Unformatted text preview: mple (Independent) Means (continued) To do a hypothesis tests for a proportion:
1. Write down your null and alternative hypotheses.
2. Press K and scroll to the TESTS menu.
3. Scroll down to 1–PropZTest and press [.
4. Look at your null hypothesis and type in the proportion stated there in the slot next to the p0.
5. Enter the number of successes (x) and sample size (n) for your sample.
(Again number, not proportion, of successes.)
6. Look at your alternative hypothesis. In the row beginning with the prop, use the arrow keys to move
the cursor left or right to select the correct form of your alternative hypothesis. Press [ to select
it. In the screen above, the twotailed (not equal) option is selected.
7. Move the cursor over the word Calculate and press [. The output screen repeats the form of the
alternative hypothesis selected. The test statistic, or zscore, z, and the pvalue, p, are given. The
results also report the sample proportion and sample size.
You can also select the option Draw in the 1–PropZTest. This will display visually the results of the test
as in the screenshot to the right. The screen reports the test statistic (the z) and the pvalue (the p).
WARNING: It is possible you will get an error message that reads ERR: DOMAIN or, when using the Draw option, ERR: SYNTAX
If you do, try the following:
1. Check that your input for x is an integer. Redo the test and make sure that x is truly a whole number, not a decimal.
2. You may have several plots that the calculator is trying to plot at the same time that are incompatible. Press the E key and
clear any extraneous equations or keystrokes by scrolling down and pressing P. If you have more than one stat plot on, you
may need turn all plots off. Not all plot types are compatible. These instructions assume that the population standard deviation is unknown. To do the procedures when s is known, use the corresponding ZTest or ZInterval. The only difference is that there is a space for you to input the value of s. In practice, we rarely know the
population standard deviation.
To make a confidence interval for a population mean (S unknown):
1. Press K and scroll to the TESTS menu.
2. Scroll down to the option TInterval and select it.
3. If you have the sample data in a list, select the Data option and enter the list name with the data. See
the top screen to the right.
4. If you have only the summary statistics, choose the Stats option and enter the summary statistics
(sample mean and standard deviation, and sample size). See the second screen to the right.
5. Determine your conﬁdence level, and select Calculate. Press [. The output screen shows the
conﬁdence interval in a set of parentheses and calculates and reports the sample’s summary statistics.
To conduct a hypothesis test for a population mean (S unknown):
1. Write down your null and alternative hypotheses.
2. Press K and scroll to the TESTS menu.
3. Scroll down until you ﬁnd the option TTest and select it.
4. If you have the data, select the Data option and enter th...
View
Full
Document
This document was uploaded on 01/28/2014.
 Spring '14

Click to edit the document details