Lecture 9 Introduction to Inference Recall: Statistical inference is making a decision or a conclusion based on the data. Example: Researchers want to know if a new drug is more effective than a placebo. Twenty patients receive the new drug, and twenty receive a placebo.
Twelve (60%) of those taking the drug show improvement
only 8 (40%) of the placebo patients VERSUS
We would conclude that the new drug is better. However, probability calculations yell us that a difference this large or larger between the results in the two groups would occur about one time in five simply because of chance variation. Since this probability is not very small, it is better to conclude that the observed difference is due to chance rather than a real difference between two treatments.
Example: The SAT test is a widely used measure of readiness for college study. Originally, there were two sections, one for verbal reasoning ability (SATV) and one for mathematical reasoning ability (SATM). Suppose you want to estimate the mean SATM score for the more than 420,000 high school seniors in California. You know better than to trust data from the students who choose to take the SAT. Only 45% of California students take the SAT. These self-selected students are planning to attend college and are not representative of all California seniors. At considerable effort and expense, you give the test to an SRS of 500 California high school seniors.
The mean score for your sample is the population of all 420,000 seniors?
. What can you say about the mean score
Statistical Confidence Suppose the entire population of SAT scores had mean .
and standard deviation
Confidence Intervals (CI) Figure below illustrates the behaviour of 95% CIs in repeated sampling. The center of each interval is at and therefore varies from sample to sample. The sampling distribution of variation.
appears on the top of the figure to show the long-term pattern of this
Two important things about a CI: It is an interval of the form (a, b), where a and b are numbers computed from the data. It has a property called a confidence level that gives the probability of producing an interval that contains the unknown parameter.
Let's denote a confidence level by C, e.g. 95% confidence means C = 0.95.
Definition: A level C confidence interval for a parameter is an interval computed from sample data by a method that has probability C of producing an interval containing the true value of the parameter.
CI for a Population Mean Let Denote
be an SRS from a population with mean .
and standard deviation .
Definition: Choose an SRS of size n from a population having unknown mean
known standard deviation . The margin of error for a level C confidence interval for is
is the value on the standard Normal curve with area and
between the critical
The level C or 100(
% confidence interval for
This interval is exact when the population distribution is Normal and is approximately correct when n is large in other cases.
Example: The National Student Loan Survey collected data about the amount of money that borrowers owe.
The survey selected a random sample of 1280 borrowers who began repayment of their loans between four to six months prior to the study. The mean debt for the selected borrowers was $18,900 and we assume that σ = $49,000. Find a 95% CI for the mean debt for all borrowers.
Conclusion: We are 95% confident that the mean debt of all borrowers is between $16,200 and $21,600.
How does a sample size affect the CI? Let n = 320.
To reduce ME: Increase n Reduce Choose smaller C How does a confidence level affect the CI?
Choosing Sample Size
The CI for a population mean will have a specified margin of error ME when the sample size is
Example: How many students should we survey if we want ME=$2,000? , for 95% CI
Inference for a Single Proportion Choose an SRS of size n from a large population with unknown proportion p of successes. The sample proportion is
, where X is the number of successes.
CI for p is
is the value for the standard Normal density curve with area and .
is the margin of error for the given confidence level.
Note: Use this interval for 90%, 95%, or 99% confidence when the number of successes and the number of failures are both at least 15.
Alcohol abuse has been described by college presidents as the number one problem on campus, and it is a major cause of death in young adults. How common is it? A survey of 13,819 students in four-year colleges collected information on drinking behavior and alcohol-related problems. The researchers defined “binge drinking” as having five or more drinks in a row for men and four or more drinks in a row for women. “Frequent binge drinking” was defined as binge drinking three or more times in the past two weeks. According to this definition, 3140 students were classified as frequent binge drinkers.
Conclusion: We estimate with 95% confidence that between 22% and 23.4% of college students are binge drinkers.
Plus Four CI for a Single Proportion Choose an SRS of size n from a large population with unknown proportion p of successes. The plus four estimate of the population proportion is
where X is the number of successes. The standard error of
An approximate 100(
is as before.
)% CI for p is
Use this interval for 90%, 95%, or 99% confidence whenever the sample size is at least n = 10. Example: Research has shown that there are many health benefits associated with a diet that contains soy food. Substances in soy called isoflavones are known to be responsible for these benefits. When soy foods are consumed, some subjects produce a chemical called equol, and it is thought that production of equol is a key factor in the health benefits of a soy diet. Unfortunately, not all people are equol producers; there appear to be two distinct subpopulations: equol producers and equol nonproducers.
A nutrition researcher planning some bone health experiments would like to include some equol producers and some nonproducers among her subjects. A preliminary sample of 12 female subjects were measured, and 4 were found to be equol producers. We would like to estimate the proportion of equol producers in the population from which this researcher will draw her subjects.
Conclusion: We estimate with 95% confidence that between 14% and 61% of women are equol producers.
Hypothesis Testing A hypothesis is a conjecture about the distribution of some random variables. For example, a claim about the value of a parameter of the statistical model.
There are two types of hypotheses: The null hypothesis,
, is the current belief.
The alternative hypothesis,
, is your belief; it is what you want to show.
Examples: Each of the following situations requires a significance test about a population mean. State the appropriate null hypothesis and alternative hypothesis in each case.
