Limits...
Differences in Connection Strength between Mental Symptoms Might Be Explained by Differences in Variance: Reanalysis of Network Data Did Not Confirm Staging

View Article: PubMed Central - PubMed

ABSTRACT

Background: The network approach to psychopathology conceives mental disorders as sets of symptoms causally impacting on each other. The strengths of the connections between symptoms are key elements in the description of those symptom networks. Typically, the connections are analysed as linear associations (i.e., correlations or regression coefficients). However, there is insufficient awareness of the fact that differences in variance may account for differences in connection strength. Differences in variance frequently occur when subgroups are based on skewed data. An illustrative example is a study published in PLoS One (2013;8(3):e59559) that aimed to test the hypothesis that the development of psychopathology through “staging” was characterized by increasing connection strength between mental states. Three mental states (negative affect, positive affect, and paranoia) were studied in severity subgroups of a general population sample. The connection strength was found to increase with increasing severity in six of nine models. However, the method used (linear mixed modelling) is not suitable for skewed data.

Methods: We reanalysed the data using inverse Gaussian generalized linear mixed modelling, a method suited for positively skewed data (such as symptoms in the general population).

Results: The distribution of positive affect was normal, but the distributions of negative affect and paranoia were heavily skewed. The variance of the skewed variables increased with increasing severity. Reanalysis of the data did not confirm increasing connection strength, except for one of nine models.

Conclusions: Reanalysis of the data did not provide convincing evidence in support of staging as characterized by increasing connection strength between mental states. Network researchers should be aware that differences in connection strength between symptoms may be caused by differences in variances, in which case they should not be interpreted as differences in impact of one symptom on another symptom.

No MeSH data available.


Differential correlations due to different subgroup variances.(A) Density plot of a skewed variable (symptom A) partitioned into 4 quartile groups, demonstrating differential variances across the subgroups. (B) Correlations between 2 skewed variables (symptoms B and C) that are correlated with symptom A and with each other. Across subgroups the correlations vary as a function of different subgroup variances. Subgroup specific correlation coefficients are shown.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC5120783&req=5

pone.0155205.g001: Differential correlations due to different subgroup variances.(A) Density plot of a skewed variable (symptom A) partitioned into 4 quartile groups, demonstrating differential variances across the subgroups. (B) Correlations between 2 skewed variables (symptoms B and C) that are correlated with symptom A and with each other. Across subgroups the correlations vary as a function of different subgroup variances. Subgroup specific correlation coefficients are shown.

Mentions: The “network approach” to psychopathology conceptualizes mental disorders not as disorders in the organism producing mental symptoms, but merely as symptoms that causally impact on each other [1–3]. Over the past few years, the network approach enjoys growing interest from researchers. The causal connections between symptoms (e.g., between disturbed sleep and fatigue) constitute the networks’ building blocks and differences in “connection strength” are often given crucial significance. However, there is insufficient awareness of a specific pitfall regarding the interpretation of differences in connection strength. The strength of the connection between 2 variables (expressed as correlation or regression coefficient) rests principally on the amount of common (or shared) variance, relative to the total variance (i.e., common variance and unique variance including measurement error). However, the direct or indirect restriction of the variance of one or both variables (“range restriction”) reduces the connection strength [4]. The comparison of (sub)groups with different severity levels may result in different connection strengths between symptoms solely due to differences in variances [5]. Differential connection strength due to differences in variance is particularly a problem when psychological symptoms are studied in relatively healthy samples. As generally the distribution of symptom scores in such samples is positively skewed, dividing the sample into subgroups based on, for example, median or quartile scores results in different variances across the subgroups, with the largest variance in the most severe subgroup. Fig 1A illustrates the positively skewed distribution of symptom A and how subgrouping based on the quartile scores of A leads to subgroups with different variances of A. If symptoms B and C are also positively skewed, and correlated with symptom A and with each other (as psychological symptoms usually do), the variance imbalance across the subgroups may also be observed in symptoms B and C. This may easily produce differential range restriction and, hence, differential connection strength across the subgroups (Fig 1B). Whereas this methodological fallacy is lurking in many network studies (e.g., [3,6,7]), it is particularly salient in a recent study by Wigman et al. [8].


