# hw9ans - Statistics 500 Fall 2009 Solutions to Homework 9 1...

This preview shows pages 1–3. Sign up to view the full content.

Statistics 500 – Fall 2009 Solutions to Homework 9 1 1. Trends in temperature. My SAS code: data temp; infile 'c:/philip/stat500/data/temperature.txt' firstobs = 2 ; input year temp; proc reg ; model temp=year / dwprob; run ; proc loess ; model temp = year / smooth = 0.6 dfmethod =exact; run ; proc mixed ; model temp = year / solution ; repeated / subject = intercept type = ar( 1 ); run ; (a) Estimated slope = 0.00449 , s.e. = 0.00035143 (b) The trend seems to be in three linear pieces. From 1880 to 1945 (approx.) we could fit a straight line, then from 1946 to 1987, the slope is close to zero, then the slope is positive again. year temperature anomaly 1880 1900 1920 1940 1960 1980 -0.4 -0.2 0.0 0.2 Your conclusion depends on your choice(s) of diagnostic. Some of the likely choices include: residual plot – does not indicate much problem, but you can see traces of the different slope from the mid 1940’s to mid 1980’s. adding quadratic or higher order terms – if you add year^2 to the model, the quadratic coefficient is not significantly different from zero. chopping year into groups and using an ANOVA lack of fit test. I got p = 0.0021; there is strong evidence that the relationship is more complex than a straight line. The specific result depends on your choice of number of groups and where they start and stop.

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Statistics 500 – Fall 2009 Solutions to Homework 9 2 using loess with a smoothing parameter of 0.6 gives F = (1.374-1.262) / (106-104.13) / (1.262 / 104.13) = 4.94. This would be compared to an F 1.87, 104 distribution. Other versions of SAS may give slightly different numbers. The p-value is 0.01. (c) I got r = 0.45, using proc reg; model … /dwprob;. Other estimators (e.g. using proc mixed or calculating residuals, lagging them, then calculating the correlation) will give slightly different values. If you calculate the correlation between resid and lag(resid), you get 0.458. Fitting an AR(1) model in proc mixed gives r = 0.489. There is no ‘right’ value.
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

### What students are saying

• As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

Kiran Temple University Fox School of Business ‘17, Course Hero Intern

• I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

Dana University of Pennsylvania ‘17, Course Hero Intern

• The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

Jill Tulane University ‘16, Course Hero Intern