Terms in this set (88)
Describes quality of relationships, actions, situations. Naturalistic context approach, inductive, and reflects investigators perspective. Examples) ethnographic, phenomenological, and research based on grounded theory. Methods: observations, interviews, and documented analysis.
Numerical data on variables. Emphasizes predictions, generalizability, and causality. Deductive in nature. Can be non-experimental (descriptive) research to collect data, but not test the hypothesis; ex) correlations, archival, and surveys. Can also be experimental research to test the hypothesis and test the effects of one or more independent variables on dependent variables.
Treatment or intervention tested to affect an outcome (DV). Symbolized as letter "X" and must have at least 2 levels of treatment for comparison.
The measured outcome of a study using the IV to test a hypothesis. Symbolized by the letter "Y."
Literally the "middle" variable. IV affects it which then affects the DV. May test this variable using Multiple Regression.
Affects direction and strength of IV and DV. Ex) an IV works better the older the participant is; age is the moderator and can be tested as an IV itself.
True Experimental Design
Only type that provides amount of control necessary to conclude observed DV variability is from IV. Also is able to randomly assign subjects.
Cannot randomly assign participant to conditions. Has preexisting groups or single group without control comparison.
Each element in the target population has a known chance being selected for inclusion in the sample. Is used to ensure sample is representative of sample population.
Extraneous (Confound) Variable
A source of systematic error that affects the relationship between IV and DV.
Error that is unpredictable (random). Sampling error and measurement error are types.
How sure the experimenter can be that the IV caused change in the DV.
Threat to validity; physical change, event, or psychological process occurs as the result of the passage of time; ex) fatigue, decreasing motivation). To control: more than one group and randomly assign to groups.
Threat to validity; an event that is external to the research study affects subject's performance on the DV in a systematic way. Control by: having more than one study group and randomly assign participants
Threat to validity; Extreme scores regress towards the mean. Control by: Don't include only extreme scores in the study or use more than one group and all groups have similarly extreme scores.
Threatens internal validity when groups differ at the beginning of the study because of the way subject were assigned to groups and is a potential threat whenever subjects are not randomly assigned to groups.
Degree to which a study's results can be generalized to other people, settings, and conditions. *Internal validity is required to achieve ____.
Threat to External validity; Occurs when pretesting affects how subjects react to the treatment. Control by: not administering a pretest or use solomon 4-group design.
Threat to external validity; Occurs when subjects respond differently to a treatment because they know they are participating in a research study. 2 types: 1) Evaluation Apprehension: avoid negative evaluation. 2) Demand Characteristics: cues in a study that inform subjects of purpose of study or expected behavior.
Between Groups Designs
Experimental research designs that allow a research to assess the effects of the different levels of one or more IVs by administering each level or combination of levels to a different group of subjects. ***Simply put: each level of IV to a different group.
Research designs that include two or more "factors" (IVs). They permit the analysis of main and interaction effects.
The effect of a single IV on the DV.
The effects of one IV at different levels of another IV.
Within Subjects Design
Research designs in which each subject receives, at different times, each level of the IV (or combinations of the IVs) so that comparisons on the DV are made within subjects rather than between groups.
Type of factorial design in which at least one IV is a between-groups variable and one IV is a within-subjects variable.
Single Subjects Designs
Research designs that include at least one A (baseline-without treatment) and one B (treatment-person is own control) phase and include multiple measurements of the DV at regular intervals during each phase.
Type of Single Subjects design; includes a single baseline phase (A) and single treatment phase (B), with the treatment being withdrawn ("reversed"- take away treatment, measure, and readminister to confirm findings) (e.g. ABA or ABAB design) during the second and subsequent baseline phases. No reversal if unethical ( causes harm). Can't conclude if effects persist after treatment (B) is removed.
Multiple Baseline Design
Type of Single Subjects design; Involves sequentially applying a treatment to different baselines (e.g. to different behaviors, settings, tasks, or subjects).
Nominal Scale of Measurement
Divides variables into unordered categories. Ex) gender or age.