Differences in Connection Strength between Mental Symptoms Might Be Explained by Differences in Variance: Reanalysis of Network Data Did Not Confirm Staging
Differential correlations due to different subgroup variances.(A) Density plot of a skewed variable (symptom A) partitioned into 4 quartile groups, demonstrating differential variances across the subgroups. (B) Correlations between 2 skewed variables (symptoms B and C) that are correlated with symptom A and with each other. Across subgroups the correlations vary as a function of different subgroup variances. Subgroup specific correlation coefficients are shown.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC5120783&req=5

pone.0155205.g001: Differential correlations due to different subgroup variances.(A) Density plot of a skewed variable (symptom A) partitioned into 4 quartile groups, demonstrating differential variances across the subgroups. (B) Correlations between 2 skewed variables (symptoms B and C) that are correlated with symptom A and with each other. Across subgroups the correlations vary as a function of different subgroup variances. Subgroup specific correlation coefficients are shown.
Mentions: The “network approach” to psychopathology conceptualizes mental disorders not as disorders in the organism producing mental symptoms, but merely as symptoms that causally impact on each other [1–3]. Over the past few years, the network approach enjoys growing interest from researchers. The causal connections between symptoms (e.g., between disturbed sleep and fatigue) constitute the networks’ building blocks and differences in “connection strength” are often given crucial significance. However, there is insufficient awareness of a specific pitfall regarding the interpretation of differences in connection strength. The strength of the connection between 2 variables (expressed as correlation or regression coefficient) rests principally on the amount of common (or shared) variance, relative to the total variance (i.e., common variance and unique variance including measurement error). However, the direct or indirect restriction of the variance of one or both variables (“range restriction”) reduces the connection strength [4]. The comparison of (sub)groups with different severity levels may result in different connection strengths between symptoms solely due to differences in variances [5]. Differential connection strength due to differences in variance is particularly a problem when psychological symptoms are studied in relatively healthy samples. As generally the distribution of symptom scores in such samples is positively skewed, dividing the sample into subgroups based on, for example, median or quartile scores results in different variances across the subgroups, with the largest variance in the most severe subgroup. Fig 1A illustrates the positively skewed distribution of symptom A and how subgrouping based on the quartile scores of A leads to subgroups with different variances of A. If symptoms B and C are also positively skewed, and correlated with symptom A and with each other (as psychological symptoms usually do), the variance imbalance across the subgroups may also be observed in symptoms B and C. This may easily produce differential range restriction and, hence, differential connection strength across the subgroups (Fig 1B). Whereas this methodological fallacy is lurking in many network studies (e.g., [3,6,7]), it is particularly salient in a recent study by Wigman et al. [8].

View Article: PubMed Central - PubMed

ABSTRACT

Background: The network approach to psychopathology conceives mental disorders as sets of symptoms causally impacting on each other. The strengths of the connections between symptoms are key elements in the description of those symptom networks. Typically, the connections are analysed as linear associations (i.e., correlations or regression coefficients). However, there is insufficient awareness of the fact that differences in variance may account for differences in connection strength. Differences in variance frequently occur when subgroups are based on skewed data. An illustrative example is a study published in PLoS One (2013;8(3):e59559) that aimed to test the hypothesis that the development of psychopathology through “staging” was characterized by increasing connection strength between mental states. Three mental states (negative affect, positive affect, and paranoia) were studied in severity subgroups of a general population sample. The connection strength was found to increase with increasing severity in six of nine models. However, the method used (linear mixed modelling) is not suitable for skewed data.

Methods: We reanalysed the data using inverse Gaussian generalized linear mixed modelling, a method suited for positively skewed data (such as symptoms in the general population).

Results: The distribution of positive affect was normal, but the distributions of negative affect and paranoia were heavily skewed. The variance of the skewed variables increased with increasing severity. Reanalysis of the data did not confirm increasing connection strength, except for one of nine models.

Conclusions: Reanalysis of the data did not provide convincing evidence in support of staging as characterized by increasing connection strength between mental states. Network researchers should be aware that differences in connection strength between symptoms may be caused by differences in variances, in which case they should not be interpreted as differences in impact of one symptom on another symptom.

No MeSH data available.