Regression

First enter the data set into the data editor (see data set entry). Note which column of data in the data editor is for the input (independent) variable and which is for the output (dependent) variable. For illustration, we assume that the input data are in column c1 and the output data are in column c2. After data entry, plot (see scatter plot) the data to get a good feel for the regression problem at hand. The displayed example shows the growth of yeast; hence, for our example we conduct a logistic regression.

From the data set window, press F5 to access the Calc menu. Press the right arrow on the thumb pad to view the Calculation Type pop-up menu.

The TI-89 can perform a regression to find the equation of best fit for nine different types of equations: cubic, exponential, linear, logarithmic, power, quadratic, quartic, sinusoidal and logistic. We emphasize that only the user can determine the type of function to use.

For our illustration, we find the logistic equation of best fit. Highlight C:Logistic and then press ENTER. You are returned to the Calculate dialog box. You now need to fill in the x-box, the y-box, then select the function for the "Store RegEQ to...".

Use the thumb pad down arrow to navigate to the x-box. Enter the column containing the input data. For example, if the input data are in column 1, then press C . Use the thumb pad down arrow again to navigate to the y-box. Enter the column containing the output data. For example, if the output data are in column c2, then press C . Use the down thumb pad arrow again to navigate to Store RegEQ to.... Press the thumb pad right arrow key to view the function submenu. Select the function to carry the regression equation. Here, we select y1(x). Press ENTER after your selection is highlighted.

After the information in the Calculate dialog box has been completed, press to conduct the regression. The STAT VARS information box is displayed with the regression results.

Warning For all regression functions except the logistic, the TI-89 uses the basic form of the function. The logistic equation has the general form . The TI-89, however, adds a vertical translation term; hence, returns an equation of the form .

After the regression, we plot the data and then overlay the scatter plot with the graph of the regression equation. To view the scatter plot, press GRAPH. If needed, adjust the view by pressing to select the Zoom menu, then select 9:ZoomData.

If the plot shows the graph of an unwanted function, go to the equation editor () and deselect any unwanted function by highlighting that function and press the key.

Note All regressions on the TI-89 are done in the same manner as the example given above. The only difference from one problem to another is the data set used and the equation selected for the regression.