9 Proselyting by Religion

9_proselyting_prls.py

import pandas as pd
import numpy as np
import survey_tools as st
from statsmodels.stats.proportion import proportions_ztest

# load in the data
data07 = pd.read_spss('../data/rls/rls2007.sav')
data14 = pd.read_spss('../data/rls/rls2014.sav')
data24 = pd.read_spss('../data/rls/rls2024.sav')

# mormon variable
data07['mormon'] = data07['reltrad'].isin([' Mormon'])
data14['mormon'] = data14['RELTRAD'].isin(['Mormon'])
data24['mormon'] = data24['RELTRAD'].isin(['Church of Jesus Christ of Latter-day Saints (Mormon)'])

data24['age_rc'] = st.recode(
    data24, 'BIRTHDECADE', 
    '"2000s" = 1; "1990s" = 1; "1980s" = 2; "1970s" = 3; "1960s" = 3; "1950s" = 4; "1940s or earlier" = 4; "No answer" = NaN'
)

## Mormons and Proselytizing
# Q42d Share your faith with non-believers
data07['q42d_rc'] = np.where(~data07['q42d'].isin(['At least once a week', 'Once or twice a month']), 0, 1)
data07['q42d_rc2'] = np.where(~data07['q42d'].isin(['At least once a week']), 0, 1)

st.tabs(data07, 'reltrad','q42d_rc', display = 'row',wts='weight') \
    .apply(lambda x:x/100) \
    .apply(lambda x:round(x,2)) \
    .to_csv('~/Desktop/q42d_rc.csv')
st.tabs(data07, 'reltrad','q42d_rc2', display = 'row',wts='weight')

data14['qi2g_rc'] = np.where(~data14['qi2g'].isin(['At least once a week', 'Once or twice a month']), 0, 1)
st.tabs(data14, 'RELTRAD','qi2g_rc', display = 'row',wts='WEIGHT') \
    .apply(lambda x:x/100) \
    .apply(lambda x:round(x,2)) \
    .to_csv('~/Desktop/qi2g_rc.csv')

data24['PRAC_D_rc'] = np.where(~data24['PRAC_D'].isin(['At least once a week', 'Once or twice a month']), 0, 1)
data24['PRAC_D_rc2'] = np.where(~data24['PRAC_D'].isin(['At least once a week']), 0, 1)
st.tabs(data24, 'RELTRAD','PRAC_D_rc', display = 'row',wts='WEIGHT') \
    .apply(lambda x:x/100) \
    .apply(lambda x:round(x,2)) \
    .to_csv('~/Desktop/PRAC_D_rc.csv')

st.tabs(data24, 'RELTRAD','PRAC_D_rc2', display = 'row',wts='WEIGHT')

st.tabs(data24[data24.mormon == True], 'age_rc', 'PRAC_D_rc', display = 'row')
st.tabs(data24[data24.mormon == True], 'GENDER', 'PRAC_D_rc', display = 'row')

data14['jellobelt'] = np.where(data14['state'].isin(['Utah', 'Idaho']), 'jello', 'not jello')

st.tabs(data14[data14.mormon == True], 'jellobelt', 'qi2g_rc', display = 'row')
tbl = st.tabs(data14[data14.mormon == True], 'jellobelt', 'qi2g_rc', display = 'count')

# proportions_ztest
count = [
    tbl.loc['jello', 1],   # successes in jello states
    tbl.loc['not jello', 1]   # successes in not jello states
]
nobs = [
    tbl.loc['jello'].sum(),   # total in jello states
    tbl.loc['not jello'].sum()   # total in not jello states
]
stat, pval = proportions_ztest(count, nobs)
print(f"Z-statistic: {stat:.3f}, p-value: {pval:.3f}")

states_2024 = {
    "red": [
        "Alabama", "Alaska", "Arkansas", "Florida", "Idaho", "Indiana", "Iowa", "Kansas",
        "Kentucky", "Louisiana", "Mississippi", "Missouri", "Montana", "Nebraska", "North Dakota",
        "Ohio", "Oklahoma", "South Carolina", "South Dakota", "Tennessee", "Texas", "Utah",
        "West Virginia", "Wyoming"
    ],
    "blue": [
        "California", "Colorado", "Connecticut", "Delaware", "Hawaii", "Illinois", "Maine",
        "Maryland", "Massachusetts", "Michigan", "Minnesota", "Nevada", "New Hampshire",
        "New Jersey", "New Mexico", "New York", "Oregon", "Pennsylvania", "Rhode Island",
        "Vermont", "Virginia", "Washington", "Wisconsin"
    ]
}

data14['red_states'] = np.where(data14['state'].isin(states_2024['red']), 'red', 'blue')

st.tabs(data14[data14.mormon == True], 'red_states', 'qi2g_rc', display = 'row')
tbl = st.tabs(data14[data14.mormon == True], 'red_states', 'qi2g_rc', display = 'count')

# proportions_ztest
count = [
    tbl.loc['red', 1],   # successes in red states
    tbl.loc['blue', 1]   # successes in blue states
]
nobs = [
    tbl.loc['red'].sum(),   # total in red states
    tbl.loc['blue'].sum()   # total in blue states
]
stat, pval = proportions_ztest(count, nobs)
print(f"Z-statistic: {stat:.3f}, p-value: {pval:.3f}")

# church attendance
data24['attend'] = np.where(data24['ATTNDPERRLS'].isin(['Once a week', 'More than once a week']), 'weekly', 'less than weekly')

st.tabs(data24[data24.mormon == True], 'attend', 'PRAC_D_rc', display = 'row')

data24['White'] = data24.RACECMB.isin(['White'])

st.tabs(data24[data24.mormon == True], 'White', 'PRAC_D_rc', display = 'row')
st.tabs(data24[data24.mormon == True], 'EDUCREC', 'PRAC_D_rc', display = 'row')

# Define the region dictionary
us_regions = {
    "Northeast": [
        "Connecticut", "Maine", "Massachusetts", "New Hampshire", "Rhode Island", "Vermont",
        "New Jersey", "New York", "Pennsylvania"
    ],
    "Midwest": [
        "Illinois", "Indiana", "Michigan", "Ohio", "Wisconsin",
        "Iowa", "Kansas", "Minnesota", "Missouri", "Nebraska", "North Dakota", "South Dakota"
    ],
    "South": [
        "Delaware", "Florida", "Georgia", "Maryland", "North Carolina", "South Carolina", "Virginia", "District of Columbia", "West Virginia",
        "Alabama", "Kentucky", "Mississippi", "Tennessee",
        "Arkansas", "Louisiana", "Oklahoma", "Texas"
    ],
    "West": [
        "Arizona", "Colorado", "Idaho", "Montana", "Nevada", "New Mexico", "Utah", "Wyoming",
        "Alaska", "California", "Hawaii", "Oregon", "Washington"
    ]
}

# Create a mapping from state to region
state_to_region = {}
for region, states in us_regions.items():
    for state in states:
        state_to_region[state] = region

# Assign the region variable
data14['region'] = data14['state'].map(state_to_region)

st.tabs(data14[data14.mormon == True], 'region', 'qi2g_rc', display = 'row')