Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
76 Cards in this Set
- Front
- Back
Alpha |
Level of Significance
Refers to the probability of rejecting the null hypothesis when it is true (Type I Error) Commonly .01 or .05 |
|
ANCOVA
Statistics |
Analysis of Covariance
A version of ANOVA used to increase the efficiency of analysis by statistically removing variability in the DV that is due to an extraneous variable. |
|
Autocorrelation
Statistics |
A disadvantage of the time-series and other within-subjects designs. Occurs when subjects' performenace on pst tests is likely to correlate with performance on pretests. Can inflate the value of t or F and therefore increases the probability of Type I error.
|
|
Between-Groups Design
Statistics |
Studies in which each level of the IV is given to a difference group of subjects.
|
|
Central Limit Theorem
Statistics |
The theorem derived from probablitity theory that predicts that the sampling distribution of the mean will:
1. approach normal as the sample increases 2. has a mean equal to the population mean 3. has a SD equal to the population SD divided by the square root of the sample size. |
|
Chi-Square Tests
Statistics |
Inferential statistic used with nominal scale data. Single sample used for one variable, multiple sample for 2 or more variables
|
|
Cluster Sampling
Statistics |
Selecting units or groups from the population, rather than individuals.
|
|
Correlation Coefficient
Statistics |
A numerical index of the relationship between two or more variables.
|
|
Pearson r
Statistics |
Correlation coefficient -- used when data on both variables are on a continuous scale.
|
|
Point Biserial
Statistics |
Correlation coefficient used when one scale is a true dichotomy and the other is a continuous scale.
|
|
Biserial
Statistics |
Correlation coefficient sued when one variable is an artificial dichotomy and the other is continuous.
|
|
eta
Statistics |
Correlation coefficient used when variables are continuous but have a nonlinear relationship.
|
|
Counterbalanced Design
Statistics |
A research design used to control carryover (order) efects; involves administering different levels of the IV to different subjects or groups of subjects in a different order. Includes Latin Square.
|
|
Cross-validation/Shrinkage
Statistics |
Validating a correlation coefficient on a new sample. Because the same chance factors are not in subsequent sample, the coefficient tends to "shrink" on cross-validation. Shrinkage is largest when original sample is small and number of predictors is large.
|
|
Demand Characteristics
|
Cues in the experimental situation that inform research participants of how they are supposed to behave during the study.
|
|
Discriminant Function Analysis
Statistics |
The multivariant technique used when there are two or more continuous predictors and one discrete (nominal) criterion. Multiple discriminant function analysis when the criterion has more than two categories.
|
|
True Experiment
Statistics |
Permits greater control of the experimental situation. Hallmark is random assignment to groups.
|
|
Experimental Research
Statistics |
Conducting a study to test hypotheses about the relationships between IV and DV.
|
|
Quasi-experimental Research
Statistics |
Research in which it is not possible to randomly assign to groups. IV is manipulated.
|
|
Experimentwise Error Rate
Statistics |
Probability of making Type I error. As number of statistical comparisons increases the experimentwise error rate increases. (Don't go fishing!)
|
|
External Validity
Statistics |
The degree to which a study's results can be generalized to other people, settings, conditions, etc.
|
|
Factorial ANOVA
Statistics |
Analysis of Variance
Used when a study includes two or more IV's. Also called two-way, three-way, etc. |
|
Factorial Design
Statistics |
A study which includes 2 or more factors (IV's).
|
|
Main Effects
Statistics |
In a factorial design, the effect of a single IV on the DV. Interaction effects may change interpretation
|
|
Interaction Effects
Statistics |
In a factorial design, occurs when the impact of the IV differs at different levels of another IV. Changes interpretation of main effect.
|
|
Independent Variable
Statistics |
Manipulated in experimental research for the purpose of determining effects on the DV. each IV must have at least 2 levels.
|
|
Dependent Variable
Statistics |
Observed or measured in a study and is believed to be affected by IV.
|
|
Internal Validity
Statistics |
The degree to which a research study allows an investigator to conclude that the observed variability of the dependent variable is due to the independent variable.
