LPLS flashcards

32 cards. Read the term and the definition here. The deck at the top of this page is optional.

Reliability

The consistency or reproducibility of a measurement across repeated administrations, raters, or items; high reliability is required for, but does not guarantee, validity.

Validity

The degree to which a measurement or inference actually reflects the construct or conclusion it claims to represent, rather than an artifact of the method used.

Classical test theory

Model stating that an observed score equals true score plus random error (X = T + E); reliability is the ratio of true-score variance to observed-score variance.

Standard error of mean

The standard deviation of the sampling distribution of the mean, equal to the population standard deviation divided by the square root of the sample size.

Central limit theorem

As sample size grows, the sampling distribution of the sample mean approaches a normal distribution regardless of the shape of the underlying population distribution.

Coefficient of determination

The square of the correlation coefficient, written r-squared, giving the proportion of variance in one variable that is statistically explained by the other variable.

Sensitivity

The proportion of true positives correctly identified by a test, computed as true positives divided by the sum of true positives and false negatives.

Specificity

The proportion of true negatives correctly identified by a test, computed as true negatives divided by the sum of true negatives and false positives.

Positive predictive value

The probability that a positive test result is a true positive; it rises as prevalence increases and falls sharply when the condition is rare.

Necessary condition

A condition that must hold for an outcome to occur; if the outcome occurs, the condition is guaranteed to be present, though it may not produce the outcome alone.

Sufficient condition

A condition whose presence guarantees that the outcome occurs; there may be other independent routes to the same outcome.

Confounding variable

A third variable associated with both the presumed cause and the outcome that can create, inflate, or mask an apparent relationship between them.

Bessel's correction

Use of n minus one rather than n in the denominator when computing sample variance, removing the systematic downward bias of the sample estimate.

Base rate

The prevalence of a condition in a population before new evidence is applied; low base rates sharply reduce the positive predictive value of a test.

Type I error

Rejecting a true null hypothesis; its probability equals the chosen significance level alpha, conventionally set at 0.05.

Type II error

Failing to reject a false null hypothesis; its probability is beta, and statistical power is defined as one minus beta.

Random assignment

Placing participants into experimental conditions by chance so that groups are comparable on average; this supports causal inference from experiments.

Random sampling

Selecting participants from a population by chance so that the sample is representative; this supports generalization of findings to that population.

p-value

The probability of obtaining data at least as extreme as observed, assuming the null hypothesis is true; it is not the probability that the null is true.

Confidence interval

A range computed so that, across repeated samples, a stated percentage of such intervals contain the true parameter value.

Statistical power

The probability of correctly rejecting a false null hypothesis; it increases with larger sample size, larger effect size, lower variability, and a more lenient alpha.

Effect size

A standardized measure of the magnitude of a difference or association, independent of sample size, allowing comparison across studies and samples.

Absolute risk difference

The arithmetic difference in event rates between two groups; it reflects practical impact better than relative risk when baseline rates are low.

Relative risk

The ratio of event rates in one group to another; identical relative risks imply very different absolute changes depending on the baseline rate.

Systematic versus random error

Systematic error, or bias, shifts measurements consistently in one direction; random error scatters them and shrinks as the number of observations increases.

Double-blind procedure

Neither participants nor assessors know condition assignment, preventing expectancy, demand, and scoring biases from distorting the observed results.

Expected value

The probability-weighted average of all possible outcomes of a decision, computed by summing each payoff multiplied by its probability of occurring.

Dimensional analysis

A check that both sides of an equation carry identical units; mismatched units reveal an algebraic or conversion error before numbers are computed.

Temporal precedence

The requirement that a proposed cause occur before its effect; it is one of three conditions needed to support a causal inference.

Ecological validity

The extent to which findings obtained under controlled conditions generalize to real-world settings, tasks, timing, and populations.

Operational definition

A precise specification of how a variable is measured or manipulated, allowing replication and reducing ambiguity about what was observed.

Ceiling and floor effects

Occur when scores cluster at the maximum or minimum possible value, compressing variance and weakening observed relationships between variables.