•
Reject
H
at the 100
p
% level of signiﬁcance if

t

> c
,where
c
is the tabulated value corresponding to column
p
.
Paired sample
t
test
Data:
Single sample of
n
measurements
x
1
,...,x
n
whichare the pairwise diﬀerences between the two original setsof measurements.
Hypothesis:
H
:
µ
= 0.
Method:
•
Calculate
x
,
s
2
and
t
=
x
√
n/s
.
•
Obtain critical value from
t
tables,
df
=
n
−
1.
•
Reject
H
at the 100
p
% level of signiﬁcance if

t

> c
,where
c
is the tabulated value corresponding to column
p
.
Two sample
t
test
Data:
Two separate samples of measurements
x
1
,...,x
n
and
y
1
,...,y
m
.
Hypothesis:
H
:
µ
x
=
µ
y
.
Method:
•
Calculate
x
,
s
2
x
,
y
, and
s
2
y
.
•
Calculate
s
2
=
(
n
−
1)
s
2
x
+ (
m
−
1)
s
2
y
/
(
n
+
m
−
2)
.
•
Calculate
t
=
x
−
y
s
2
1
n
+1
m
.
•
Obtain critical value from
t
tables,
df
=
n
+
m
−
2.
•
Reject
H
at the 100
p
% level of signiﬁcance if

t

> c
,where
c
is the tabulated value corresponding to column
p
.
CI for population mean
Data:
Sample of measurements
x
1
,...,x
n
.
Method:
•
Calculate
x
,
s
2
x
.
•
Look in
t
tables,
df
=
n
−
1, column
p
. Let thetabulated value be
c
say.
•
100(1
−
p
)% conﬁdence interval for
µ
is
x
±
cs
x
/
√
n
.
CI for diﬀerence in population means
Data:
Separate samples
x
1
,...,x
n
and
y
1
,...,y
m
.
Method:
•
Calculate
x
,
s
2
x
,
y
,
s
2
y
.
•
Calculate
s
2
=
(
n
−
1)
s
2
x
+ (
m
−
1)
s
2
y
/
(
n
+
m
−
2)
.
•
Look in
t
tables,
df
=
n
+
m
−
2, column
p
. Let thetabulated value be
c
say.
•
100(1
−
p
)% conﬁdence interval for the diﬀerence in
population
means i.e.
µ
x
−
µ
y
, is(
x
−
y
)
±
c
s
2
1
n
+1
m
.
Regression and correlation
The linear regression model:
y
i
=
α
+
βx
i
+
z
i
.
Least squares estimates of
α
and
β
:ˆ
β
=
ni
=1
x
i
y
i
−
nxy
(
n
−
1)
s
2
x
,
and ˆ
α
=
y
−
ˆ
βx.
Conﬁdence interval for
β
•
Calculateˆ
β
as given previously.
•
Calculate
s
2
ε
=
s
2
y
−
ˆ
β
2
s
2
x
.
•
Calculate
SE
(ˆ
β
) =
s
2
ε
(
n
−
2)
s
2
x
.
•
Look in
t
tables,
df
=
n
−
2, column
p
. Let thetabulated value be
c
.
•
100(1
−
p
)% conﬁdence interval for
β
isˆ
β
±
cSE
(ˆ
β
).
Test for
ρ
= 0
Hypothesis:
H
:
ρ
= 0.
•
Calculate
t
=
r
n
−
21
−
r
2
1
/
2
.
•
Obtain critical value from
t
tables,
df
=
n
−
2.
•
Reject
H
at 100
p
% level of signiﬁcance if

t

> c
,where
c
is the tabulated value corresponding to column
p
.
Approximate CI for proportion
θ
p
±
1
.
96
p
(1
−
p
)
n
−
1where
p
is the observed proportion in the sample.