|
|
Maturation
Statistics |
Threat to internal validity. Occurs when a physical or psychological event occurs as a result of the passage of time and has a systematic effect on the DV.
|
|
History
Statistics |
Threat to internal validity. An event that is external to the study but effects performance on the DV in a systematic way.
|
|
Selection
Statistics |
Threat to internal validity. Occurs when participants in different treatment groups are initially different and therefore would differ at the end of the study even if no treatment had been applied. Threat when there has not been random assignment to groups.
|
|
Interval Recording
Statistics |
Method of behavioral sampling that involves dividing a period of time into discrete intervals and recording whether the event occurs in each interval.
|
|
Event Sampling
Statistics |
A method of behavioral sampling that is useful for behaviors that are rare or leave a permanent product. Involves recording each occurrence of a behavior during a predefined or preselected event.
|
|
LISREL
Statistics |
A causal (structural equation) modeling technique used to verify a predefined causal model or theory. Allows two-way paths, takes into account observed variables, and the latent traits they are believed to measure, and the effects of measurement error. More complex than path analysis.
|
|
MANOVA
Statistics |
Multivariate Analysis of Variance
A form of ANOVA used when a study includes one or more IV's and two or more DV's. Variable must be on interval or ratio scale. Helps to reduce experiment wise error. |
|
Measures of Central Tendency
Statistics |
Mean, Median, Mode
|
|
Mean
Statistics |
Arithmetic average of a set of scores. Can be used in interval and ratio scales.
|
|
Median
Statistics |
Middle score of a distribution of scores. Can be used with ordinal, interval, and ratio scales. Less affected by outliers than the mean.
|
|
Mode
Statistics |
The most frequent score in a distribution. Used with nominal categories. Susceptible to variations in sampling
|
|
Mixed Designs
Statistics |
Designs in which both between groups and within-groups comparisons can be made.
|
|
Multiple Regression
Statistics |
Multivariate technique used for predicting a score on a continuous criterion based on performance on two or more continuous or discrete predictors.
|
|
Multicolinearity
Statistics |
High correlations between predictors in multiple regression.
|
|
Normal Curve
Statistics |
Symmetrical bell-shaped distribution that is defined by a mathematical formula. 68% of scores occur within one SD of the mean, 95% occur with 2 SD of the mean, and 99% occur within 3 SD of the mean.
|
|
Null Hypothesis
Statistics |
Stated in a way that implies that the independent variable does not have an effect on the Dependent variable. Goal to reject the null hypothesis.
|
|
One-way ANOVA
Statistics |
A parametric statistical test used to compare the means of two or more groups when a study includes one IV and one DV measured on an interval or ratio scale. Preferable to t-tests when there are more than three groups to control experimentwise error rate.
|
|
F-Ratio
Statistics |
Result of ANOVA. Indicates if means are significantly different if F is greater than 1.0. Represents the measure of the treatment effects plus error divided by a measure of error.
|
|
Parametric Tests
Statistics |
Inferential statistics used when assumptions (parametircs) are met:
1. interval or ratio scale 2. scores are normally distributed There is homoscedasticity (population variances are equal) |
|
Nonparametric tests
Statistics |
Less powerful that papmetric tests. Used with nominal and ordinal scales or when parametric assumptions are not met. Includes the chi-square, Mann-Whitney U and Wilcoxson matched pairs.
|
|
Path Analysis
Statistics |
A causal modeling technique used to verify a pre-defined causal model theory. Involves translating the theory into a path diagram, collecting data on the variables of interest, and calculating and interpreting path coefficients.
|
|
Protocol Analysis
Statistics |
Technique used by cognitive psychologists to identify the cognitions underlying problem-solving and decision-making. Involves having an individual "think aloud" while working and then analyzing the record (protocol) of the individual's verbalizations.
|
|
Random Assignment
Statistics |
Assigning subjects to treatment groups using a random method, central to "true" experimental research. Enables the conclusion that variability on the DV is due to the IV rather than random error.
|
|
Random Error
Statistics |
Error that is unpredictable. Sampling error is a type of random error.
