You must SHOW ALL WORK for full credit (except for plots and things computed entirely in R, in which case just state "from R" and give the key commands for computations). Please staple your assignment if it is more than one page.

Required problems:

2) In semiconductor manufacturing, it is important to control the oxide thickness deposited on the wafers. The dataset thickness is from an experiment where the oxide thickness was measured in a 2^4 experiment with factors of temperature, time, pressure, and gas flow.
  a) Plot the response versus run order and comment on what you see.
  b) Compute the main and interaction effects.
  c) Construct a normal probability plot to determine which effects appear to be significant. (Remember to leave out the intercept.)
  d) Compute the standard error of an effect assuming that all three-way and higher order interactions are insignificant and see which effects appear significant. Does this method give the same results as part (c)?

2) The data are from problem 8.8, but the parts below are somewhat different, as we'll only analyze the force of dissociation. A study on hip replacement was done. Part of the study involves measuring the force necessary to dissociate the bipolar cup under different conditions, in particular for capture heights (CH) of 3mm (-) vs. 8mm (+), retaining ring openings (OP) of narrow vs. wide, femoral head offsets (OFF) of 0mm vs. 5mm, and ring sizes (RS) of 42mm vs. 58mm. The data are in the file hip.
  a) Plot the response versus run order and comment on what you see.
  b) Calculate the main and interaction effects.
  c) Construct a normal probability plot to determine which effects appear to be significant. (Remember to leave out the intercept.)
  d) Compute the standard error of an effect assuming that all three-way and higher order interactions are insignificant and see which effects appear significant. Does this method give the same results as part (c)?
  e) Develop a prediction equation using the significant effects and interactions.
  f) Using this prediction equation, predict the force for a 3mm capture height with wide retaining ring openings, a 5mm femoral head offset, and a ring size of 42mm.

3) Problem 10.1: A study of the relationship between rough weight (X) and finished weight (Y) of castings was made. A sample of 12 castings was examined and the data are in the file castings.
  a) Make a scatterplot to see the relationship between X and Y.
  b) Use the method of least squares to calculate the coefficients in the simple linear regression model, Y = a + bX.
  c) Calculate the standard errors of the estimated coefficients and determine if they are significant at the 95% confidence level.

4) Project planning. [You don't need to turn anything in for this.]
Read the guidelines on project outline and scope. If you have your own project idea, start thinking about these points and refining your plans so that they follow these guidelines.