Ordinal Scale of Measurement
Divides variables into ordered categories. Ex) 1st, 2nd, 3rd places in a race.
Interval Scale of Measurement
Variables are ordered and have equal intervals of measurement. Does not have an absolute zero. Ex) Temperature.
Ratio Scale of Measurement
Variables are ordered and have equal intervals and an absolute zero. Ex) Kelvin scale.
Symmetrical, bell-shape distribution, can be defined by mathematic equation and predict based on knowledge of one variable. Areas: 68%- fall between the scores that are plus and minus two standard deviations from the mean; 95%- fall between the scores that are plus and minus 3 standard deviations from the mean.
Asymmetrical distribution. Determine if negative or positive by where the tail is. Positive- more scores on the low end. Negative- more scores on the high end.
Most common score in a set. If there are two most commonly occurring the set is bimodal. Easy to find, but not necessarily useful.
Divides scores in half when ranked from highest to lowest.
Sum of scores divided by the number of scores. Less susceptible to sampling fluctuations. Can be thrown off by extreme outlier scores.
Standard Deviation (SD)
Square root of the variance. Larger the SD the greater the scores disperse around the mean.
Areas Under the Normal Curve
68.26%- scores fall within 1 SD above and below the mean. 95.44%- scores fall between above and below 2 SD. 99.7%- scores fall between above and below 3 SD. 34% of scores found between mean and 1 SD or vice versa.
Distribution of sample means that would be obtained if an infinite number of equal-size samples were randomly selected from the population and the mean for each sample was calculated. Resembles a normal curve.
Central Limit Theorem
Derived from Probability Theory. Predicts that sampling distribution of the mean 1) will approach a normal shape as the sample size increases, regardless of the shape of the population distribution of the scores, 2) has a mean equal to the population mean, and 3) has a SD equal to the population SD divided by the square root of the sample size.
Standard Error of the Mean
SD of sampling distribution of the mean (how much the mean of a sample can be expected to vary from population mean due to sampling error). Larger the sample size, the smaller the SEM.
The IV does NOT have an effect on the DV.
IV DOES have an effect on the DV.
Sample values that unlikely to occur as a result of sampling error; reject the null hypothesis. *defined by alpha.
Central portion of sampling distribution. Values likely to occur due to error; fail to reject the null hypothesis. *is equal to one minus alpha.
Determines the probability of rejecting the null hyopthesis when it is true (probability of making a Type I Error). The value is set by the examiner prior to collecting or analyzing data. Is commonly set to .01 or .05.
Type I Error
Occurs when a true null hypothesis is rejected (rejected the null, but null was valid). Probability of making this type of error is alpha.
Type II Error
Occurs when a false null hypothesis is retained (failed to reject the null when alternative hypothesis was valid). Probability of making this type of error is B (power).
Probability of rejecting a false null hypothesis. Power cannot be directly controlled but is increased by having a large sample, maximizing the effects of the IV, increasing the size of alpha, and reducing error.
Inferential statistical tests used when data to be analyzed (DV) is on an interval or ratio scale and when certain assumptions about the population distribution(s) have been met...i.e. when scores on the variable of interest are normally distributed and when there is homoscedasticity (population variances are equal). This includes t-tests and ANOVAs. Advantage: more "powerful" than nonparametric tests.
Inferential statistics test used to analyze nominal or ordinal data. Includes chi-square. Less powerful test.
Nonparametric test used with nominal data. Analyzes frequency of observations in each level or category. The groups are independent and no frequency expected less than 5.
Single Sample Chi-Square
Used when the study includes one variable with multiple categories. "Goodness of Fit."
Used when the study includes two or more variables with different categories.
Parametric test used to compare two means.
t-test for Single Sample
Used to compare a single obtained sample mean to a known or hypothesized population mean.
t-test for Independent Samples
Used to compare means from two independent groups.
t-test for Correlated Samples
Used to compare two sample means when subjects in the two groups are related in some way (e.g. because they were matched on an extraneous variable or because a single-group pretest/post-test design was used).
