Chapter 1 Study Guide - Dr. Alan Huebner PDF

Preview

Summary

Dr. Alan Huebner...

Description

Chapter 1 Study Guide Practice Problems: • •

From the text (answers are provided in the back of the book): 1.37, 1.45, 1.49 (the data can be quickly typed into R), 1.57 (parts a and c), 1.61, 1.65, 1.71 Also, Example 1.10, Example 1.17

Chapter 1 Learning Objectives: • • • • • • • • • • • •

Given a written problem, identify the population, sample, experimental units, and variables Distinguish between population parameters and sample estimates. Calculate the sample variance and sd “by hand” Calculate a confidence interval for any confidence level and interpret it in the context of the problem. Given a written problem, identify the null and alternative hypotheses. Given a written problem, identify the type of test to perform (e.g. single mean or two means, large or small sample, paired, lower, upper or two-tailed, etc.) Given sample statistics, perform all steps of a hypothesis test. Recite the definition of a p-value on page 43 of the text and apply it in a given context. Explain Type I and Type II error in the context of a specific hypothesis test. Write R code to obtain critical values and p-values, i.e. know how to use pnorm() and qnorm() Identify the inputs and outputs of the following R functions: library(), hist(), mean(), sd(), var(). Know how to access columns of an R data frame using the $ symbol. Identify the output when brackets [ ] are applied to a vector in R (this is known as “subsetting”).

Notes: •

The text presents two methods of performing a hypothesis test, (1) the p-value approach and (2) the critical value approach. We will only do (1), so anything about (2) can be ignored.

Chapter 3 Study Guide Chapter 3 Learning Objectives: Objectives for Exam 1: •

• • •

• •

• • • • •

Write down the linear regression model and identify all components (intercept, slope, error, predictor and response variable), sketch an ฀฀/฀฀ axis with these quantities labeled, and give conceptual explanations of each. 󰆹1 , and specific values of ฀฀ and ฀฀. Give Compute fitted values (฀฀�s) and residuals (฀฀s) given 󰆹฀฀0 , ฀฀ conceptual explanations of the ฀฀�s and ฀฀s, and sketch an ฀฀/฀฀ axis with these quantities labeled. Explain the concept of “least squares”, i.e. the linear regression line minimizes the sum of squared errors (SSE). Given a small data set (i.e ฀฀ and ฀฀�s) compute the SSE and ฀฀, and interpret ฀฀ is the context of a given problem.

Note: The objectives below will NOT be included on Exam 1 Compute and interpret a CI for ฀฀1 . Use the qt() function to obtain the critical value for the CI. Perform a hypothesis test for ฀฀1 . Calculate the test statistic given ฀฀󰆹1 and ฀฀�฀฀1 . Use the pt() function in R to compute the p-value. State the conclusion of the test, and give a conceptual explanation of the p-value. Explain the summary output for the lm() function in R including the columns Estimate, Std. Error, t value and Pr(>|z|). Explain the relation between a CI and test for ฀฀1 . Describe the concept of correlation between two variables. Perform a hypothesis test for a correlation. Interpret the coefficient of determination ฀฀ 2 and explain the concept via a sketch with the quantities ฀฀฀฀฀฀ and ฀฀฀฀฀฀฀฀ labeled....