Skip to main content

Section 9.4 Summary of One-sample \(t\) Procedures

One-sample \(t\) Procedures.

Parameter: \(\mu\) = the population mean
To test \(H_0: \mu = \mu_0\)
Standardized (test) statistic:
\begin{equation*} t_0 = \frac{\bar{x} - \mu_0}{s/\sqrt{n}} \end{equation*}
Degrees of freedom = \(n - 1\)
\(t\)-Confidence interval for \(\mu\)
\begin{equation*} \bar{x} \pm t_{n-1}^* \frac{s}{\sqrt{n}} \end{equation*}
Technical conditions: These procedures are considered valid if the sample distribution is reasonably symmetric or the sample size is at least 30; and the data are independent and identical observations from a random process or are from a large population (\(N \gt 20 n\)).

Technology Instructions.

Hint 1. R
Raw data:
t.test(data, mu = hypothesized, alt = "greater", "less", or "two.sided", conf.level)
Summary data:
iscamonesamplet(xbar, sd, n, hypothesized, alternative, conf.level)
Hint 2. JMP
Raw data: Analyze > Distribution
Summary data: Use ISCAM Journal file: Hypothesis Test for One Mean and Confidence Interval for One Mean. You can specify a column of data (raw data) or summary statistics (summary data); select the \(t\)-test and \(t\) interval radio buttons.
Hint 3. Theory-Based Inference applet
  • Use the pull-down menu to select One Mean.
  • Specify the summary statisti (the sample size, sample mean, and sample standard deviation \(s\)) or paste in the raw data.
  • Check the box for Test of significance and specify the hypothesized value, use the \(>\) button to specify the direction of the alternative and press Calculate
  • and/or check the box for Confidence Interval, specify the confidence level and press Calculate CI.
    • The applet can report both the confidence interval and the prediction interval.

Prediction Intervals for Individual Observations.

\(t\)-prediction Interval
\begin{equation*} \bar{x} \pm t_{n-1}^* s\sqrt{1+\frac{1}{n}} \end{equation*}
Technical conditions: This procedure is considered valid only with normally distributed observations (from random process or large population).

Technology Instructions.

Hint 1. R
predict(lm(y ~ 1), newdata = data.frame(var = 0), interval = "predict")
Hint 2. JMP
Raw data: From Analyze > Distribution, use the hot spot to select Prediction Interval
Hint 3. Theory-Based Inference applet
Check the box for the Prediction interval
You have attempted of activities on this page.