BMJ Statistics Notes series

back to stats portal

The statistical notes series is a great series of short articles on statistics for medical researchers. The text is accessible and useful also for biologists. Have a read! And update the list if you come across a new publication in the series. The publisher, BMJ [1], makes the articles publicly available only after 12 months. That means, links to the most recent papers are for subscribers only.

An opinion on the series

Gerard E. Dallal, author of the excellent "Little Handbook of Statistical Practice" [2], says this about the series:

"Perhaps the finest series of short articles on the use of statistics is the occasional series of Statistics Notes started in 1994 by the British Medical Journal. ...

Absence of evidence is not evidence of absence is something every investigator should know, but too few do. Along with Interaction 2: compare effect sizes not P values, these articles describe two of the most common fatal mistakes in manuscripts submitted to research journals. The faulty reasoning leading to these errors is so seductive that papers containing these errors sometimes slip through the reviewing process and misinterpretations of data are published as fact.

Correlation, regression, and repeated data, Calculating correlation coefficients with repeated observations: Part 1--correlation within subjects, and Calculating correlation coefficients with repeated observations: Part 2--correlation between subjects provide an excellent introduction to the subtleties of analyzing repeated measurements on the same subject.

Statistical Notes  publications (in chronological order)

1994

• Correlation, regression, and repeated data J Martin Bland & Douglas G Altman BMJ 1994;308:896 (2 April)
• Regression towards the mean J Martin Bland & Douglas G Altman BMJ 1994;308:1499 (4 June)
• Diagnostic tests 1: sensitivity and specificity Douglas G Altman & J Martin Bland BMJ 1994;308:1552 (11 June)
• Diagnostic tests 2: predictive values Douglas G Altman & J Martin Bland BMJ 1994;309:102 (9 July)
• Diagnostic tests 3: receiver operating characteristic plots Douglas G Altman & J Martin Bland BMJ 1994;309:188 (16 July)
• One and two sided tests of significance J Martin Bland & Douglas G Altman BMJ 1994;309:248 (23 July)
• Some examples of regression towards the mean J Martin Bland & Douglas G Altman BMJ 1994;309:780 (24 September)
• Quartiles, quintiles, centiles, and other quantiles Douglas G Altman & J Martin Bland BMJ 1994;309:996 (15 October)
• Matching J Martin Bland & Douglas G Altman BMJ 1994;309:1128 (29 October)

1995

• Multiple significance tests: the Bonferroni method J Martin Bland & Douglas G Altman BMJ 1995;310:170 (21 January)
• The normal distribution Douglas G Altman & J Martin Bland BMJ 1995;310:298 (4 February)
• Calculating correlation coefficients with repeated observations: Part 1--correlation within subjects J Martin Bland & Douglas G Altman BMJ 1995;310:446 (18 February)
• Calculating correlation coefficients with repeated observations: Part 2--correlation between subjects J Martin Bland & Douglas G Altman BMJ 1995;310:633 (11 March)
• Absence of evidence is not evidence of absence Douglas G Altman & J Martin Bland BMJ 1995;311:485 (19 August)

1996

• Presentation of numerical data J Martin Bland & Douglas G Altman BMJ 1996;312:572 (2 March)
• Logarithms J Martin Bland & Douglas G Altman BMJ 1996;312:700 (16 March)
• Transforming data J Martin Bland & Douglas G Altman BMJ 1996;312:770 (23 March)
• Transformations, means, and confidence intervals J Martin Bland & Douglas G Altman BMJ 1996;312:1079 (27 April)
• The use of transformation when comparing two means J Martin Bland & Douglas G Altman BMJ 1996;312:1153 (4 May)
• Comparing several groups using analysis of variance Douglas G Altman & J Martin Bland BMJ 1996;312:1472-1473 (8 June)
• Measurement error and correlation coefficients J Martin Bland & Douglas G Altman BMJ 1996;313:41-42 (6 July)
• Measurement error proportional to the mean J Martin Bland & Douglas G Altman BMJ 1996;313:106 (13 July)
• Interaction 1: heterogeneity of effects Douglas G Altman & John NS Matthews BMJ 1996;313:486 (24 August)
• Measurement error J Martin Bland & Douglas G Altman BMJ 1996;313:744 (21 September)
• Interaction 2: compare effect sizes not P values John NS Matthews & Douglas G Altman BMJ 1996;313:808 (28 September)
• Interaction 3: How to examine heterogeneity John NS Matthews & Douglas G Altman BMJ 1996;313:862 (5 October)
• Detecting skewness from summary information Douglas G Altman & J Martin Bland BMJ 1996;313:1200 (9 November)

1997

• Cronbach's alpha J Martin Bland & Douglas G Altman BMJ 1997;314:572 (22 February)
• Units of analysis Douglas G Altman & J Martin Bland BMJ 1997;314:1874 (28 June)
• Trials randomised in clusters J Martin Bland & Sally M Kerry BMJ 1997;315:600 (6 September)

1998

• Analysis of a trial randomised in clusters Sally M Kerry & Martin Bland BMJ 1998;316:54
• Weighted comparison of means Martin Bland & Sally M Kerry BMJ 1998;316:129 (10 January)
• Sample size in cluster randomisation Sally M Kerry & J Martin Bland BMJ 1998;316:549 (14 February)
• The intracluster correlation coefficient in cluster randomisation Sally M Kerry & J Martin Bland BMJ 1998;316:1455-1460 (9 May)
• Generalisation and extrapolation Douglas G Altman & J Martin Bland BMJ 1998;317:409-410 (8 August)
• Time to event (survival) data Douglas G Altman & J Martin Bland BMJ 1998;317:468-469 (15 August)
• Bayesians and frequentists J Martin Bland & Douglas G Altman BMJ 1998;317:1151-1160 (24 October)
• Survival probabilities (the Kaplan-Meier method) J Martin Bland, & Douglas G Altman BMJ 1998;317:1572-1580 (5 December)
• Treatment allocation in controlled trials: why randomise? Douglas G Altman & J Martin Bland BMJ 1999;318:1209-1209 (1 May)

1999

• Variables and parameters Douglas G Altman & J Martin Bland BMJ 1999;318:1667-1667 (19 June)
• How to randomise Douglas G Altman & J Martin Bland BMJ 1999;319:703-704 (11 September)

2000

• The odds ratio Douglas G Altman & J Martin Bland BMJ 2000;320:1468 (27 May)
• Blinding in clinical trials and other studies Simon J Day & Douglas G Altman BMJ 2000;321:504 (19 August)

2001

• Concealing treatment allocation in randomised trials Douglas G Altman & Kenneth F Schulz BMJ 2001;323:446-447 (25 August)
• Analysing controlled trials with baseline and follow up measurements Andrew J Vickers & Douglas G Altman BMJ 2001;323:1123-1124 (10 November)

2002

• Validating scales and indexes J Martin Bland & Douglas G Altman BMJ 2002;324:606-607 (9 March)

2003

• Interaction revisited: the difference between two estimates Douglas G Altman & J Martin Bland BMJ 2003;326:219 (25 January)

2004

• The logrank test J Martin Bland & Douglas G Altman BMJ 2004 328(7447):1073 (1 May)
• Diagnostic tests 4: likelihood ratios. JJ Deeks & Douglas G Altman BMJ 2004 329:168-169