The research glossary defines terms used in conducting social science and policy research, for example those describing methods, measurements, statistical procedures, and other aspects of research; the child care glossary defines terms used to describe aspects of child care and early education practice and policy.
The T distribution (or Student's t-distribution) is a theoretical probability distribution that is similar to a normal distribution (i.e., it is a symmetrical bell-shaped distribution). It is used when testing differences in group means for small sample sizes (sample n 30).
A statistical test that is used to compare the means of two samples (independent t-test), the means of one sample at different times (paired sample t-test) or the mean of one sample against a known mean (one sample t-test). The test is appropriate for small sample sizes (less than 30) although it is often used when testing group differences for larger samples. It is also used to test whether correlation and regression coefficients are significantly different from zero.
The population to which the researcher would like to generalize her or his results based on analysis of a sample. The sample is selected from a target population.
The degree to which a measure produces consistent results over several administrations.
The selection of individuals within a naturalistic research study based on emerging findings as the study progresses to ensure that key issues are adequately represented.
General statement that describes a hypothesized relationship between different phenomena or characteristics. Theories should be specific enough to be testable with a well-designed research study.
A sequence of observations or data which are ordered in time. Time series data are often collected at a regular interval, but the interval between time points does not have to be equal. The Head Start Program Information Report (PIR) is an example of a time series database. Data on Head Start enrollments and the characteristics of the programs serving Head Start children are collected and reported annually.
Time Series Analysis
Time series analysis or trend analysis is a set of statistical techniques used to identify patterns or associations in data across time. These methods can be used with continuous or discrete numeric data to examine univariate and multivariate time series models.
Time-invariant effects refer to effects of a variable on another variable that are the same across time. For example, the effect of parental education on children's math achievement at time 1 is the same as its effect on math achievement at time n.
A time-varying covariate (TVC) is a variable with values that can change across time, but its effect on the dependent (outcome) variable is assumed to be constant. For example, the amount of mathematics instructional time a child receives could be a TVC in a study of children's growth in math achievement from kindergarten through grade 5. Although the number of hours of math instruction children receive can change at each grade, the estimated relationship between math instruction and math achievement might remain constant across time.