|
|
Randomized Block Factorial ANOVA
Statistics |
ANOVA used when blocking has been used to control an extraneous variable. Allows an analysis of the main and interaction effects of the extraneous variable.
|
|
Regression Analysis
Statistics |
A statistical technique used to predict a score on a criterion based on the person's obtained score on a predictor. Involves the identification of a regression line (line of best fit) and the use of the equation for that line, the regression line.
|
|
Rejection and Retention Regions
Statistics |
Size of the rejection region is defined by alpha. The rejection region contains those values that are unlikely to be obtained simply as the result of sampling error. If the obtained sample falls in this region the null hypothesis is rejected.
|
|
Sampling Distribution of the Mean
Statistics |
Normally shaped distribution with a mean equal to the population mean. The distribution of sample means that would be obtained if an infinate number of sample means were randomly selected from the population and the mean for each sample calculated.
|
|
Standard Error of the Mean
Statistics |
The Standard deviation of the standard distribution of the mean. Equal to the population SD divided by the square root of the sample size. Used in inferential statistics to determine how likely it is to obtain a particlura sample mean given the population mean and population standard deviation, the sample size, and the level of significance.
|
|
Nominal Scale
Statistics |
Categories that are "named" Only yields frequency data
|
|
Ordinal Scale
Statistics |
Categories are arranged in "order" of amount of variable.
|
|
Interval Scale
Statistics |
Scale of measurement that has set intervals between points on the scale. allows for addition and subtraction functions.
|
|
Ratio Scale
Statistics |
Most sophisticated scale of measurement. Has an absolute zero. Able to use multiplication and division of scale.
|
|
Shared Variability
Statistics |
A correlation coefficient that can be squared to obtain a measure of shared variability. For example, if the corelation between X and Y is .50 this means that 25% of the variability on Y is shared with (or accounted for by) variability on X.
|
|
Single-Subject Designs
Statistics |
Used in behavioral research, esp. behavioral analysis. Contain at least one baseline (A) and one treatment (B) phase.
|
|
AB Design
Statistics |
Single subject design. Contains one baseline and one treatment phase.
|
|
Reversal Design
Statistics |
Single-subject designs. Include at least 2 baseline phases. (ABA, ABAB).
|
|
Multiple Baseline Designs
Statistics |
Single-subject designs. Involves sequentially applying the treatment in multiple baselines (different behaviors, settings, or subjects).
|
|
Skewed Distributions
Statistics |
Asymmetrical distributions in which most scores are on one side of the distribution. Positive...most scores are on the low (negative side) with the long tail on the high (positive side.
|
|
Standard Deviation
Statistics |
A measure of dispersion (variability) of scores around the mean of the distribution. Calculated by dividing the sum of the squared deviation scores by N (or n-1) and taking the square root of the result. Square root of the variance.
|
|
Statistical Power
Statistics |
Refers to the probablity of rejecting a false null hypothesis. Power can be increased by including a large sample, maximizing the effects of the IV, increasing the size of the alpha, and reducing error.
|
|
Systematic Error
Statistics |
Predictable error.
|
|
Extraneous Variables
Statistics |
A source of systematic error. Also called confounding variables.
|
|
t-tests
Statistics |
Parametric test used to compare two means. Single sample t-test is used to compare a single obtained sample mean to a known or hypothesized population mean. T-test for independent samples is used to compare two independent samples. t-test for correlated samples is used when groups are related in some way.
|
|
Trend Analysis
Statistics |
Type of ANOVA used to assess linear and nonlinear trends when the IV is quantitative.
|
|
Type I Error
Statistics |
Occurs when a true null hypothesis is rejected. Probability of making Type I error is Alpha.
|
|
Type II Error
Statistics |
Occurs when a false null hypothesis is retained. Probability of making Type II error is equal to beta (which is usually unknown.
|
|
Within-Subjects Designs
Statistics |
An experimental design in which each participant receives, at different times, each level of the IV (or combinations of the IVs) so that comparisons on the DV are made within participants rather than between groups.
|