Statistics and Research design 2
Terms
undefined, object
copy deck
- AB Design
- a single-subject research design involving a single basline (A)phase and a single treatment (B) phase.
- ANCOVA (analysis of covariance)
- a variation on the analysis of variance procedure that allows for the statisitical control of one or more extraneous (irrelevant)variables. Ex: when studying effects of reading programs for diff. aged children, the effects of the children's IQ level can be statistically controlled through the use of ANCOVA.
- alpha
- the prob. of rejecting the null hypothesis when it is true (prob. of making a Type I error) The value of alpha is set by the researcher in advance, usually at .01 or .05.
- ANOVA (analysis of variance)
- a statistical test used to assess the differences btwn 2 means.
- Alternative Hypothesis
- the statistical hypothesis that states the opposite of the null hypothesis: usually predictst hat there is a relationship btwn variables
- Beta
- the probability of retaining the null hypothesis when it is false (prob. of making a Type II error)
- blocking
- a method of controlling an extraneous variable by making it another independent variable in a study in order to statistically analyze its effects on the dependent variable.
- case study
- an in-depth study of a single individual or other single unit (Group, family, institution)
- central limit theorem
- statistical theory stating that, as a sample size increases, the shape of the sampling distribution of means approaches normality and its mean approaches the population mean.
- Chi-Square Test
- inferential statistical test used when the data are frequencies of observations within categories. Test the hypothesis that observed frequencies equal those that would be expected if the null hypothesis were true. (Coke vs. Pepsi example)
- coefficient of determination
- the square of the correlation coefficient; indicates the proportion of variability that 2 variables share
- cohort effects
- the effects of being part of a grp (cohort) that was born at a particular pt in time and, as a result, that was exposed to unique educational, cultural, and other experiences. Cohort effects can confound the results of a cross-sectional study.
- confound (extraneous variable)
- a variable that is not of interest in a research study, but exerts a systemic effect on the dependent variable
- correlation coefficient
- stat value usually btwn -1.00 and +1.00, that indicates the magnitude and the direction of the relationship btwn 2 or more variables. can be + or -. If + when 1 variables increases in value the 2nd also increases. If -, when 1 increases, the other decreases
- correlational research
- type of investigation in which variables are measured only, not manipulated, in order to determin the relationship among these variables.
- counterbalancing
- technique designed to control order effects in a repeated measures research design; involves admin. tx to diff subjects or grps of subjects in a diff order
- criterion variable
- outcome variable in correlational research that one tries to predict
- critical value
- the # above or below which is a statistic (e.g. t, F) is significant.
- cross-sectional study
- study that assesses the effect of development (i.e. age) by examining individuals of diff ages at 1 pt in time
- cross-sequential study
- study that assesses the effect of dev. (ie age) by combining cross-sectional and longitudinal methodologies. It examines ind. of diff ages at dff pts in time
- degree of freedom (df)
- number of values that are "free to vary" in a stat calculation. DF are used in the calculational formulas of stat hypothesis tests
- demand characteristics
- cues in a research study that give subjects clues about how they are expected to behave
- dependent variable
- variable that is hypothesized to be affected by the ind. variable; it is measured by the investigator after the ind variable is manipulated
- descriptive statistics
- stat techniques used to describe and summarize a set of data. Includes frequency distributions, measures of central tendency, and measures of variability
- discriminant function analysis
- statistical tech used to find orderly patterns of responses on tests, which distinguish grps of ppl bases on these responses.