P value: The probability (ranging from zero to one) that the results observed in a study (or more extreme results) could have occurred by chance if in reality the null hypothesis were true (refers to a Type I error).6

Patient registry: An organized system that uses observational study methods to collect uniform data (clinical or other) to evaluate specified outcomes for a population defined by a particular disease, condition, or exposure, and that serves one or more predetermined scientific, clinical, or policy purposes.43

Patient-centered outcomes research (PCOR): Research focusing on the outcomes of concern to patients; these may include three major categories of patient-assessed health outcomes: 1) health status (encompassing health-related quality of life and functional status); 2) health utilities (patients’ values for a particular state of health); and 3) patient satisfaction.44

Patient-Centered Outcomes Research Institute (PCORI): An independent organization created to help patients, clinicians, purchasers and policy makers make better informed health decisions.45 PCORI commissions research that reflects and supports patients’ values and interests to provide reliable, evidence-based information for the health care choices patients and their caregivers they face.45 The American Reinvestment and Recovery Act (ARRA) allocated $1.1 billion for comparative effectiveness research (CER) and the Patient Protection and Affordable Care Act established PCORI to promote ongoing CER.46

Patient-reported outcomes (PRO): An umbrella term that refers to outcome data reported directly by the patient.1 This is one source of data that may be used to describe a patient’s condition and response to treatment. It includes such outcomes as global impressions, functional status, well-being, symptoms, health-related quality of life, satisfaction with treatment, and treatment adherence.

Per protocol analysis: An analysis of the subset of participants from a randomized controlled trial who complied with the protocol sufficiently to ensure that their data would be likely to exhibit the effect of treatment.6 This subset may be defined after considering exposure to treatment, availability of measurements, and absence of major protocol violations. This analysis strategy may be subject to bias because the reasons for noncompliance may be related to treatment.

Performance bias: Systematic differences between intervention groups in care provided apart from the intervention being evaluated.6 For example, if participants know they are in the control group, they may be more likely to use other forms of care. Health care providers might behave differently if they are aware of a patient’s assignment to a particular study group. Blinding of study participants and providers of care is used to protect against performance bias.

Persistence: The continued use of the prescribed pharmacotherapeutic regimen or other program. Also called treatment persistence.1 See also adherence.
Pharmacoepidemiology: Study of the use, effects, and outcomes of drug treatment from an epidemiological (population) perspective.1

Pharmacovigilance: The scientific field of collecting, analyzing, and interpreting postmarketing reports with the intention to generate detect, and/or validate signals for potential side effects from marketed products.1 See also postmarketing surveillance, data mining, and patient registry.

PICOTS: Acronym for Population, Intervention, Comparator, Outcome, Timing, and Setting.47 Parameters developed for formulating questions and locating primary studies for inclusion in systematic reviews. Also useful for evaluating applicability.

Planned analysis: Statistical analysis specified in a study protocol that is planned in advance of data collection (in contrast to unplanned analysis).6 Also called a priori analysis, pre-specified analysis.

Point estimate: A value (statistic) obtained from sample data this is used as the best estimate of what is true for the relevant population from which the sample is taken.4, 6 A point estimate is a measure of central tendency (e.g., mean, median, mode) that alone does not consider variability (e.g., standard deviation, standard error). Often used as a general term for results (e.g., risk difference, odds ratio, relative risk) obtained from a sample (a study or meta-analysis).

Population: The entire collection (group) of observations or participants that have something in common (e.g., age, disease) and to which conclusions are being inferred.4, 6

Positive predictive value (PPV): The proportion of individuals with a positive test result who have the disease, and can be interpreted as the probability that a positive test result is correct.1, 6 Calculation: PPV = (TP) / (TP + FP), where TP = true positive and FP = false positive.

Positive study: A study with statistically significant results, usually indicating a beneficial effect of the intervention being studied.6, 41 The term can generate confusion because it refers to both statistical significance and the direction of effect; studies often have multiple outcomes; the criteria for classifying studies as negative or positive are not always clear; and, in the case of studies of risk or undesirable effects, “positive” studies are ones that show a harmful effect.6  See also negative study and publication bias.

Postmarketing surveillance: The practice of monitoring a drug or device after marketing and is a component of the science of pharmacovigilance.1 The primary aim is to evaluate safety, including the risk for specific adverse effects or for potential differences in the drug’s safety profile in special populations or disease states. Approaches to monitor the safety of drugs include spontaneous reporting databases, prescription event monitoring, electronic health records, and patient registries.

Power: The probability of rejecting the null hypothesis when a specific alternative hypothesis is true. The power of a hypothesis test is one minus the probability of Type II error.6 In clinical trials, power is the probability that a trial will detect, as statistically significant, an intervention effect of a specified size. Studies with a given number of participants have more power to detect large effects than small effect. In general, power is set at 80% or greater when calculating sample size. Also called statistical power.

Pragmatic trial: A controlled clinical trial designed to measure the benefit of an intervention in normal practice (effectiveness) to help guide decisions between options for care.29, 30 Trials of health care interventions are often described as either explanatory or pragmatic. See also explanatory trial.

Precision: 1. In statistics, precision is the degree of certainty surrounding an effect estimate for a given outcome.6 The greater the precision, the less the measurement error. Confidence intervals around the estimate of effect from each study are one way of expressing precision, with a narrower confidence interval meaning more precision. 2. In trial searching, precision is the proportion of relevant articles identified by a search strategy expressed as a percentage of all articles (relevant and irrelevant) identified by that strategy. Highly sensitive strategies tend to have low levels of precision. Calculation: Precision = number of relevant articles / number of articles identified.

Predictive value: A measure of the usefulness of a screening/diagnostic test.1, 6, 48 The probability that an individual with a positive test is a true positive is referred to as the positive predictive value of a test. In contrast, the negative predictive value of a test is the probability that the individual with a negative test is a true negative. Predictive value is related to the sensitivity and specificity of the test and the prevalence of the disease in the population tested.

Prevalence: The proportion of a population that is affected by a given disease or condition at a specified point in time.4 It is not truly a rate, although it is often incorrectly called prevalence rate.

PRISMA: Acronym for Preferred Reporting Items for Systematic reviews and Meta-Analyses.48, 49 PRISMA is the major reporting guideline for systematic reviews and meta-analyses. Website: http://www.prisma-statement.org.

Prospective study: In evaluations of the effects of health care interventions, a study in which participants are identified according to current risk status or exposure, and followed forward through time to observe outcomes.6 Randomized controlled trials are always prospective studies. Cohort studies are commonly either prospective or retrospective, whereas case-control studies are usually retrospective. See also retrospective study.

Publication bias: The tendency of research with positive (statistically significant) results to be submitted and published more than research with negative or neutral (null or non-significant) results.50 Publication bias is a type of reporting bias. See also reporting bias.