Mental health problems of children and adolescents occur frequently in the general population with prevalence rates of psychopathology estimated from 7% in rural Brazil and Norway, 10% in Britain and Denmark and up to 15% in Russia and Bangladesh [1]–[6]. In Denmark one prevalence study indicated that approximately 10% of Danish 8–9-year-olds meet the DSM-IV criteria for a psychiatric diagnosis [7]. However, a considerable discrepancy has been found between prevalence rates and the number of children being treated through childhood and adolescence. This is disturbing as psychopathology developed in childhood shows stability over time and can progress into adult psychiatric disorders. Factors associated with the development of psychopathological disorders include age and gender, socioeconomic markers and family conditions [8]. The strength of these associations may however vary between cultural settings. In order to screen for mental health disorders in children and adolescents there is a need for instruments to assess for behavioural and emotional problems, which have been validated across cultural settings.

The strengths and difficulties questionnaire (SDQ) is a brief instrument developed to screen for child and adolescent psychopathology. It is used worldwide, has been translated into more than 60 languages, and has screening properties comparable with more comprehensive instruments [9]. It consists of 25 items and generates scores within five domains of psychological adjustment: Hyperactivity/Inattention (hereafter Hyperactivity), Peer problems, Conduct problems, Emotional symptoms and Prosocial behaviours. The items are based on key symptoms for DSM-IV diagnoses and have been grouped into scales using exploratory factor analysis. The five hyperactivity items have for example been selected to assess hyperactivity, inattention and impulsiveness as these constitute the key symptoms for the DSM diagnosis of Attention/Deficit Hyperactivity Disorder (ADHD). The questionnaire is widely used for clinical as well as research purposes [10].

The SDQ appeals to researchers as well as clinicians for several reasons: firstly, because of its brevity, secondly because it covers key aspects of common childhood and adolescence psychopathology, and thirdly because it includes strengths as well as difficulties, which makes it more acceptable for parents, especially in the general population.

The SDQ has been used extensively in European as well as non-European contexts [10], [11] since it was developed by Goodman in Britain in the late 1990s as an extension of the early work of Rutter [12]. A recently published review looking into the psychometric properties of the parent and teacher versions of the SDQ included 48 studies from 17 different cultural settings and a total of 131,223 raters [11]. Mean scores and cut-offs have shown some variation across cultural settings indicating some variations in the prevalence of child and adolescence psychopathology. British presented mean scores and cut-offs tend to be higher than northern European mean scores [13], but similar to or lower than the mean scores presented for the southern European countries [14]. Outside European settings, markedly higher than British mean scores have been reported for (non-western) Chinese and Brazilian children [3], [15] but similar to American and Australian samples [16], [17].

Most studies looking into the factor structure of the SDQ have applied exploratory factor analyses (EFA) and Principal component analysis (PCA). These have by and large found support for Goodman's predicted five factor model [15], [18]. Few studies have applied confirmatory factor analysis (CFA) and those that have done so have not found unequivocal support for the five factor model [19]–[21]. Dickey and Blumberg found support for a three factor structure representing prosocial, internalising and externalising problems in an American sample of 4–17-year-olds and concluded that U.S. parents may construe conduct and peer problems differently from European parents [19]. Along the same lines, a British study concluded that there are advantages to using the broader internalising and externalising subscales for analyses in low-risk epidemiological samples, while one should retain the five subscales when screening for disorders among high-risk children [20]. On the other hand one thorough Norwegian study applying both confirmatory and exploratory factor analyses found none of the alternative models to fit the data better than a slightly modified version of Goodman's five factor model [21].

The discrepancies found in the existing literature for the mean scores and cut-offs, as well as for the factor structure therefore need further investigation. Culture plays a major role in the expression of psychosocial problems and for this reason previous investigations of discrepancies between studies have not been able to identify the extent to which they are expressions of true differences in scores and to what extent they are caused by demographic or cultural variations. In order to rule out any potential cultural and linguistic factors there is therefore a need for a study looking further into these variables within a homogenous cultural and linguistic setting from a large number of raters. Such study would also permit for cross-age, cross-gender and cross-rater comparisons.

