pandas - Margin of Error for Complex Sample in Python -
i have weighted stata dataset of national survey (n=6342). data has been weighted, i.e. each respondent represents 4000 respondents on average.
i reading dataset pandas.read_stata function. basically, need achieve extract data each question respected frequencies(%) along margin of error each frequency. 
i have written python code , works fine frequency itself, i.e. calculating sum of weighted value in each frequency , divide total weighted value sum.
pseudo-code looks this:
   q_5 = dataset['q5'].unique()`     frequencies = {}     value in q_5:         variable = dataset[dataset['q5'] == value]         freq = ((variable['indwt'].sum()/weights_sum)*100)         freq = round(freq,0)         frequencies.update({value : freq})    however, cannot proper confidence intervals or margin of error since complex sample. advised use r instead, taking consideration syntax learning curve, rather stick python.
is there statistical package python calculate me complex sample?
 
 
Comments
Post a Comment