This preview shows pages 1–2. Sign up to view the full content.
Finding Pvalues
For hypothesis testing for proportions were we calculate a Z test statistic (I’ll call it Zstat)
and for testing means we use a t test statistic (I’ll call it t
stat
).
Finding the pvalue (or
probability value) is based on the
alternative
hypothesis, Ha.
Proportion Tests
If Ha uses “>” then the pvalue is P(Z > Zstat) or P(t > t
stat
).
{Read this as the probability
of getting a Zvalue (or tvalue) greater than Zstat (or t
stat
).
For the Z tests you can refer
to the previous lesson where we discussed finding probabilities when we introduced the
Standard Normal Table.
For example, you would find the Zstat in the table, look up the
cumulative probability for that value, and then subtract that probability from 1 to get the
pvalue.
If Ha uses “<” then the pvalue is P(Z < Zstat) or P(t < t
stat
).
{Read this as the probability
of getting a Zvalue (or tvalue) less than Zstat (or t
stat
).
For the Z tests you can refer to
the previous lesson where we discussed finding probabilities when we introduced the
Standard Normal Table.
For example, you would find the Zstat in the table, look up the
cumulative probability for that value, and then this is the pvalue.
If Ha uses “≠” then the pvalue is P(Z > Zstat) or P(t > t
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
This is the end of the preview. Sign up
to
access the rest of the document.
 '08
 SENTURK,DAMLA
 PValues, Probability, Regression Analysis

Click to edit the document details