Scientific and Statistical Reasoning Exam UvA Year 2

The challenge of determining whether an observed connection between two variables implies a cause-and-effect relationship.

Graphs used to represent relationships between variables and potential causal pathways.

Arrows indicating the direction of causal influence in a DAG.

The absence of cycles or loops in a DAG, preventing circular causal relationships.

A key goal of developmental psychology, aiming to improve human lives.

Humans naturally use causal thinking to understand their world.

Even if researchers can distinguish between association and causation, general audiences often cannot.

The process of drawing conclusions about cause and effect from observed associations.

A method used in research to eliminate bias caused by uncontrolled factors. It works by randomly assigning participants to different groups, ensuring that each group has an equal chance of receiving a particular treatment or condition.

A notation used in causal inference to represent the effect of an intervention on an outcome variable. It's like setting a variable to a specific value and observing the result.

A type of bias that occurs when a variable is associated with both the exposure and the outcome, but is not on the causal pathway between them.

A definition of confounding that outlines the variable's relationship to the exposure and outcome, but incorrectly claims it's related to both.

The uncertainty in research results stemming from the randomisation procedure, which is known and quantifiable.

A theory should be testable and it must be possible to prove the theory false through empirical observation or experimentation.

The simplest theory that explains a phenomenon is preferred. Encourages minimising unnecessary complexity.

Refers to whether the theory has a restricted reach, or is applicable to a broad range of phenomena. Theories should be as broad as possible, while still providing a genuine explanations of phenomena.

Refers to whether the theory can be used in practice.

Refers to whether the theory actually provides a genuine explanation of the data.

Refers to the consistency of the theory with other models, as well as internal coherence.

Refers to the level of detail, accuracy and specificity in a theory. A precise theory is provided in specific and clear language. Would all researchers interpret the theory in exactly the same way?

Formal models can represent the mechanisms and processes proposed by a theory. Researchers can simulate the model under different conditions and compare the simulated outcomes to observed data, providing a more comprehensive evaluation of the theory.

The amount of variance in the outcome explained by the model relative to how much variation there was to explain in the first place.

The improvement in prediction resulting from using the linear model rather than the mean. It is calculated as the difference between SST and SSR (SSM = SST - SSR).

The proportion of improvement due to the model. It is calculated as SSM divided by SST (R^2 = SSM / SST).

Pearson's correlation coefficient. It is calculated as the square root of R^2 (r = √R^2).

A statistical test used to determine whether a linear model is significantly better than using the mean to predict the outcome.

Cases that differ substantially from the main trend in the data.

Standardised residuals greater than 3.29 are cause for concern. They are unlikely to occur in an average sample.

Standardised residuals greater than 2.58 are evidence that the level of error within the model may be unacceptable.

A statistical method used to determine how two variables influence each other, taking into account a third variable.

This type of analysis is conducted when moderation is statistically significant, and it examines how the relationship between the predictor and the outcome changes at different levels of the moderator.

A statistical method used to understand the indirect effect of a predictor on an outcome through a mediating variable. It involves testing whether the mediator significantly explains the relationship between the predictor and the outcome.

In moderation analysis, this refers to a range of values for the moderator variable where the predictor doesn't significantly influence the outcome.

A process used to transform a variable by subtracting its mean from each of its observed values, leading to a more interpretable analysis.

This refers to the combined effect of the direct and indirect paths from the predictor to the outcome, and is one of the key results of a mediation analysis

In mediation analysis, this is the effect of the predictor on the mediator, and serves as a crucial part in determining the overall indirect effect

In mediation analysis, this is the direct effect of the predictor on the outcome, meaning the influence that doesn't go through the mediator.

Combining multiple strings, sequences, or sets into one by joining them end-to-end.

Assigning numbers to objects or events according to specific rules to represent the quantity of a given attribute.

The way numerical values are assigned to psychological attributes. It involves three properties: identity, order, and quantity.

The ability to distinguish between different categories. Categories must be mutually exclusive (no overlap) and exhaustive (cover all possibilities).

The ability to reflect ranking or ordering of items. Determines which item has more or less of the attribute.

The ability to provide information about the magnitude of the attribute. Uses standardized units.

Zero represents the complete absence of the attribute being measured.

Zero represents the lowest point on the scale, but not necessarily the complete absence of the attribute.