When we execute not know the population standard deviation sigma, σ, and the sample size, n, is much less than 30, we use the t-test to advice a claim. Think about the complying with problem:

A scientist think the mean waste recycle by adult in the united state is now an ext than one lb per human per day. In a random sample of 12 us adults, the typical waste recycled per day per human being is 1.9 pounds with a traditional deviation that 0.3 pounds. At a 10% definition level, go the sample data assistance the claim?

In statistics, the is constantly a an excellent idea to lay out the situation described in the problem:

The sample typical is much to the best of the assumed population mean, µ = 1.

You are watching: How to calculate standard deviation in statcrunch

To resolve this problem, we start by stating the null and alternative hypotheses:

The insurance claim includes the phrase “more than” which shows the math operator is > .Because the null should be a kind of equality < ≤, =, or ≥ >, the case is the alternative. Ho: µ ≤ 1; Ha: µ > 1.

We deserve to perform the hypothesis test one of two ways:

Find the an important value of t and determine if the test statistic is in the rejection region.Calculate the p-value for the test statistic and compare it come alpha.

Rejection an ar approach.

The mathematics operator in the alternative, >, points to the right, therefore this is a right-tail test.To discover the an essential value of t, we require the levels of freedom.N = 12df = n-1 = 11Using Excel,

Using the StatCrunch command sequence, Stat > Calculators > T. Get in the df and also alpha. Select the “≥” operator to gain the ideal tail. Click Compute. I favor StatCrunch for this due to the fact that it always creates the map out which helps avoid “dumb” tail errors.

The an essential value of t is 1.36 and also the rejection region is t > 1.36, the area in red.

Now we need to find the check statistic.

Although I have the right to do this utilizing the Compute function in StatCrunch, I favor to usage Excel because that this since I can save the record and reuse on similar problems:

Since t = 10.39 drops in the rejection region to the appropriate of t-critical = 1.36, we refuse the null hypothesis.

Now let’s usage the p-value approach.

First, using Excel:

Now using StatCrunch: usage the command sequence Stat > T Stats > One Sample > with Summary. Enter the sample mean, sample standard deviation, and n. Note: execute not transform the sample s come the traditional error (sigma below x-bar) as we did utilizing Excel since StatCrunch has that step built-in.

See more: 6 Tips From A Woman On How To Get Laid On The First Date, 10 Surefire Ways To Get Laid On The First Date

StatCrunch gives has the test statistic, 10.392, in the output in addition to the p-value

Getting the trust interval using Excel is not difficult though you have to recall we use the critical value the t because that alpha/2, which is the two-tail critical value even though we were to run a one-tail theory test. That trips increase a the majority of students who just use the t-critical for the rejection area.