0.000 173.637 213.990
x 10.4202 0.588 17.724 0.000 9.219 11.621
==============================================================================
Omnibus: 57.423 Durbin-Watson: 1.316
Prob(Omnibus): 0.000 Jarque-Bera (JB): 379.511
Skew: -3.901 Prob(JB): 3.89e-83
Kurtosis: 17.958 Cond. No. 33.8
==============================================================================
Warnings:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.
The plot:
To which value in the statsmodels summary relates the error bar size in the plot?
They are not "error bars". They are prediction intervals and they can't be computed from the summary output.