Term
| Sampling distribution of difference of two means, independent with sd unknown (Welch's) t = |
|
Definition
| [(x1-xbar)-(mew1-mew2)]/[(s1^2/n1)+(s2^2/n2)]^0.5 |
|
|
Term
| 3 assumptions to testing hypotheses regarding the difference of two means |
|
Definition
1. The samples are obtained using simple random sampling
2. The samples are independent
3. The populations from which the samples are drawn are normally distributed or n1>=30 and n2>=30 |
|
|
Term
Two-tailed test, two independent samples with sd unknown
H0:
H1: |
|
Definition
H0: mew1 = mew2
H1: mew1 not=to mew2 |
|
|
Term
Left-tailed test, two independent samples with unknown sd
H0:
H1: |
|
Definition
H0: mew1 = mew2
H1: mew1 < mew2 |
|
|
Term
Right-tailed test, two independent samples with unknown sd
H0:
H1: |
|
Definition
H0: mew1 = mew2
H1: mew1 > mew2 |
|
|
Term
Two-tailed test, classical approach
If t0 > t(alpha/2), then |
|
Definition
|
|
Term
Left-tailed test, classical approach
If t0 < -talpha, then |
|
Definition
|
|
Term
Right-tailed test, classical approach
If t0 > talpha, then |
|
Definition
|
|
Term
|
Definition
|
|
Term
|
Definition
|
|
Term
| Lower bound CI, two independent samples with unknown sd = |
|
Definition
(xbar1-xbar2) - t(alpha/2) x [(s1^2/n1)+(s2^2/n2)]^0.5
where t(alpha/2) is computed using the smaller of n1-1 or n2-1 degrees of freedom |
|
|
Term
| Upper bound CI, two independent samples with unknown sd = |
|
Definition
(xbar1-xbar2) + t(alpha/2) x [(s1^2/n1)+(s2^2/n2)]^0.5
where t(alpha/2) is computed using the smaller of n1-1 or n2-1 degrees of freedom calculation |
|
|
Term
| Degrees of freedom calculation = |
|
Definition
| [(s1^2/n1) + (s2^2/n2)^2]/[((s1^2/n1)/n1-1) + ((s2^2/n2)/n2-1)] |
|
|
Term
|
Definition
| Computed by finding a weighted average of the sample variances and uses this average in the computation of the test statistic |
|
|
