Psychometric analysis of the Mental Health Continuum-Short Form (MHC-SF)

Comparing Rasch, CFA and Mokken models

Author
Affiliation

Magnus Johansson

RISE Research Institutes of Sweden

Published

2024-02-08

Code 
# one package below requires that you use devtools to install it manually:
# first install devtools by
# install.packages('devtools')

library(RISEkbmRasch) # devtools::install_github("pgmj/RISEkbmRasch")
library(grateful)
library(ggrepel)
library(car)
library(kableExtra)
library(readxl)
library(tidyverse)
library(eRm)
library(mirt)
library(psych)
library(psychotree)
library(matrixStats)
library(reshape)
library(knitr)
library(patchwork)
library(formattable) 
library(glue)

### optional libraries
#library(TAM)
#library(skimr)

### some commands exist in multiple packages, here we define preferred ones that are frequently used
select <- dplyr::select
count <- dplyr::count
recode <- car::recode
rename <- dplyr::rename

source("RISE_theme.R")
Code 
### other, bigger dataset from [@echeverría2017]
### read file
df.all <- read_excel("data/data_sMHCSF_Echeverria2017.xlsx")
df <- df.all
### create dif variables
dif.sex <- factor(df$Sex)
df$Sex <- NULL

### Load item information
# make sure that variable names in df match with itemlabels$itemnr
itemlabels <- read_excel("data/itemlabels_MHC_SF.xlsx") %>% 
  mutate(item = str_squish(item))

names(df) <- itemlabels$itemnr

df <- df %>%
  mutate(across(everything(), ~ car::recode(.x,"'Never'=0;'1 or 2 times a month'=1;'About 1 time a week'=2;'About 2 or 3 times a week'=3;'Almost daily'=4;'Daily'=5", as.factor = FALSE)))

0.1 Introduction

In a paper recently made available as a preprint (Johansson et al. 2023), we argue that the basic aspects of a psychometric analysis should include information about five basic criteria:

  • Unidimensionality
  • Response categories
  • Invariance
  • Targeting
  • Measurement uncertainties (reliability)

0.2 About the MHC-SF

The Mental Health Continuum-Short Form (MHC-SF) is a well-being scale designed to assess emotional, psychological and social well-being (Keyes 2009). The dataset for this analysis was made available as open data connected to a psychometric analysis publication (Echeverría et al. 2017, n.d.).

While there are papers suggesting a three factor or bi-factor model for the MHC-SF, in practice it is usually used as a sum scored unidimensional scale, which is why our analyses will focus on how the data fits a unidimensional model.

Here is some text about the MHC-SF that I wrote some years back when investigating different well-being questionnaires:

Flourishing & Mental Health Continuum Short Form (MHC-SF, Keyes, 2014). 14 items (derived from the 40-item long version) measuring the following three aspects of flourishing (Keyes, 2002, 2005, 2006): emotional wellbeing (3 items; e.g., “In the past month, how often have you felt happy?”); psychological wellbeing (6 items); e.g., “In the past month, how often did you feel good at managing the responsibilities of your daily life?”); and social wellbeing (5 items; e.g., “In the past month, how often did you feel that you belonged to a community like a social group, your school, or your neighborhood?”). Participants rated their responses using a scale with the following labels: 1 (Never), 2 (Once or twice), 3 (About once a week), 4 (Two or three times a week), 5 (Almost every day), and 6 (Every day). (Paragraph copied from (Sahdra et al., 2016)).

Other factor structures have been proposed as well, such as a bi-factor model, combining the three factors with a general well-being factor (de Bruin & du Plessis, 2015; Lamborn et al., 2018) and a 2-factor model with mental health and mental illness as correlated factors (Lamers et al., 2011), but in general the 3-factor model seems replicable. IRT analysis (Lamers et al., 2012) showed DIF for gender (item 8), age (items 10 and 12) and education level (item 5), estimated to be of non-significant impact on latent scales (but says nothing about sum scores). Items 4 and 5 from the social well-being subscale have been found to have very low factors loadings (.32-.34) in two papers (Lamers et al., 2011; Lupano Perugini et al., 2017).

