Exercise 4.28: Keeping water supplies clean requires regular measurement of levels of pollutants. The measurements are indirect—a typical analysis involves forming a dye by a chemical reaction with the dissolved pollutant, then passing light through the solution and measuring its “absorbance.” To calibrate such measurements, the laboratory measures known standard solutions and uses regression to relate absorbance and pollutant concentration. This is usually done every day. Here is one series of data on the absorbance for different levels of nitrates. Nitrates are measured in milligrams per liter of water. Data can be found on Crunchit>File>Load from> Chapter 4> Exercise 28. b) It is appropriate to find the correlation (r) because the form of the relationship is c) Chemical theory says that these data should lie on a straight line. If the correlation is not at least 0.997, something went wrong, and the calibration procedure is repeated. Find the correlation using Crunchit!. Correlation r = (Enter it exactly as it appears on Crunchit!) d) The calibration process sets nitrate level and measures absorbance. At this point it appears as if Nitrate level is x and the absorbance is y but the roles of x and y get switched. Once established, the linear relationship will be used to estimate the nitrate level in water from a measurement of absorbance. If we are going to estimate the Nitrate level then that becomes the response variable. What is the equation of the line used for estimation? Write it in the form = + *. The two variables are "Nitrates", "Absorbance". e) What is the estimated nitrate level in a water specimen with absorbance 40? Your answer must have two decimal places. mg/liter f) Based on the correlation r we can say that the predicted value (estimate) of nitrate level is (very good/good/bad) g) The percent of the variation in Nitrate s that can be explained by absorbance is %. (two decimal places) h) We will only be able to use the regression equation to make predictions of nitrates for absorbance between nd . That is, we cannot plug in a number outside this range into the the regression equation to make a prediction