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.
Refers to the process where research subjects change their behavior in response to being studied. That is, people behave differently because they are being observed. For example, teachers in a classroom might change their discipline practices if they are part of a study that uses classroom observations as a data collection approach.
The degree of dissimilarity among cases with respect to a particular characteristic.
Heterogeneous Treatment Effects
Randomized experimental designs test the average effect of a treatment or intervention. However, the treatment might affect different research subjects or groups of subjects in different ways. The effects might be larger for some subjects and smaller for others, and it may have no effect on some subjects in the treatment group. The study of treatment effect heterogeneity is the study of these differences across subjects and groups of subjects. The findings from these studies provide important information that can be used to develop theories about the conditions under which the treatment is effective or ineffective.
A distribution characterized by a changing (non-constant) variance or standard deviation. Heteroskedasticity is problematic in statistical models because estimated standard errors will be inefficient and biased. Consequently, traditional significance test will not be valid.
Hierarchical Linear Modeling (HLM)
A multi-level modeling procedure that is used to analyze the variance in the outcome variables when the predictor variables are at varying hierarchical levels (child, classroom, programs) and nested such that children are nested in classrooms and classrooms are nested in programs. For example, HLM can be used to estimate the effects of child characteristics (e.g., race/ethnicity, gender, social economic status) on children's academic skills for designs that include children nested in classrooms. HLM enables a researcher to estimate effects within individual units (children), formulate hypotheses about cross level effects (children and classrooms) and partition the variance and covariance components among levels (share of variance explained by child and by classroom characteristics).
A hierarchical model is a type of linear regression model that is used when the data one is analyzing are organized into a tree-like structure (or hierarchy). That is, data at one level is nested under another level. For example, children are nested in classrooms. Hierarchal models are used when predicting outcomes (e.g., children's test scores) using variables from the different levels (child level variables such as gender and prior test scores and classroom level variables such as class size and quality of teacher-child interactions).
A visual presentation of data that shows the frequencies with which each value of a variable occurs. Each value of a variable typically is displayed along the bottom of a histogram, and a bar is drawn for each value. The height of the bar corresponds to the frequency with which that value occurs.
A statement that predicts the relationship between the independent (causal) and dependent (outcome) variables.
Statistical tests to determine whether a hypothesis is accepted or rejected. In hypothesis testing, two hypotheses are used: the null hypothesis and the alternative hypothesis. The alternative hypothesis is the hypothesis of interest; it generally states that there is a relationship between two variables. The null hypothesis states the opposite, that there is no relationship between two variables.