Scribd
Upload
8 views7 pages

Assignment #3

The document discusses statistical analysis related to regression models, including hypothesis testing and the significance of variables in predicting final grades based on midterm and homework grades. It presents calculations for various statistical measures such as SSR, SSE, and MSE, and concludes that there is a significant linear relationship between midterm grades and final grades, while homework grades do not significantly contribute to the model. The results indicate that the model fits well with the data, but homework grades lack meaningful explanatory power.

Uploaded by

Tom Pham
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
8 views7 pages

Assignment #3

The document discusses statistical analysis related to regression models, including hypothesis testing and the significance of variables in predicting final grades based on midterm and homework grades. It presents calculations for various statistical measures such as SSR, SSE, and MSE, and concludes that there is a significant linear relationship between midterm grades and final grades, while homework grades do not significantly contribute to the model. The results indicate that the model fits well with the data, but homework grades lack meaningful explanatory power.

Uploaded by

Tom Pham
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

1 a .

B =
=
Exiy- Ex) z
n

[x ; -

E
[09
2

=
-
(30)(344)
12
I 7, 267
-

90-200
17 , 267)(2, 5) 10 , 5
* B 28 , 67
=

y
.

=
-
=

67
2 5

i=
428
,
=
,

10742-144880
6667
Syy
,
iss = =

10g2
SSR =
(2 =
= 792 , 06667

SXX 15

SSE =
TSS -
SSR = 88 , 6000
If regression =
1
10
If error = 12-2 =

MSE-l
88 6000
,
=
8, 86
=

lo
E

MSR
SSR
= 792 066 ,
=

F =

MSR =
89 , 3980

↑
(1 , =4 , 96
10 , 0,
05) ·

Since FT F21
, 10 , 0
,
05) we reject null
hyp .
&

linear relation
conclude that there is
signficant
.

bu no .
of ads o No ·

of .
cars
2 a . X
, sXz ,
... , Xi are observed without errors

y's independent distributed w/ Ely) = Bo + PIX + ... + Pk Y K


,

y's have constant variance * X


, , X2 , ... , XK

ys ~ N
[E(y)) (2) X , , Xz , ...,
Xk -

b .

Bo
&
Bi -

&
B2

E
y =
17 , 349 + 0
. 537x ,
+ 0
, 25742 + .

.
c

Ho : Pl =
Baro
have
We
F(2 17
= 5 , 46 Ha : At least 1870
, ,
0 .

01) .

conclude
Since FT F (a , 1, 0 .

01)
we
reject hull hyp o
and
there is a
sign relationship 3/0 final grades
homework grade with midterm
along grade at 2 = 0
, 01

d Ho: B ,
7
0 005
42
=
< 0
01
.

= 0 + = ,
,

Ha :

B, O

t - =
4 , 66

R .
R:
reject Ho if
t 7 t2/z ,
n- (k + 1)

t < -

ty2 ,
n -
(k + 1)

-
10 , 005 ·
17) = 2
, 898
to conclude
Since + t ,
we reject &
12/2 ,
n-1K + 1)

8 001
relationship at :

the model has a


signif .
Linear
< final gradea midterm grade
Ho :
B2 =0

J 2 p
= 0

Ha :
Be Fo
, 257
0
2, 14
t =
= -
=

saB 0 , 120

Reject Ho if t > +y , n -
(k+ 1)
RR:

t(ty(z)n -
(k+ 1)
D failed to Mo
Since t +
x2 ,
n- (k+ 1)
we
reject
,

conclude there
& there isn't enough evidence to say
blu final homework
is a linear
relationship grade &

grade
06
.
e R
=SR4383
=

2 1036 , 317/17 0
, 625
r 1
adj
-
=
=

3091/19

The model fits well with


the data , indicating
useful model With & adj r2 being
strongo
.

both predictors
contribute meaningfully
close suggest
8

# = 8 , 29
0
(1 , 18 0
01)
P2
,
.

Ho
=

]
:
< =
0
, 0

Ha :
Be Fo

R
. R :
reject Ho if F T F(k , n - 1k +
1)

FC
F((
-

, n
-

(k + 1)

Since FDF(1 ,
We failed to reject Ho
, 17 , 0
.

01)
and conclude homework isn't a
significant factor
This matches the +-test
of final grade at 8 = 0 . 01. .

and reinforces our statement that homework grade


doesn't add meaningful explainatory power to the

model ,

You might also like