0% found this document useful (0 votes)
67 views2 pages

Regression Equations On The Ti-82: 1. Prepare y Screen

This document provides instructions for using a TI-82 graphing calculator to perform regression analysis on data sets. It explains how to prepare the calculator, enter data points, calculate linear and other regression models (quadratic, cubic, quartic, logarithmic, exponential), store and graph the regression equations. Key steps include turning on StatPlot mode, clearing lists, entering paired x and y data, performing linear regression analysis to generate the line of best fit equation, and comparing regression models to determine the best fit line.

Uploaded by

kunichiwa
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
67 views2 pages

Regression Equations On The Ti-82: 1. Prepare y Screen

This document provides instructions for using a TI-82 graphing calculator to perform regression analysis on data sets. It explains how to prepare the calculator, enter data points, calculate linear and other regression models (quadratic, cubic, quartic, logarithmic, exponential), store and graph the regression equations. Key steps include turning on StatPlot mode, clearing lists, entering paired x and y data, performing linear regression analysis to generate the line of best fit equation, and comparing regression models to determine the best fit line.

Uploaded by

kunichiwa
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

REGRESSION EQUATIONS ON THE TI-82

1. Prepare y= screen.
Clear y1. Either clear all other equations or turn them off.
To turn off y2: y= ? Y2=, use arrow keys to position cursor over = sign, press ENTER .
2. Turn on STAT PLOT.

2nd [ STAT PLOT] 1: Pl ot 1. . . ENTER .


= On ENTER .
? Type: highlight first graphing option, press ENTER .
? Xlist: highlight L1 ENTER .
? Ylist: highlight L2 ENTER .
? Mark: highlight desired option ENTER 2nd [ QUI T] .
When you are finished with the statistics applications, you will need to turn off STAT PLOT:
2nd [STAT PLOT] 4 PlotsOff ENTER .

3. Clear old data.


An easy way of clearing an entire list is: STAT 1:Edit,use the up arrow > to highlight
the name of the list you wish to clear, then press CLEAR ENTER .
Another method is used in the home screen: STAT 4:ClrList 2nd [L1] ENTER .
4. Enter data points.
STAT 1: Edi t ENTER .
Clear old data, then enter the x-values in L1 and the y-values in L2. Press ENTER after
each entry. Enter each pair side-by-side, and be sure you have the same number of entries
in each list. (You cannot use 0 as an x-value for logarithmic regression; enter .000001
instead of 0 for x.)
2nd [QUIT] after all data is entered.
Example: Data pairs:
1
113
Lists:
2
114
3
119
4
122
5
129
5. Draw scatter plot.
ZOOM 9: ZoomSt at
2nd [QUIT].

Scatter plot:
ENTER .

6. Calculate linear regression equation.


STAT < CALC 5:LinReg(ax+b) 2nd [L1] , 2nd [L2]
The default lists are L1 and L2 and may be omitted.
This means that y = 4x + 107.4 is the line of best fit.
7. Store regression equation as Y1.
This must be done immediately after the regression equation is
calculated.
Y= Y1= VARS 5 5:Statistics...
< < EQ 7 7:RegEQ ENTER 2nd [QUIT].
To superimpose regression equation on scatterplot: GRAPH .

8. The correlation coefficient r.


The correlation coefficient r is a number between 1 and +1 that indicates the closeness of
the fit of the regression line. The closer |r| is to 1, the better the fit. This line is a good fit,
but there may be another type of regression that is even better.
9. Use regression equation to predict other y-values.
Example: To find y when x = 10: 2nd Y-VARS] 1:Function ENTER 1:Y1 ENTER ( 1
0 ) ENTER .
You could also store 10 as X and then evaluate Y1, or you could use the graph and the 2nd
[CALC] 1:value option.
10. Calculate other types of regression models: coefficients rounded to 3 decimals.
Quadratic model:

QuadReg

y = .714x2 .286x + 112.4

Cubic model:

CubicReg

y = .714x2 .286x + 112.4


Isnt that strange!!

Quartic model:

QuartReg

y = .5x4 6x3 + 25.5x2 41x + 134


This is a perfect fit!

Natural logarithmic
model:

LnReg

y = 110.585 + 9.206ln x
Exponential model:
y = 107.933*(1.034x)

Regression Equations on the TI-82


Judy Ahrens
Pellissippi State Technical Community College
June 7, 1999

ExpReg

You might also like