SOC 200--Fall, 2009
M. Senter

Reading:  Social Statistics for a Diverse Society, Chapters 4, 5, 6, 7 (not including pages 138-44) .  (You may need to review earlier chapters.)

Practice (on the web page):    Measures of Central Tendency and Dispersion,

Practice on Percentage change and Percentage-Point Change,

Practice on Sampling (Part A only)

Consult Web Page: Tables; Introduction to SPSS; Introduction to Excel

The format of this exam will be the same as Exam #1--multiple-choice and short-answer.  You will NOT need to use SPSS or Excel during the exam.  However, for some questions, I will give you SPSS and/or Excel output and ask you to make sense of it. 

1. Be able to compute by hand (with a calculator) means, medians, and modes. Make sure that you can compute by hand the measures of central tendency from raw data (that is, from the actual data cases before they have been summarized in tables) and from data that have already been summarized in tables.

2.  Be able to find and make sense of commonly used percentiles such as deciles, quintiles, and quartiles.

3. Make sure that you know when each measure of central tendency is appropriate to use (given the variable's level of measurement) and that you know how to make sense of these statistics (in words) whether you create them by hand or interpret them from SPSS or Excel.

4.  Be able to calculate the percentage-point change and the percentage change.  (Review.  People had problems on Exam #1.)

5.  Be able to calculate by hand the range, interquartile range (IQR), and standard deviation. 

6.  Be able to know when each measure of variability (dispersion) is appropriate to use (given the variable's level of measurement) and that you know how to make sense of these statistics (in words) whether you create them by hand or interpret them from SPSS.

7.  Be able to make sense of box plots.

8.  What are the characteristics of the normal curve?  How do you know when a variable is normally distributed?  What percentage of all cases fall within 1, 2, and 3 standard deviations of the mean if a variable is distributed normally?  (These are the "benchmarks" that I asked you to memorize.)

9.  Know how to calculate a z-score and know how to interpret a z-score.

10.  Be able to use the Standard Normal Table (Appendix B in your textbook) to figure out the percentage of cases between the mean and various scores (given the standard deviation).  Be able to use the Standard Normal Table to figure out the percentage of cases between various scores (given the standard deviation and mean).  I will give you a copy of the Standard Normal Table during the exam.

11.  Be able to use the Standard Normal Table to figure out the percentage of cases above or below a particular score (given standard deviation and mean). 

12.  Be able to use the Standard Normal Table to figure out the percentile associated with a particular score (given the standard deviation and mean).

13.  Be able to use the Standard Normal Table to figure out the score you would need on a test (or variable) that is normally distributed to capture a given percentage of all cases (given the standard deviation and mean).  For instance, be able to figure out the score you would need to be in the top 20% of all scores.

14.    Be able to discuss the advantages of probability samples over nonprobability samples?

15.    Be able to distinguish between a population distribution, the distribution of sample observations, and a sampling distribution.

16.    What is the Central Limit Theorem (for means and for proportions) and why is it important?

17.    What are the main types of probability samples? Be able to draw a systematic sample with a random start and a simple random sample using a random number table.  (I will give you the random number table.  See Appendix A in your textbook.)

18.    Know how to create a stratified systematic sample with a random start and know why such stratification is desirable (when it is possible).

Other Concepts and Terms You Want to Understand:

raw data, tabular data, independent variable, dependent variable, level of measurement, nominal variables, ordinal variables, interval-ratio variables, dichotomous variables, individual as the unit of analysis, aggregate (such as a city or household) as the unit of analysis, artifact as the unit of analysis, table, graph, figure, histogram, frequency, cumulative frequency, proportion, p, pi, percent, valid percent, missing data, cumulative percent, univariate statistics, measures of central tendency, Y, Y-bar, mu,  mean (average), median, mode, percentile, decile, quintile, quartile, score or code, recode, symmetrical distribution, positive skew, negative skew, skewed distribution, outlier, measures of variability (dispersion), range, minimum (lowest score), maximum (highest score), interquartile range (IQR), Q1, Q3, box (and whisker) plots, variance, standard deviation, s, sigma, raw score, z-score, positive z-score, negative z-score, standard score, normally distributed, normal distribution (as a theoretical distribution), bell-shaped curve, areas under the normal curve, Standard Normal Table, probability sample, representativeness, population, parameter, survey sample, sample statistic, generalizing from a sample to the population, population distribution, distribution of sample observations, sampling distribution of the mean, sampling distribution of the proportion, sampling error, sampling element, sampling frame, simple random sample, random number table, systematic samples with a random start, k or the sampling interval (POPULATION N/SAMPLE N), stratified sample

Formulae:

I will give you the formulae for the mean, standard deviation, variance, and z.
 

• Bring a calculator with you to the exam.

RETURN TO MAIN PAGE