Related Experiment Video
Updated: Jul 17, 2026
Inverse Probability of Treatment Weighting (Propensity Score) using the Military Health System Data Repository and National Death Index
Published on: January 8, 2020
The SF36 Version 2: critical analyses of population weights, scoring algorithms and population norms
Graeme Hawthorne1, Richard H Osborne, Anne Taylor
1Department of Psychiatry, Royal Melbourne Hospital, The University of Melbourne, Level 1 North, Main Building, Grattan St, Parkville, VIC, 3052, Australia. graemeeh@unimelb.edu.au
Background:
The SF36 Version 2 (SF36V2) is a revision of the SF36 Version 1, and is a widely used health status measure. It is important that guidelines for interpreting scores are available.
Method:
A population sample of Australians (n = 3015) weighted to achieve representativeness was administered the SF36V2. Comparisons between published US weights and sample derived weights were made, and Australian population norms computed and presented.
Major Findings:
Significant differences were observed on 7/8 scales and on the mental health summary scale. Possible causes of these findings may include different sampling and data collection procedures, demographic characteristics, differences in data collection time (1998 vs. 2004), differences in health status or differences in cultural perception of the meaning of health. Australian population norms by age cohort, gender and health status are reported by T-score as recommended by the instrument developers. Additionally, the proportions of cases within T-score deciles are presented and show there are important data distribution issues.
Principal Conclusions:
The procedures reported here may be used by other researchers where local effects are suspected. The population norms presented may be of interest. There are statistical artefacts associated with T-scores that have implications for how SF36V2 data are analysed and interpreted.
Related Concept Videos
01:24Testing a Claim about Population Proportion
There are two methods of testing a claim about a population proportion: (1) Using the sample proportion from the data where a binomial distribution is approximated to the normal distribution and (2) Using the binomial probabilities calculated from the data.
The first method uses normal distribution as an approximation to the binomial distribution. The requirements are as follows: sample size is large...
01:26Estimating Population Standard Deviation
01:14Central Limit Theorem
The sample size, n, that...
01:15One-Way ANOVA: Unequal Sample Sizes
01:11Testing a Claim about Mean: Known Population SD
Estimating a population mean requires the samples to be distributed normally. The data should be collected from the randomly selected samples having no sampling bias. The sample size needed to be higher than 30, and most importantly, the population standard deviation should be already known.
In most realistic situations, the population standard deviation is often unknown, but in rare circumstances, when it...
01:15One-Way ANOVA: Equal Sample Sizes
Different sample means can result in different values for the variance estimate: variance between samples. This is because the variance between samples is calculated as the product of the sample size and the variance between the...