# Confused by clinical research methods? Get a clue!

*Thomas Perneger*

Clinical research used to be simple, a relaxing diversion after a long day at the surgery. A doctor reviewed the charts of all three patients in his or her practice who suffered from an exotic ailment, computed a proportion or two (“a third died”), took photographs of a Petri dish and of a face rash, added a black bar to cover the eyes of Exhibit 2 – done.

That was then. Today researchers are like wedding planners – they obsess about inclusion criteria, cover up adverse events before anyone notices, lose sleep over budget overruns, and miss out on all the fun. Readers of medical journals are not spared. Articles are full of jargon, and it’s not medical Latin like in the old days. Especially maddening are statistical concepts, disguised as single letters (p, r, kappa), cute metaphors (neural network, bootstrap), or outright lies (normality, significance, error). It’s no wonder doctors only read GetWithIt™ updates anymore! To remedy this situation, Swiss Medical Weekly proposes here an interactive learning tool that will turn you into an instant expert in current research methodology.

To proceed, consider each clue, close your eyes, and let free associations flow. Soon a statistical or epidemiological phrase will occur to you. Do not over-think it. For instance, if the clue is “Final ranking at a beauty pageant?” a valid answer is “Miss classification”. Get it? Misclassification! Don’t worry about sloppy spelling or awkward grammar. Click on “show answer” to verify that you got it right. If you are unfamiliar with the scientific concept, read the comment (if you don’t get the joke, you are on your own).

Let’s play!

**1. Final ranking at a beauty pageant**

Miss classification

*(misclassification) Error in the measurement of a risk factor or a disease, which typically weakens the observed association (misclassification bias)*

**2. Blueprint for an airport luggage scanner**

Case-control design

*Type of study in which patients who have a disease are compared to controls who don't*

**3. Mindset of a helpful doctor**

Intention to treat

*Analysis of a clinical trial that includes all participants as initially randomised (regardless of actual treatment received)*

**4. Possibility of your crazy uncle dropping by**

Relative risk

*Ratio of risks in the exposed and the unexposed*

**5. Editing a captain's entry**

Log transformation

*Application of the logarithm function*

**6. Sigmund Freud's memoirs**

Meta-analysis

*Statistical synthesis of the results of several studies that address the same research question*

**7. Ultimate goal of rehabilitation?**

Normal function

*Bell-shaped probability density distribution; synonym of Gaussian distribution*

**8. Slip-up by an evil nerd?**

Mean square error

*In analysis of variance, the sum of squared differences between observed and predicted values divided by the degrees of freedom*

**9. They are raised at a nudist camp**

Odds of exposure

*Odds are a function of a proportion, namely the proportion p divided by its complement (1-p). Exposure is synonym of risk factor.*

**10. Scale that goes from 0 (sane) to 10 (Hannibal Lecter)**

Psycho metric

*(psychometric) Related to classic methods for the measurement of unobserved attributes (often psychological variables)*

**11. Choosing Ronaldo over Messi**

Forward selection

*Method for selecting covariates for a multivariable model, which starts with the best univariable predictor, then adds the second best, etc.*

**12. Ask what you will be charged for water or electricity**

Cost utility

*Type of economic analysis where costs incurred are related to health utility gains*

**13. Requirement for a double date**

Two by two table

*Common tool in epidemiology; e.g. tabulation of exposure by outcome*

**14. Outfitting the troops**

Uniform distribution

*Distribution that assigns equal probability (or density) to all values on a given interval*

**15. Telling a friend that she was right to get a divorce?**

Split-half validation

*Validation method where a model is built on one half of the data and then applied to the other half*

**16. Urinalysis report**

p-values

*Probabilities of the observed result or more extreme results under the null hypothesis*

**17. They don’t make the news**

Censored events

*In time-to-event analysis, observations for which the event of interest has not occurred at the time of analysis*

**18. Recycling facility for plastics**

Composite endpoint

*Occurrence of any of several events that are considered equally relevant and therefore combined in a clinical trial*