Parametric test used to compare the means of two or more groups when a study includes one IV and one DV that is measure on an interval or ratio scale.
Multivariate technique used to group people or objects into a smaller number of mutually exclusive and exhaustive subgroups (clusters) based on their similarities (i.e. to group people/objects so that the identified subgroups have within group homogeneity and between group heterogeneity).
Factorial Analysis of Variance
Used when study includes two or more IV's and a single DV that is measure on an interval or ratio scale. Also known as a two-way ANOVA, three-way ANOVA, etc. with the numbers "two" and "three" referring to the number of IVs.
Randomized block ANOVA
Used when blocking has been used a as a method for controlling an extraneous variable (i.e., when the extraneous variable is treated as an independent variable). Allows an investigator to statistically analyze the main and interaction effects of the extraneous variable.
Used to increase the efficiency of the analysis by statistically removing variability in the DV that is due to an extraneous variable. Each person's score on the DV is adjusted on the basis of their score on the extraneous variable.
Linear structural relations analysis used to verify a predefined causal model or theory. More complex than path analysis and it allows two-way (non-recursive) paths and takes into account observed variables, the latent traits they are believed to measure and the effects of measurement error.
Mixed (Split-Plot) ANOVA
Type of factorial ANOVA that is used when a study includes at least one between-groups IV and one within-subjects IV.
Multivariate Analysis of Variance (MANOVA)
Used when a study includes one or more IVs and two or more DVs that are each measured on an interval or ratio scale. Helps reduce the experimentwise error rate (probability of making a Type I error) and increases power by simultaneously analyzing the effects of the IV(s) on all of the DVs.
Measure of the magnitutde of the relationship between IVs and DVs and is useful for interpreting the relationship's clinical or practical significance (e.g. for comparing clinical effectiveness of two or more treatments).
Indicates the difference between two groups in terms of SD units.
Indicates the percent of variance in the dependent variable that is accounted for by variance in the IVs.
Single number depicting degree of association between variables.
Used to predict a score on one criterion based on the person's obtained score on one predictor. Involves identifying the location of the regression line ("line of best fit") and using the equation for that line, the regression equation, to make predictions.
Correlation coefficient for two or more variables can be squared to obtain a measure of _______. Ex) if the correlation between X and Y is .50 this means that 25% of variability in Y is shared with (or is accounted for by) variability in X.
Least Square Criterion
Used to locate the regression line so that the amount error in prediction is minimized.
Multivariate technique used for predicting a score on a continuous criterion based on performance on two or more continuous and/or discrete predictors.
Pearson r Coefficient
Used when data on variables represent a continuous scale. *2 interval or ratio variables.
High correlations between predictors.
Spearman rho Coefficient
Used when both variables are ranks.
Validating a correlation coefficient on a new sample (e.g. a criterion-related validity coefficient).
Discriminant Function Analysis
Appropriate multivariate technique when two or more continuous predictors will be used to predict or estimate a person's status on a single discrete (nominal) criterion.
Because the same chance factor operating in the original sample are not operating in the subsequent sample, the correlation coefficient tends to "shrink" on cross-validation. Greatest when the original sample is small and the number of predictors is large.
Point Biserial Coefficient
Used when One variable is a true dichotomy and the other is continuous variable.
Used to verify a predefined causal model or theory. Involves translating the theory into a path diagram, collecting data on the variables of interest (the observed variables) and calculating and interpreting path coefficients indicating strength/direction of relationship between pairs of variables. If pattern fits predicted from theory it supports the theory.
Used when the variables are both continuous and have a nonlinear relationship. *2 interval/ratio.
Used when one variable is an artificial dichotomy and the other is continuous (interval/ratio).
Experimentwise Error Rate
The probability of making a Type I error. As the number of statistical comparisons in a study increases, probability of making a type I error increases.
Indicates if any group means are significantly different. Represents a measure of treatment effects plus error divided by a measure of error only. When the treatment has had an effect, the ratio is larger than 1.0.