solve

OLS Regression Results Dep. Variable: sale_price R-squared: 0.565 Model: OLS Adj. R-squared: 0.563 coef std err t P | t| [0. 025 0. 975] Intercept -7. 407e+04 9826.933 -7.537 0. 000 -9.33e+04 -5. 48e+04 C(year_sold) [T. 2013] 3.222e+04 1. 03e+04 3. 124 0. 002 1. 2e+04 5.24e+04 C(year_sold) [T. 2014] 4.551e+04 1. 04e+04 4. 395 0. 000 2. 52e+04 6.58e+04 C(year_sold) [T. 2015] 7.902e+04 9971. 857 7. 924 0 . 000 5. 95e+04 9. 86e+04 C(year_sold) [T. 2016] 7.291e+04 9653. 510 7.552 0. 000 5. 4e+04 9. 18e+04 C(year_sold) [T. 2017] 8. 331e+04 9629. 238 8. 652 0. 000 6. 44e+04 1. 02e+05 C(year_sold) [T. 2018] 1. 094e+05 9688. 443 11.291 0 . 000 9. 04e+04 1.28e+05 C(year_sold) [T. 2019] 1. 315e+05 9892 . 236 13. 292 0. 000 1. 12e+05 1.51e+05 C(year_sold) [T. 2020] 1.371e+05 1.35e+04 10.147 0. 000 1. 11e+05 1. 64e+05 area 138.5599 2. 766 50. 101 0. 000 133. 136 143. 983 Test for Constraints coef std err P| t| [0. 025 0. 975] cl -1. 33e+04 9614.875 -1.383 0. 167 -3.22e+04 5557 .325 The dataframe house_df includes data columns 'sale_price' for the sale price of the house in dollars, 'area' for the size of the house in square feet, and the 'year_sold', for year the house was sold. Years range from 2012 to 2020. The code below creates the results in the table. year_results = smf.ols(sale_price ~ area + C(year_sold)', data=house_df).fit() print(year_results.summary()) Suppose you run the following and gen the results in the second table hypothesis = 'C(year_sold)[T.2013] = C(year_sold)[T.2014]' t_test = year_results.t_test(hypothesis) How do you interpret the results? There is no statistically significant difference between the price of a house of the same area sold in 2013 compared to 2014. O There is statistical evidence that houses sold in 2013 sold for more than houses sold in 2014. O There is no statistically significant difference between the price of a house of the same area sold in 2013 compared to 2012. O There is statistical evidence that houses sold in 2013 sold for less than houses sold in 2014