**19. Cindy Crawford trying to save on groceries, e.g.**

Parsimonious model

*Statistical model that includes as few covariates as possible while explaining as much as possible of the outcome*

**20. It’s all a small window needs**

Single blind

*A clinical trial in which the patients do not know which treatment they receive*

**21. List of favourite neighbourhood watering holes**

Bar chart

*Graph that represents by the height of a bar a characteristic of interest (mean, percentage, etc.) for several subgroups*

**22. Hanging the flag upside down, e.g.**

Standard error

*Level of uncertainty of an estimator (i.e., a value obtained from the data) due to the limited sample size*

**23. Telephone contact of the health insurance department that preapproves health care expenditures**

Number needed to treat

*Measure of treatment effectiveness; the number of persons that must be treated in order to avoid one clinically relevant event*

**24. Immature behaviour by the planning committee**

Logistic regression

*Modelling method used for binary outcome variables*

**25. Pretending that you have won at roulette, e.g.**

Monte Carlo simulation

*Computer-based method that explores a phenomenon through the simulated behaviour of repeated samples*

**26. Iconoclast on drugs**

High outlier

*Unusually high value of a variable*

**27. Inside squabble**

Within-group variance

*In analysis of variance, variability that is not attributable to group membership*

**28. Dropping a four-letter bomb?**

F-test

*Statistical test used in analysis of variance*

**29. Two qualities of an effective parental admonishment**

Sensitivity and specificity

*Ability of a test to correctly identify the diseased (sensitivity) and the non-diseased (specificity)*

**30. Ultimate pluck**

Confidence limit

*Upper or lower bound of a confidence interval, which is the range of values of a parameter that are compatible with the observed data*

**31. When nobody comes to the fashion show**

Discrete event modelling

*Simulation technique of a complex process that can lead to one or several distinct events*

**32. Proportion of medical students who choose psychiatry?**

Shrinkage parameter

*In empirical Bayes estimation, the relative weight given to the overall mean when it is combined with the local estimate*

**33. Probability of winning the Ig Nobel Prize, e.g.**

p <0.001

*Low p-value that typically leads to the rejection of the null hypothesis*

**34. Neatly stacked stolen goods, presented in court**

Pyramid of evidence

*Hierarchy of scientific evidence based on the trustworthiness of the methods used (meta-analysis of randomised trials at the top and expert opinion at the bottom)*

**35. What differentiates solitary confinement, county jail and house arrest**

Degrees of freedom

*Number of independent bits of information that are used to compute a statistic or estimate a model*

**36. What a wide-receiver should engage in before the pass**

Safety monitoring

*Procedures for detecting threats to patient safety in a clinical trial*

**37. Enduring battery life?**

Patient autonomy

*Ethical principle that gives patients ultimate say in decisions that affect them, including participation in research*

**38. What the Civil Rights Act of 1964 aimed to do**

Recall bias

*Systematic error that can affect case-control studies, because the cases may remember their exposure history differently from the controls*

**39. Parliamentary committee**

Representative sample

*Sample drawn through a process that guarantees fair representation of the underlying population in the long run (e.g., at random)*

**40. First date, essentially**

Interaction test

*Statistical procedure that examines the effect of a variable as a function of another; e.g. a test to compare the effectiveness of a treatment in men versus women*

**41. Theory of evolution?**

Adaptive design

*Design of a clinical trial that incorporates future decisions based on accumulated data*

**42. Like someone who orders Bud Light when Westmalle is on tap**

Tripel blind

*(triple blind) Triple blinding ensures that the patient, the researcher, and the data analyst are unaware of treatment allocation*

**43. Important cricket game**

Test of significance

*Procedure for choosing between two hypotheses (typically “the treatment doesn’t work” vs “the treatment works”) based on observed data*

**44. Hence the saying “traduttore, traditore”**

Translational trials

*Studies that test whether basic science advances are applicable to patient care*

**45. Someone as crazy as you or me**

Normal deviate

*Normally distributed statistic or observation expressed in standard deviation units*

**46. Result of neglecting one’s workouts**

Marginal conditioning

*Treating marginal distributions as fixed when the association between two variables is examined; e.g. the row and column totals are considered fixed when a kappa statistic is computed*

