Web version [missing some pieces]
INFORMATION ABOUT THE MIDTERM: There will be four sections: (1) questions based on core concepts and skills related to Chapters 1-5, (2) a normal curve/ hypothesis testing section (Chapters 6-10), (3) an "advanced concepts" section (in which you will be asked to demonstrate your understanding of the core concepts related to distributions, the normal curve, and hypothesis testing) and (4) interpreting SPSS output section (in which you will interpret the output for a t-test). Below are practice questions, a list of possible questions for the advanced concepts section, and a list of formulas you should know. Recommendation: Do the practice questions over the weekend; you will be going over these in lab next Monday/Tuesday.
Practice Questions for Midterm, 302:
1. Create a histogram (ungrouped) from the following frequency table. Label your axes.
[sorry, not available except in printed version]
Describe the distribution in words: _________________ and ______________________.
2. Draw (A) a normal distribution (B) a rectangular distribution (C) a bimodal distribution and (D) a sampling distribution for B, when n=20.
A. B.
C. D.
3. Jerry scores 4.5 on a stats anxiety question. The population mean for stats anxiety is 3, and the variance is 16.
A. What is Jerry's Z-score? SHOW YOUR WORK!!
B. Fatima has a Z-score of -2 on stats anxiety. What was her score on the stats anxiety question? SHOW YOUR WORK!!
C. What is the variable in the preceding two questions? ______________
4. Ranges:
A. Probabilities range from ________ to _______.
B. Z-scores in the middle 96 percent of a normal distribution range from ______ to _______.
5. There will be a question on the midterm that gives you a research question, a sample size and mean, and possibly some other information. From this information, you need to be able to decide which test is appropriate (z-test, single sample t, or independent samples t) formulate and test a hypothesis, using the steps outlined in lectures and the book. At the end of the process, you will need to give an answer to the research question.
Know the step by step procedure backwards and forwards, so that you will be able to take the information given and jump right into action.
6. Hypothesis Testing : Explain the research situation that calls for the following tests:
a. z-test:
b. single sample t-test:
c. independent samples t-test:
7. Hypothesis Testing Cont.
Research question (step 0): "Do first born children have above average IQs?" For the general population, the parameters are myuu = 100 and sigma = 15. State two hypotheses, do a hypothesis test, and then give your answer to the research question. I've provided a sample mean for step 4. SHOW YOUR WORK, including any FORMULAS used. Be sure to note any decisions you make (about alpha and number of tails, for example, and justify your choices).
1. State the two hypotheses, and select the alpha level:
2. Find critical value(s) and shade in critical region(s) on the sampling distribution:
3. Collect data & calculate your test statistic (Assume you have collected data and have a sample mean for 20 first born children = 105).
4. Make decision about H0:
5. What's your answer to the research question, in ordinary English (not statistical jargon) based on this test?
8. In the "advanced concepts" section of the midterm, you will be asked to explain a few concepts (or relations between concepts) such as the following. Your study guide is very useful in explaining these. You will need to be able to explain these *In your own words.* Feel free to draw pictures too if they help you to explain.
Why we make the n-1 correction when estimating the population variance using sample data
Relation between sampling distribution, population distribution, and the distribution of sample
How the astronomer's error law and the normal distribution are related
Why the central limit theorem (CLT) is important for hypothesis testing
Give two reasons that a large sample size is useful in testing hypotheses.
Why a sampling distribution is necessary for hypothesis testing
Why the null hypothesis is necessary for hypothesis testing
The relation between the normal curve and significance level
Why the failure to reject the null hypothesis does not "prove" our alternative hypothesis is wrong
Why we need to use a t-distribution instead of the normal curve when doing t-tests.
9. Know formulas for Mean, Pop & Sample Variance, Pop & Sample Standard Deviation, Z-score (for X scores and for sample means), finding raw score (X) from Z-score, t-statistic (signle sample and independent measures) & Standard Error (for z or t test) handy to consult. Most not are on the inside front cover of your book for easy reference.
[There is also an "interpret this SPSS printout" question in printed version]