(a) The mean area of the several thousand apartments in a new development is advertised to be 1250 square feet. A tenant group thinks that the apartments are smaller than advertised. They hire an engineer to measure a sample of apartments to test their suspicion.
(b) Larry's car consumes on average 32 miles per gallon on the highway. He now switches to a new motor oil that is advertised as increasing gas mileage. After driving 3000 highway miles with the new oil, he wants to determine if his gas mileage actually has increased.
(c) The diameter of a spindle in a small motor is supposed to be 5 millimeters. If the spindle is either too small or too large, the motor will not perform properly. The manufacturer measures the diameter in a sample of motors to determine whether the mean diameter has moved away from the target.
Guidelines for Hypothesis testing Hypothesis testing is a proof by contradiction. The testing process has four steps: Step 1: Assume
Step 2: Use statistical theory to make a statistic (function of the data) that includes . This statistic is called the test statistic. Step 3: Find the probability that the test statistic would take a value as extreme or more extreme than that actually observed. Think of this as: probability of getting our sample assuming is true. This is what we'll call a P-value. Step 4: If the probability we calculated in step 3 is high it means that the sample is likely under and so we have no evidence against . If the probability is low, there are two possibilities: - we observed a very unusual event, or - our assumption is wrong
Test Statistic • The test is based on a statistic that estimates the parameter that appears in the
hypotheses. Usually this is the same estimate we would use in a confidence interval for the parameter. When is true, we expect the estimate to take a value near the parameter value specified in
• Values of the estimate far from the parameter value specified by give evidence against . The alternative hypothesis determines which directions count against . • A test statistic measures compatibility between the null hypothesis and the data. • To assess how far the estimate is from the parameter, standardize the estimate. In many common situations the test statistics has the form
Example: An air freight company wishes to test whether or not the mean weight of parcels shipped on a particular route exceeds 10 pounds. A random sample of 49 shipping orders was examined and found to have average weight of 11 pounds. Assume that the standard deviation of the weights is 2.8 pounds.
P-values Definition: The probability, assuming is true, that the test statistic would take a value as extreme or more extreme than that actually observed is called the P-value of the test. The smaller the P-value, the stronger the evidence against provided by the data. Guideline for how small is “small”:
P-value > 0.1 provides no evidence against . 0.05 < P-value < 0.1 provides weak evidence against . 0.01 < P-value < 0.05 provides moderated evidence against P-value < 0.01 provides strong evidence against .
We can compare the P-value we calculate with a fixed value that we regard as decisive. The decisive value of P is called the significance level (denoted by ). Most common values for are 0.1, 0.05, 0.01. If the P-value is as small or smaller than , we say that the data are statistically significant at level . In other words, the P-value is the smallest level of significance for which the null hypothesis should be rejected.
For example, P-value = 0.03 is significant at the level level .
, but not significant at the
Example: 85% of the general public is right-handed. A survey of 300 chief executive officers of large corporations found that 95% were right-handed. Is this difference in percentages statistically significant? Use . Find the P-value for the test.
Tests for a Population Mean ( is known) z-test: To test the hypothesis (where is the specified value of ) based on an SRS of size n from a population with unknown mean and known standard deviation , compute the test statistic
In terms of a standard Normal random variable Z, the P-value for a test of
is These P-values are exact if the population distribution is Normal and are approximately correct for large n in other cases.
Example: In 1999, it was reported that the mean serum cholesterol level for female undergraduates was 168 mg/dl with a standard deviation of 27 mg/dl. A recent study at Baylor University investigated the lipid levels in a cohort of sedentary university students. The mean total cholesterol level among n = 71 females was . Is this evidence that cholesterol levels of sedentary students differ from the previously reported average?
Two-sided significance tests and CIs Recall:
Example: The Deely Laboratory analyzes specimens of a pharmaceutical product to determine the concentration of the active ingredient. Such chemical analyses are not perfectly precise. Repeated measurements on the same specimen will give slightly different results. The results of repeated measurements follow a Normal distribution. The standard deviation grams per liter. The laboratory analyzes each specimen three times and reports the mean result. The laboratory has been asked to evaluate the claim that the concentration of the active ingredient in a specimen is 0.86 grams per liter. The true concentration is the mean of the population of repeated analyses. So they would test: The lab chooses
Three analyses of one specimen give concentrations:
0.8403 From the data
, sample size n = 3, and we know
Let's find a 99% CI for the mean concentration.
Note: A level two-sided significance test rejects a hypothesis the value falls outside a level confidence interval for .
Testing Hypotheses on a Proportion Draw an SRS of size n from a large population with unknown proportion p of successes. To test the hypothesis , compute the z statistic
In terms of a standard Normal random variable Z, the approximate P-value for a test of against
Example: According to the National Institute for Occupational Safety and Health, job stress poses a major threat to the health of workers.
A national survey of restaurant employees found that 75% said that work stress had a negative impact on their personal lives. A sample of 100 employees of a restaurant chain finds that 68 answer “Yes” when asked, “Does work stress have a negative impact on your personal life?” Is this good reason to think that the proportion of all employees of this chain who would say “Yes”, differs from the national proportion p0=0.75?
Conclusion: The restaurant data are compatible with the survey results.