beautypg.com

Texas Instruments TI-85 User Manual

Page 24

background image

B-24

TI-85/TI-86 Graphing Calculators

Copyright © Houghton Mifflin Company. All rights reserved.

output values are constant. If the first differences are ÒcloseÓ to constant, this is an
indication that a linear model may be appropriate.

Program

DIFF

is given in the TI-85/TI-86 Appendix.

To run the program, press

PRGM

F1

(

NAMES

) and

then the

F

-key under the name of the program. Press

ENTER

. If you have not entered the data, stop the

program by pressing

F2

(

Quit

) . To continue, press

F1

(

Yes

) .

At the

Choice?

prompt, press

F1

(

1st

) to generate

the list of first differences.

Note: You may not be able to see the complete list
on this screen. If not, go to the list editor to see the
complete list of first differences stored in

L

3

.

Exit program

DIFF

with

F4

(

Quit

) .

TI-85

View list

L

3

containing the first differences in

the output data by pressing

2nd

(

LIST

)

F4

(

EDIT

)

F3

(

L3

)

ENTER

.

TI-86

If you do not want to use program

DIFF

, you can

use your TI-86 to compute first differences of any list.

Press

2nd

(

LIST

)

F5

(

OPS

)

MORE

MORE

F4

(

Deltal(

)

EXIT

F3

(

NAMES

) and the menu key under

L

2.

Press

)

ENTER

to see the list of first differences in

the output data.

If necessary, use

to scroll to the right to see the remainder of the first differences. Use

to scroll back to the left.

Be certain you have evenly-spaced input values if you are using this to give information
about first differences and linear models.

¥ Both Program

DIFF

should not be used for data with input (

L

1

) values that are not evenly

spaced. First differences give no information about a possible linear fit to data with
inputs that are not the same distance apart.

1.4.7 FINDING A LINEAR MODEL

Use your calculator to obtain the linear model t h a t

best fits the data. Your calculator can find two different, but equivalent, forms of the linear
model: y = ax + b or y = a + bx. For convenience, we always choose the model y = ax + b.