0.2.1 Items

Code 
RIlistitems(df)
itemnr item
mhc1 Happy
mhc2 Interested in life
mhc3 Satisfied with your life
mhc4 That you had something important to contribute to society?
mhc5 That you belonged to a community?
mhc6 That our society is becoming a better place for people like you?
mhc7 That people are basically good?
mhc8 That the way our society works makes sense to you?
mhc9 That you liked most parts of your personality?
mhc10 Good at managing the responsibilities of your daily life?
mhc11 That you had warm and trusting relationships with others?
mhc12 That you had experiences that challenged you to grow and become a better person?
mhc13 Confident to think or express your own ideas and opinions?
mhc14 That your life has a sense of direction or meaning to it?

0.2.2 Response categories

  • ‘Never’,
  • ‘1 or 2 times a month’,
  • ‘About 1 time a week’,
  • ‘About 2 or 3 times a week’,
  • ‘Almost daily’,
  • ‘Daily’

0.3 Demographics

Code 
RIdemographics(dif.sex, "Gender")
Gender n Percent
Man 962 28.7
Woman 2393 71.3

0.4 Descriptives

Response distribution for all items are summarized below.

Code 
# Specify the numeric-to-label mapping
numeric_to_labels <- c('Never', '1 or 2 times a month', 'About 1 time a week', 'About 2 or 3 times a week', 'Almost daily', 'Daily')
df %>% 
  mutate(across(everything(), ~ factor(.x, labels = numeric_to_labels))) %>% 
  RIallresp()
Response category Number of responses Percent
Never 4439 9.5
1 or 2 times a month 5742 12.2
About 1 time a week 5053 10.8
About 2 or 3 times a week 7895 16.8
Almost daily 13076 27.8
Daily 10765 22.9

0.4.1 Descriptives - item level

Code 
RIlistItemsMargin(df, fontsize = 12)
itemnr item
mhc1 Happy
mhc2 Interested in life
mhc3 Satisfied with your life
mhc4 That you had something important to contribute to society?
mhc5 That you belonged to a community?
mhc6 That our society is becoming a better place for people like you?
mhc7 That people are basically good?
mhc8 That the way our society works makes sense to you?
mhc9 That you liked most parts of your personality?
mhc10 Good at managing the responsibilities of your daily life?
mhc11 That you had warm and trusting relationships with others?
mhc12 That you had experiences that challenged you to grow and become a better person?
mhc13 Confident to think or express your own ideas and opinions?
mhc14 That your life has a sense of direction or meaning to it?
Code 
RItileplot(df)

Code 
RIbarstack(df) +
  scale_fill_viridis_d(labels = rev(numeric_to_labels), direction = -1)

Code 
RIbarplot(df)

Code 
RImissing(df)

0.5 References

Echeverría, Guadalupe, Manuel Torres-Sahli, Nuria Pedrals, Oslando Padilla, Attilio Rigotti, and Marcela Bitran. 2017. “Validation of a Spanish Version of the Mental Health Continuum-Short Form Questionnaire.” Psicothema 29 (February): 96–102. https://doi.org/10.7334/psicothema2016.3.
———. n.d. “Data, Instrument and Code for Validation of s-MHC-SF.” https://doi.org/10.6084/m9.figshare.3370828.v1.
Johansson, Magnus, Marit Preuter, Simon Karlsson, Marie-Louise Möllerberg, Hanna Svensson, and Jeanette Melin. 2023. “Valid and Reliable? Basic and Expanded Recommendations for Psychometric Reporting and Quality Assessment.” https://doi.org/10.31219/osf.io/3htzc.
Keyes, Corey L. M. 2009. “Brief Description of the Mental Health Continuum Short Form (MHC-SF).” https://peplab.web.unc.edu/wp-content/uploads/sites/18901/2018/11/MHC-SFoverview.pdf.