Author information from the last article
Regionalt kunnskapssenter for barn og unge – psykisk helse og barnevern
Institutt for psykisk helse
NTNU
Forfatterbidrag: utforming/design av statistiske analyser, tolking av data, litteratursøk, revisjon av manus og godkjenning av innsendt manus.
Stian Lydersen er dr.ing. og professor i medisinsk statistikk ved Regionalt kunnskapssenter for barn og unge – psykisk helse og barnevern (RKBU Midt-Norge) ved Institutt for psykisk helse, NTNU.
Articles by Stian Lydersen
Do not adjust for the baseline value in observational studies
- Stian Lydersen,
- Eva Skovlund
22.11.2021:
In randomised trials with measurements at two or more time points, it is recommended to adjust for the baseline value, for example by using an analysis of covariance. In an observational study, such an analysis will lead to biased effect estimates and problems with interpretation. When we randomise...
Pairwise comparisons of three groups
- Stian Lydersen
11.10.2021:
In some studies, the researcher wants to compare three or more groups. This could, for example, be a randomised controlled trial including several treatments. In this case, it will be relevant to conduct pairwise comparisons between the groups. If the study includes three groups – A, B and C – up to...
Adjustment of p-values for multiple hypotheses
- Stian Lydersen
28.09.2021:
It is quite common to investigate multiple hypotheses in a single study, which increases the probability of Type I errors. This can be dealt with in various ways. A researcher may have various reasons for testing multiple hypotheses in the same study, for example to investigate the effect on several...
Why are one-sided hypothesis tests rarely used?
- Stian Lydersen
07.06.2021:
Many hypotheses in medical research are in principle one-sided, for example in a randomised, controlled trial that investigates whether a new type of clinical treatment has a better effect than treatment as usual. So why are two-sided hypothesis tests used? Let us assume, for example, that we...
How to summarise ordinal data
- Stian Lydersen
28.08.2020:
Many studies include ordinal data, such as the integers from 1 to 4. Can the mean or median be a relevant summary measure for such data? Ordinal scales, often called Likert scales, are frequently used in medical research and many other fields. One example is the following question in the Nord...
Mean and standard deviation or median and quartiles?
- Stian Lydersen
11.06.2020:
Mean and standard deviation are frequently used measures of central tendency and variability in data from scale variables. If data are not normally distributed, some researchers prefer reporting median and quartiles instead. But the mean and standard deviation have useful properties and can be...
Use of peripheral venous catheters in two Norwegian hospitals
- Lise Husby Høvik,
- Kari Hanne Gjeilo,
- Stian Lydersen,
- Erik Solligård,
- Jan Kristian Damås,
- Lise Tuset Gustad
22.05.2020:
Peripheral venous catheters are used frequently in Norwegian hospitals to administer intravenous fluids, drugs and blood products (1). In Norway, no record is kept of the number of patients who have a peripheral venous catheter, how many catheters each patient has, or how long these catheters remain...
26.03.2020:
In a randomised controlled trial there should be no systematic differences in background variables between the groups before treatment. But sometimes it can be sensible to adjust for some pre-defined variables in the statistical analyses. In some studies there are background variables which are...