ATMS 391
Homework 8: Linear regression
Problem 1
Perform a linear regression between hourly temperature (DryBulbCelsius)
and dewpoint (DewPointCelsius)
at Chicago for the month of August 2015. Ignore missing data.
(a) Make a scatter plot of the data, and the linear regression fit. Include a legend.
(b) What are the fit coefficients?
(c) What is the 95% confidence interval of the fit?
0 | 1 | |
---|---|---|
Intercept | 6.911831 | 9.306457 |
DryBulbCelsius | 0.300409 | 0.408113 |
(d) Can we reject the null hypothesis that there is no relation between temperature and dewpoint? At what confidence level?
(e) What is the value of for this fit?
(f) Include Mean Sea Level Pressure (SeaLevelPressure)
and Wind Speed (Wind Speed)
in a multiple linear regression model. Calculate p-values for each variable to see if it works? Are these new variables directly or inversely related with temperature? With the additional data, does the multiple linear regression improve the fit, compared with the linear model above? Give value of the fit.