Several large scale birth cohorts have been established in Denmark within the last few decades, a number of which have included the SDQ in their follow-up phases. Denmark may therefore, despite its small size, be the country in which the largest number of SDQ ratings has been collected. The aims of the current study were therefore: 1. to evaluate the internal reliability and the five domains of psychological adjustment supposedly evaluated by the SDQ by means of principal component analysis, and 2. to evaluate the mean scores and percentiles across age groups, gender and raters. This is performed for parent and teacher raters, boys and girls and 5-, 7- and 10–12-year-olds separately. It is hypothesised that sound reliability will be established, particularly so for the hyperactivity scale, and that the original proposed five scale factor structure will be confirmed. It is further hypothesised that mean scores and percentiles will be similar to those found in the other Nordic countries but lower compared to other European settings.

This article presents the psychometric properties of the Danish SDQ from a total of 71,265 raters after excluding data on the basis of missing values. To the authors' knowledge this is the first time that data from so many informants from the same cultural setting have been included in the same study. By contrast, a recently published review presented results from 48 studies from across the world with a total of 131,223 raters [11]. This review noted that the methodologies of the included studies varied making it difficult to compare them. Strengths of the present study are the inclusion of studies that apply similar methodologies and are derived from the same cultural setting creating a unique opportunity to investigate the psychometric properties of the SDQ between genders, ages and raters. It appears from the above presented analyses that the psychometric properties of the Danish version of the SDQ are strong, particularly for the teacher version.

The pattern matrices of the EFA replicated Goodman's five factor structure for parents and teachers. It appears from the higher teacher loadings that the questionnaire works a little better for teachers than for parents. Investigating the structure matrices, however, revealed two kinds of scale problems that are worth mentioning: firstly, that Conduct items load on non-conduct scales and conversely non-conduct items load on the Conduct scale and secondly that the positively worded items tend to load on the Prosocial scale. This is more so for teachers than for parents. With regard to the high loading of the Conduct items on the other scales it seems that these items are as much part of a hyperactivity construct as part of a notion of conduct for teachers. This is somewhat in line with a British study [20] applying CFA that concludes that the five subscales may not tap into distinct aspects of child mental health among low-risk, epidemiological samples which is exactly what characterises the four included samples. Instead one should use the broader Internalising and Externalising subscales. In regards to the positively worded items this finding is in line with Goodman [18] who also found these items to load on the Prosocial scale. Although the positively worded items are precisely one of the advantages of this questionnaire they also seem to involve some psychometric drawbacks. Thus, although the five dimensions could overall be confirmed by examination of the pattern matrix (indicating no scale problems) the distinctiveness of the factors and some of the items do not seem particularly strong when one investigates the structure matrix that allows for cross-loadings between factors. For the clinicians this means that one should not put too much emphasis on the five individual subscales, much less use the SDQ as a diagnostic tool. These rater differences also illustrates the importance of running rater specific analyses.

The reliability estimates presented above are very similar to those found in other studies [11]. Sound reliability estimates and factor loadings of the hyperactivity scale indicate that the SDQ provides a solid estimate of symptoms of ADHD. The reliability of the Emotional scale has generally been reported as being poorer than what was found in this study, indicating that Danish parent and teachers may be better at reporting Internalising problems compared to other cultural settings. The Conduct subscale was, on the other hand, uniformly found to have the lowest reliability estimates and the lowest factor loadings, indicating a limitation of the usefulness of the scale within a low risk sample.

Lower reliability estimates were found for parents compared to teachers indicating that teachers are more likely than parents to view individual subscale items as measuring the same ability or trait. This may indicate that the subscale items may be viewed as less one-dimensional by parents caused by different tester attitudes. Conversely, teachers may be influenced by some sort of “halo-effect” which in the literature is referred to as the impact of one class of behaviour on the perception of another [30]. This means that children exhibiting problem behaviours in one area are more likely to be rated as problematic in other areas as well. Support for this hypothesis also comes from the teacher factor loadings where several items show high loadings on more than one subscale. Halo-effects have in the literature been found to show a different pattern for boys and girls and these tendencies could also contribute to the higher reliability estimates for boys than for girls [30].

