According to the passage, the fundamental misunderstanding regarding the p-value under the frequentist NHST paradigm is that researchers often mistakenly believe it represents:

the probability of observing the collected data if the null hypothesis is true.

the probability that the alternative hypothesis is entirely false.

the probability that the null hypothesis itself is true.

the probability that a replicated experiment will yield the exact same data.

The author characterizes "p-hacking" as which of the following?

A deliberate fabrication of data to secure academic tenure.

An unconscious behavioral adaptation to structural incentives within the scientific community.

A malicious, coordinated effort by academic journals to suppress null results.

A flawless statistical technique that has been unfairly scapegoated for the replication crisis.

It can be inferred from the passage's discussion of the "file drawer effect" that the overall body of published psychological literature:

presents an artificially inflated picture of the validity and frequency of certain behavioral effects.

is entirely composed of studies that utilized Bayesian statistical frameworks.

contains an equal ratio of statistically significant findings to null results.

has completely abandoned the use of Null Hypothesis Significance Testing.

Which of the following most accurately describes the primary distinction between the frequentist NHST approach and the Bayesian framework as presented in the passage?

NHST guarantees empirical truth, whereas Bayesian frameworks only offer statistical estimates.

NHST evaluates the likelihood of data under a fixed assumption, whereas Bayesian inference updates the probability of the hypothesis based on data.

NHST requires researchers to specify their prior beliefs, whereas Bayesian inference relies purely on objective data collection.

NHST focuses heavily on the file drawer effect, whereas Bayesian frameworks eliminate publication bias entirely.

The tone of the author regarding the shift toward Bayesian statistical frameworks is best described as:

aggressively dogmatic and entirely dismissive of all previous psychological research.

cautiously optimistic about replacing binary sensationalism with a more resilient methodology.

deeply pessimistic that any statistical model can rescue a fatally flawed discipline.

completely neutral, presenting both frameworks without implying a preference for either.

←

The Epistemic Recalibration of Social Psychology: From Frequentist Fragility to Bayesian Inference

PRACTICE

100:00+4 −1MCQ Single Answer

Reading Passage

Over the past decade, social psychology has been convulsed by the "replication crisis," a systemic reckoning in which a staggering proportion of foundational, textbook-enshrined behavioral effects failed to replicate under rigorous secondary scrutiny. While early discourse often attributed this epistemic fragility to deliberate scientific malfeasance, methodologists have increasingly identified the root cause as structural: the field's historic, monolithic reliance on Null Hypothesis Significance Testing (NHST). Within this frequentist paradigm, a result is deemed "statistically significant" if the p-value falls below an arbitrary threshold (typically p < 0.05), a metric widely misinterpreted as the probability that the null hypothesis is true. In reality, the p-value only quantifies the probability of observing the collected data—or more extreme data—assuming the null hypothesis were already true. This subtle but profound conditional inversion incentivizes researchers to pursue statistical significance rather than empirical truth. This incentive structure is exacerbated by systemic publication bias, famously termed the "file drawer effect." Because academic journals overwhelmingly favor novel, statistically significant findings, researchers implicitly learn to shelve null results. Concurrently, the pressure to publish engenders "p-hacking"—the post-hoc manipulation of data analysis parameters, such as dropping outliers or altering dependent variables, until the coveted p < 0.05 threshold is achieved. Crucially, p-hacking is rarely an act of conscious deception; rather, it is an unconscious methodological drift driven by confirmation bias within a publish-or-perish ecosystem. When thousands of researchers engage in minor, seemingly justifiable data-dredging exercises, the aggregate literature becomes deeply saturated with false positives, masquerading as objective psychological laws. In response, a vanguard of psychological methodologists is advocating for a paradigm shift away from frequentist NHST toward Bayesian statistical frameworks. Unlike the frequentist approach, which evaluates the likelihood of data under a fixed null assumption, Bayesian inference dynamically updates the probability of the hypothesis itself based on the observed data and prior knowledge. By requiring researchers to formally specify their prior beliefs and mathematically update them via Bayes' theorem, this framework eschews the binary, absolute categorizations of "significant" versus "insignificant." Instead, it recasts psychological research as a continuous process of uncertainty quantification. Ultimately, this methodological recalibration forces the discipline to abandon the illusion of definitive, singular discoveries, substituting it with a more resilient, albeit less sensational, epistemology of iterative probability.

Which of the following best captures the primary purpose of the passage?