linear regression (2 regressors)

what was the goal of running regressions on three different time periods (1990-2007, 2008-2019, 2019-2024)?

to see if the relationship between unemployment, interest rates, and house prices in NY changed over time due to events like the Great Recession and COVID-19

what does a negative coefficient on unemployment mean in a housing price model?

it means that when unemployment increases, house prices tend to go down—suggesting a negative relationship

what does a positive coefficient on the federal funds rate mean?

it suggests that as interest rates rise, house prices also rise—although this is counterintuitive and could reflect indirect or delayed effects

what does a p-value above 0.05 mean for a coefficient?

it means the result is not statistically significant—we do not have strong evidence that the variable truly affects the outcome

what does the adjusted R-squared tell you about a model?

it shows how much of the variation in the outcome is explained by the predictors—the higher, the better. Negative values mean the model performs worse than using the mean

how did the 2008-2019 period differ from 1990-2007 in terms of regression results?

unemployment had a stronger negative effect on house prices after 2008, showing that the housing market became more sensitive to economic conditions

what happened in the 2019-2024 regression?

neither unemployment nor interest rates had a meaning impact—prices surged like due to other COVID-related factors not included in the model

why might house prices increase even when interest rates go up?

because of lag effects, regional demand, or external shocks (like COVID), which override typical market patterns

what does it mean if the intercept is high but variables are not significant?

the overall trend is strong (like a surge in prices), but not explained by unemployment or interest rates—other drivers are likely at play

what is a residual standard error?

it shows the average error between predicted and actual values. A lower value = better model accuracy

why is comparing different time periods important in econometrics?

because economic relationships change over time, especially around major events like recessions or pandemics