AP Statistics
If our data comes from a simple random sample (SRS) and the sample size is sufficiently large, then we know that the sampling distribution of the sample means is approximately normal with mean μ and standard deviation. The spread of the sampling distribution depends on n and σ. σ is generally unknown and must be estimated. NOW…THEORY ASIDE AND ONTO PRACTICE ! AP Statistics, Section 11.12
SRS – size n Normal distribution of a population μ and σ are unknown To estimate σ – use “S” in its place Then the standard error of the sample mean is AP Statistics, Section 11.13
The z statistic has N (0,1) When s is substituted the distribution is no longer normal AP Statistics, Section 11.14
The t statistic is used when we don’t know the standard deviation of the population, and instead we use the standard deviation of the sample distribution as an estimation. The t statistic has n-1 degrees of freedom (df). AP Statistics, Section 11.15
Interpret the t statistic in the same way as the z statistic There is a different distribution for every sample size. The t statistic has n-1 degrees of freedom. Write t (k) to represent the t distribution with k degrees of freedom. AP Statistics, Section Density curves for the t distribution are similar to the normal curve (symmetrical and bell shaped) The spread is greater and there is more probability in the tails and less in the center. Using s introduces more variability than sigma. As d.f. increase, t(k) gets more normal
In statistical tests of significance, we still have H 0 and H a. We need to provide the mu in the calculation of the t statistic. Looking at the t table is fundamentally different than the z table. AP Statistics, Section 11.17
Assume SRS size n with population mean μ Confidence interval will be correct for normal populations and approx. correct for large n. AP Statistics, Section 11.18
Let’s suppose that Mr. Young has been told that he should mop the floor by 1:25 p.m. each day. We collect 12 sample times with an average of minutes after 1 p.m. and with a standard deviation of minutes. Find a 95% confidence interval for Mr. Young’s mopping times. AP Statistics, Section 11.19
10
Step 1: Population of interest: ◦ Mr. Young’s mopping time Parameter of interest: ◦ average time of arrival to mop Hypotheses ◦ H 0 : µ=25 min past 1:00 ◦ H a : µ>25 min past 1:00 AP Statistics, Section
We are using 1 sample t-test? Bias? ◦ SRS not stated. Proceed with caution. Independence? ◦ Population size is at least 10 times the sample size? ◦ We assume that Mr. Young has mopped on a lot of days Normality? ◦ Big sample size (> 30). No ◦ Sample is somewhat normal because the sample distribution is single peaked, no obvious outliers. AP Statistics, Section
Calculate the test statistic, and calculate the p-value from Table C AP Statistics, Section
Is the t-value of statistically significant at the 5% level? At the 1% level? Does this test provide strong evidence that Mr. Young arrives on time to complete his mopping? AP Statistics, Section Try this exercise on your calculator using: STAT TESTS Tinterval STAT TESTS T-Test
Wednesday: 11.6 – Thursday:11.13 – Friday:T-Test Worksheet AP Statistics, Section