A quick statistical test reference guide is presented to help shorten the learning curve for you as you proceed to the most challenging part of the dissertation process. It is not meant as a substitute for a good primer or course on statistics but rather a handy list of jargon that most doctoral students encounter.
One footnote - You can do this. You have help here. I will help you to complete your doctoral degree. And you might even end up surprising your self about how you feel about research. It is more fun than most students anticipate.
Alpha Level - The probability that a statistical test will find significant differences among groups. It is usually .05, .01 or .001 for most research studies.
One Way Analysis of Variance (ANOVA) - A statistical test that determines whether the means of two or more groups are statistically different. There is one dependent and one independent variable. F statistic
Analysis of Covariance (ANCOVA) - Same as ANOVA procedure but very helpful when you need to perform an adjustment on the dependent variable. For example, if pretesting shows differences prior to treatment, you may adjust the dependent variable before comparing groups for differences. F statistics
Correlation - the degree to which two variables are associated. The correlation coefficient is the measure of degree to which two variables are related and can range from 0 to +1 of positively correlated and 0 to -1 if negatively correlated. Lower case r indicates the correlation coefficient.
Descriptive Statistics - Basic statistics used to summarize and describe the data. Usually, mean, median, mode and measures of variation are included.
Dichotomous variables - Variables that have only two categories.
Discriminant Analysis - A grouping method that identifies characteristics that distinguish among groups.
Dummy Coding - A coding strategy where each value of a categorical variables in turned into its own dichotomous variables and coded either 0 or 1.
Factor Analysis - An exploratory form of a multivariate analysis that takes a large number of variables and clusters the factors that are explained by the interrelationships among the variables. Factor loadings are usually set at .30 or .40.
Hierarchical Linear Modeling - A multi level modeling procedure that works well for nested circumstances. Also called HLM. The are Level 2 and Level 3 models that are often used.
Linear Regression - A statistical technique used to find a linear relationship between one or more continuous independent variables and a continuous outcome or dependent variable. Multiple R is the statistic.
MANOVA - Multivariate Analysis of Variance, a statistical test that measures varying group effects using multiple dependent variables. F statistic.
Paired t-test - Usually used to determine before and after effects of an intervention. The lower case t is the statistic.
Power - The degree to which a statistical test will detect significant differences between groups in a sample.
T-test - A statistical test used to compare the means of two samples. Lower case t is the statistic.
Two Way ANOVA - The statistical test to study the effect of two categorical independent variables on a continuous variable or dependent variable. F is the statistic.
Return from the statistical tests reference guide to statistical tests.