The means and percentiles presented above are in line with those reported for other Scandinavian studies and somewhat lower on the Hyperactivity, Peer and Total difficulties scales compared to those found in other European and non-European studies [10], [11]. The 90^th percentile for the Total difficulties scores were for boys and girls in the present study found to be between 11 and 14 for parent ratings and between 12 and 18 for teacher ratings. These parent ratings are somewhat lower than the British recommendation of 17 [18] and Swedish of 14 [31] indicating that children of all the included age groups are rated as exhibiting fewer emotional and behavioural problems compared to other samples. Different explanations for the above described differences can be given. Firstly, they may indicate that Danish parents and teachers rate children more positively than do British parents and teachers. When the upper 10% British percentiles for boys and girls were applied for parent and teacher raters it appeared that the teacher ratings were more similar across cultures than the parent ratings indicating that this is only so for the parents. Secondly, it may be that the included samples are more selective and therefore less representative of the general population compared to the samples included in other studies. The present study is characterised by four large scale cohorts with attrition rates between 5 and 56% making the samples more or less non-representative of the general population biasing the included children toward a psychiatrically low-risk sample. This was particularly true for the large DNBC cohort. Since data were included in the analyses without compensatory weightings for underrepresented groups this may have introduced a potential source of bias. Thirdly, it may reflect actual behavioural and emotional differences in the Nordic countries characterised by better social security, low poverty, high living standards and less economic and social inequality. Meltzer et al. [8] found that children with mental disorder were more likely to live in lower income households, with a lone parent and in social sector housing. Denmark is characterised by a relatively homogenous population with a high level of social security which may cause fewer behavioural and emotional problems in the general populations.

Looking into potential gender differences boys were found to score higher than girls on the Hyperactivity, Conduct and Peer subscales and Total difficulties and Impact scores. Girls on the other hand were rated higher on the Emotional and Prosocial scales. Few other studies have reported potential significant differences between boys and girls [32]. The present study found medium to large effect sizes between boys and girls on the Hyperactivity, Conduct and Prosocial scales and Total difficulties scores. The present large-scale study has thus shown the importance of running the analyses separately for boys and girls. Failure to do so may potentially mask large differences between the sexes.

Younger children were in the present study found to score higher than older ones on the two Externalising subscales (Hyperactivity and Conduct scales). This is in similar vein to a German study [33] reporting younger children exhibiting more hyperactivity compared to older ones and a Dutch study [34] reporting a decline in parent ratings of total difficulties, emotional and hyperactivity scores with age. Interestingly, this same study reported increased total difficulties, conduct and emotional scores for teacher ratings as compared to parental ratings. Again, these results show the importance of running separate analyses for younger and older children.

Some limitations of the present study should be noted. The questionnaires from all the cohorts were mainly completed by mothers rather than fathers and this may have had an impact on the distribution of scores. Generally, other studies do not report on the gender distribution of the rater and this may cause some of the variability of scores across studies. Additionally, future studies would benefit from including information on socioeconomic risk factors. One study did find strong effects of social class on the Hyperactivity scale and somewhat less on the Peer scale [33] so controlling for a number of risk factors as for example second order factors in confirmatory factor analyses will further improve the findings of future studies. Future studies should further investigate different factor models using a confirmatory factor analytic approach. Finally, the SDQ is a widely used instrument in Danish epidemiologic studies and future work could advantageously examine the predictive validity of the SDQ as this is of prime importance in order to know how well the SDQ predicts future child, adolescent and adult psychiatric illness.

In conclusion, despite the above mentioned limitations this study demonstrates that SDQ is a well-functioning questionnaire with sound psychometric properties. The internal consistency is high, the factor structure could largely be confirmed and the means and percentiles make theoretical sense.