Nursing Research Hypotheses Definitions & Differentiation

Vocabulary flashcards covering the four main axes of nursing research hypotheses, testing methods, p-values, and classification steps.

Hypothesis

A testable prediction about the relationship between two or more variables, used exclusively in quantitative research in nursing.

Simple Hypothesis

A hypothesis that predicts the relationship between exactly two variables (1 Independent Variable + 1 Dependent Variable).

Complex Hypothesis

A hypothesis that predicts relationships among three or more variables (such as 2 IVs + 1 DV, 1 IV + 2 DVs, or 2 IVs + 2 DVs).

Associative Hypothesis

A hypothesis stating that variables exist together or change together in the real world, but does NOT state that one directly causes the other.

Causal Hypothesis

A hypothesis stating that one variable (the Independent Variable) directly causes, produces, or predicts a change in another variable (the Dependent Variable), usually involving an intervention, treatment, or active manipulation.

Associative vs. Causal Clue Words

Associative hypotheses use clue words like "associated with", "related to", "co-occur with", and "positive/negative relationship". Causal hypotheses use clue words like "causes", "leads to", "results in", "produces", and "will reduce/increase following intervention".

Directional Hypothesis

A hypothesis that predicts the exact direction of the relationship or outcome, explicitly telling whether a value goes UP or DOWN.

Non-Directional Hypothesis

A hypothesis stating that a relationship or difference exists, but does NOT specify which direction it goes.

Statistical / Null Hypothesis ($H_0$)

A hypothesis stating that NO relationship or NO difference exists between the variables being studied, assuming any observed effect is due purely to chance.

Research / Alternative Hypothesis ($H_a$)

A hypothesis stating the expected relationship, difference, or effect based on clinical theory or literature.

Variable Counting Test

The test used to differentiate simple from complex hypotheses by counting total variables: a count of $2$ indicates a simple hypothesis, while a count of $3$ or more indicates a complex hypothesis.

Intervention / Cause Test

The test used to differentiate associative from causal hypotheses by asking if one variable directly causes or changes another via an intervention versus co-varying naturally.

Up / Down Arrow Test

The test used to differentiate directional from non-directional hypotheses by checking if the statement explicitly specifies direction using words like higher, lower, increase, or decrease.

Zero Difference Test

The test used to differentiate statistical (null) from research hypotheses by asking if the statement claims that nothing happens or no difference/relationship exists.

Low $p$-value ($p < 0.05$)

Indicates a low probability that the Null Hypothesis ($H_0$) is true (for example, $p = 0.03$ represents a $3\%$ chance that $H_0$ is true), requiring the researcher to reject the Null Hypothesis.

High $p$-value ($p > 0.05$)

Indicates a high probability that the Null Hypothesis ($H_0$) is true (for example, $p = 0.40$ represents a $40\%$ chance that $H_0$ is true), requiring the researcher to fail to reject the Null Hypothesis.

Critical Rules for Null Hypotheses

1. ALL Null Hypotheses ($H_0$) are non-directional by definition. 2. Statistical tests ALWAYS test the Null Hypothesis ($H_0$), never the research hypothesis directly.

Master Decision Sequence

The 4-step rapid check order used to classify any hypothesis statement: 1. Count variables, 2. Check for cause, 3. Check for direction, and 4. Check stance.