**47. Tongue tied abbot**

Non-informative prior

*In Bayesian statistics, the a priori distribution of a parameter that reflects ignorance of its true value*

**48. Dilemma of the schizophrenic patient?**

Multiplicity problem

*Proliferation of “significant” results due to type 1 errors when a large number of tests is performed*

**49. Democracy?**

Law of large numbers

*Principle that describes the average behaviour of a procedure when it is repeated many times*

**50. Concession in Amazonia**

Forest plot

*Graph used in meta-analysis representing the results of several studies, with their confidence intervals, plus the pooled effect*

**51. Lead a working group at ISO**

Direct standardisation

*Method for removing confounding, where rates of disease observed in strata of the confounder (e.g., in age groups) are applied to a reference population*

**52. The custom of putting your boss on your papers, e.g.**

Research protocol

*Document that describes in detail all procedures to be used in a study*

**53. Possible causes of mistaken fraternity?**

Alpha and beta errors

*Type 1 and type 2 errors. The former is the probability of rejecting the null hypothesis when it is true, the latter the probability of accepting the null hypothesis when the alternate is true*

**54. Its rejection in science leads to acceptance in Nature (and vice versa)**

Null hypothesis

*Hypothesis of no association or no effect that the researcher hopes to reject.*

**55. Pissing contest, often**

Non-inferiority test

*Test of the hypothesis that a treatment is less effective than another by a pre-specified amount*

**56. Ceremony on the golf course**

Link function

*Mathematical function applied to the expected value of the outcome variable in generalised linear models; e.g. logarithm function applied to the number of events in log-linear models*

**57. Prince Philip saying “I do”, e.g.**

CONSORT statement

*Guideline for the reporting of randomised controlled trials*

**58. Getting stood up, e.g.**

N-of-1 trial

*Trial where two treatments are alternated at random within a single patient*

**59. Ironman deity**

Goodness of fit

*Measure of the adequacy of a model for a given dataset*

**60. The sinking of Noah’s ark?**

Pairwise deletion

*Method for dealing with missing data when correlations are obtained for >2 variables, where each correlation is computed on all available pairs*

**61. Replying to personal ads on a dating website**

Disclosure of interests

*Authors’ disclosures of financial or other links with private entities that may bias scientific conclusions*

**62. Flipping the USB key to make it fit in the slot, e.g.**

Two-sided test

*Statistical test that leads to rejection of the null hypothesis if the data deviate from the null value in either direction*

**63. When you wonder if the waiter understood what people wanted to drink next**

Second order uncertainty

*In modelling, uncertainty about the values of parameters (whereas first order uncertainty concerns values of individual observations)*

**64. The pride of aesthetes, and the bane of oppressed minorities**

Discrimination

*Ability of a diagnostic or predictive model to correctly categorise patients with and without a characteristic (e.g., a specific disease)*

**65. Fil__ng in _he bl_nks**

Imputation of missing data

*Replacement of missing data by plausible values*

**66. Checking the authenticity of a wooden relic during the Inquisition**

Cross validation

*(cross-validation) Method for verifying the properties of a predictive model*

**67. The number of times you have been fined for speeding or for disorderly conduct**

Citation count

*The number of times an article is cited in the scientific literature*

**68. Double take?**

Peer review

*Evaluation of research articles or protocols by experts in the field to aid the decision to publish the paper or to fund the study*

**69. What an effective doctor strives for**

Good clinical practice

*(Good Clinical Practice) Regulations for clinical trials established by the International Conference on Harmonization*

**70. Plan B?**

Residual plot

*In regression modelling, differences between observed and predicted values, plotted against predicted values*

**71. The long and the short of it?**

Range of values

*Lowest and highest values of a variable*

Thank you for playing along!

**Disclosure statement**

No financial support and no other potential conflict of interest relevant to this article was reported.

Thomas Perneger, MD, PhD

Division of clinical epidemiology

Geneva University Hospitals

6 rue Gabrielle-Perret-Gentil

CH-1211 Geneva

** **