6-4-4

Performing Statistical Calculations

 

 

 

 

 

1

 

 

 

n

 

 

 

 

 

• Linear Regression ...

MSe =

 

 

 

Σ (yi – (axi+ b))2

 

 

 

n – 2

 

 

 

 

 

 

 

 

 

 

 

i =1

 

 

 

 

 

 

 

 

 

 

1

 

 

 

n

 

 

 

 

 

• Quadratic Regression ...

MSe =

 

 

 

 

Σ (yi – (axi 2+ bxi+ c))2

 

 

 

 

 

 

 

 

 

 

n – 3

 

 

 

 

 

 

 

 

 

 

i =1

 

 

 

 

 

 

 

 

 

 

1

 

 

 

n

 

 

 

 

 

• Cubic Regression ...

MSe =

 

 

 

 

 

Σ (yi – (axi3+ bxi2+ cxi +d ))2

 

 

 

n – 4

 

 

 

 

 

 

 

 

 

i =1

 

 

 

 

 

 

 

 

 

 

1

 

 

 

n

 

 

 

 

 

• Quartic Regression ...

MSe =

 

 

 

 

Σ (yi – (axi4+ bxi3 + cxi2 + dxi + e))2

 

n – 5

 

 

 

 

 

 

 

 

i =1

 

 

 

 

 

 

 

 

 

 

1

 

 

 

n

 

 

 

 

 

• Logarithmic Regression ... MSe =

 

 

 

Σ (yi – (a + b ln xi ))2

 

 

 

n – 2

 

 

 

 

 

 

 

 

 

 

 

 

i =1

 

 

 

 

 

 

 

 

 

 

1

 

 

 

n

 

 

 

 

 

• Exponential Repression ...

MSe =

 

 

 

iΣ=1

(ln yi

– (ln a + bxi ))

2

 

 

n – 2

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

1

 

 

 

n

 

 

 

 

 

• Power Regression ...

MSe =

 

 

 

iΣ=1

(ln yi

– (ln a + b ln xi ))

2

 

n – 2

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

1

 

 

 

n

 

 

 

 

 

• Sin Regression ...

MSe =

 

 

 

iΣ=1

(yi – (a sin (bxi + c) + d ))

2

n – 2

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

1

 

 

 

n

 

2

 

 

 

• Logistic Regression ...

MSe =

 

 

 

Σ

yi –

C -bxi

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

n – 2

 

 

 

i =1

 

1 + ae

 

 

 

u Estimated Value Calculation for Regression Graphs

The STAT mode also includes a Y-CAL function that uses regression to calculate the estimated y-value for a particular x-value after graphing a paired-variable statistical regression.

The following is the general procedure for using the Y-CAL function.

1.After drawing a regression graph, press !5(G-SLV)1(Y-CAL) to enter the graph selection mode, and then press w.

If there are multiple graphs on the display, use f and c to select the graph you want, and then press w.

• This causes an x-value input dialog box to appear.

20050401