Skip to main content

EDUC/PSY 6600 Pretest Study Guide

The EDUC/PSY 6600 pretest consists of 30 randomly selected test questions from a large test bank. The content of the pretest is based on the objectives of a typical undergraduate social science statistics course, which are as follows:

To understand the selection, computation, and interpretation of descriptive and inferential statistics, including:

1) Organizing, describing, transforming, and graphing data;
2) Measures of central tendency and variability;
3) The normal distribution;
4) Hypothesis testing and estimation with 1 and 2 samples;
5) One-Factor ANOVA; and subsequent post hoc, multiple comparison procedures;
6) Correlation; simple linear regression;
7) Chi square tests for frequencies for 1 and 2 samples.

To successfully pass the pretest, students should be able to define the terms and concepts listed below at a basic level. Additionally, students should know how to compute the following by hand: basic math (equivalent to high school algebra), mean, median, mode, range, standard error of the mean, and z-scores. A score of 70% correct is required to pass the pretest. Students who need additional preparation for the test should review a good introductory statistics text such as Essentials of Statistics for the Behavioral Sciences by Gravetter and Wallnau.

  1. Basic Concepts
  • The goals of users of statistics: to organize, summarize, and describe numeric information and to make inferences from the data
  • Populations and Samples
  • Parameters and Statistics
  • Variables
  • Continuous and Categorical variables
  • Independent and Dependent variables
  • Measurement scales
    1. Nominal
    2. Ordinal
    3. Interval
    4. Ratio
  • The summation symbol, Σ (“sigma”), summation notation, and rules for summation
  1. Frequency Distributions
  • Advantages of organizing data into a frequency distribution
  • Intervals of a frequency distribution
  • Histograms
  • Shapes of distributions
    1. Normal
    2. Skewed
    3. Flat or peaked
  • Characteristics of the standard normal distribution
  1. Measures of Central Tendency
  • The purpose of using measures of central tendency
  • Mean
  • Median
  • Mode
  • Formula for the mean
  • Advantages, uses, and limitations of mean, median, and mode
  • Respective symbols for the population and sample mean
  1. Measures of Variability
  • The concept of variability of scores in a distribution
  • Range
  • Deviation scores
  • Sum of squared deviation scores or “Sums of Squares”
  • Variance and the standard deviation
  • Difference between population and sample formulae for the variance and standard deviation
  • Respective symbols for the population and sample variance/standard deviation
  1. z-scores
  • z-scores as a standard way of describing a score’s position within a distribution
  • Converting a raw score to a z-score
  • Converting a z-score to a raw score
  • Interpreting positive and negative z-scores
  • Interpreting a z-score of zero
  1. Probability, Random Samples, and the Sampling Distribution of the Mean
  • Random samples
  • Independent vs. dependent samples
  • Random sampling vs. random assignment
  • Sampling error
  • Central Limit Theorem and the mean and variance of a sampling distribution
  • Distribution of sample means or “sampling distributions”
  • Standard Error of the Mean
  • Relationship between sampling error, n-size, and the Standard Error of the Mean
  1. Hypothesis Testing
  • Research hypotheses vs. statistical hypotheses
  • Null and alternative hypotheses: What does each hypothesis state?
  • Tests of statistical significance, critical values, and how to decide whether a result is likely given the null hypothesis
  • Kinds of errors that can be made in interpreting p values from tests of statistical significance
    1. Type I error
    2. Type II error
  • The α-level or Type I error rate
  • Directional (one-tailed) vs. non-directional (two-tailed) hypotheses
  • The relationship between sample size and statistical significance
  • Situations in which a one-sample z-test might be used
  1. The t Statistic and the One-Sample t-test
  • Situations in which the t-test is used instead of the z-test
  • Null hypothesis for the one-sample t-test
  1. The Independent-Samples t-test and the Dependent-Samples t-test
  • Situations in which an independent samples t-test is used
  • The null hypothesis for the independent samples t-test
  • Situations in which a dependent samples t-test is used
  • Effect sizes: Using Cohen’s d or the point-biserial correlation coefficient to describe the magnitude of the mean difference
  1. Estimation
  • Confidence intervals
  • Relationship between the precision of an estimate, the standard error of the mean, and the width of confidence intervals
  • Relationship of confidence intervals to hypothesis testing
  1. One-Factor Analysis of Variance (ANOVA)
  • Situations in which ANOVA is used instead of an independent samples t-test
  • The null hypothesis in the 1-way ANOVA
  • Components of the 1-way ANOVA summary table:
    1. Sums of Squares
    2. Mean Squares
    3. F-ratio or F-statistic
  • Interpretation of a statistically significant F-ratio in ANOVA
  • Multiple comparison methods for testing individual pairs of means
  • Effect size: eta squared or η2
  1. Correlation and Simple Regression
  • Meaning of correlation between two variables
  • Situations in which the Pearson correlation coefficient might be used
  • Interpreting the correlation coefficient
  • Situations in which regression is used
  • The regression equation
    1. Interpretation of the intercept and slope coefficients
    2. Using the regression equation to predict a value for the dependent variable
    3. Chi-Square Tests for one and two variables: Tests of Goodness of Fit and Independence
  • Situations in which a Chi-square Goodness of Fit test is used
  • Situations in which a Chi-square Test of Independence is used
  • Effect size: phi coefficient and Cramer’s V