Patterns of Perceived Control That Buffer Against Cognitive Decline in Midlife and Old Age

Abstract

Objectives: The relationship between domain-general or global perceptions of control and cognition is well-established. However, little is known about how these domain-general beliefs combine with domain-specific perceptions in central life domains to form multifaceted patterns of control that may buffer against cognitive declines in midlife and old age.

Methods: We used 9-year data from the Midlife in the United States Study (n = 2,734, Mage = 55 years, range = 33-83; 58% female) to identify profiles of domain-general (personal mastery, perceived constraints) and domain-specific control over central life domains (health, work, finances, others' welfare, child relationships, and partner relationship). We subsequently assessed profile differences in 9-year trajectories of cognitive aging and whether these differences became pronounced in old age.

Results: Factor mixture models showed that 4 common profiles emerged: low control, family control, work control, and domain-specific control. Autoregressive ANCOVAs showed the family control and work control profiles experienced the least 9-year decline in executive functioning (F3,2330 = 3.46, p = .016). Moderation models showed the family control profile experienced less decline in executive functioning than the work control profile, but only in old age (b = -0.006, p = .020). Supplemental analyses showed profile differences in cognitive aging were (a) mediated by theory-derived process variables (positive and negative affect) and (b) extended to a broader suite of health-related developmental outcomes (functional limitations, chronic conditions, and mortality).

Discussion: Findings inform lifespan theories of development by documenting meaningful patterns of domain-general and domain-specific control that have implications for healthy cognitive aging.

Keywords: Cognitive aging; Control belief profiles; Domain-specific; Latent profile analysis; Person-centered approach.

Figure 1.

Results from the k = 4 profile model of domain-specific and domain-general perceived control. The low control profile (n = 670) reflected individuals with very low levels of control across all aspects of domain-specific and domain-general control. The family control profile (n = 663) reflected individuals with high levels of control over their family relationships with children and spouses and relatively average levels of control over most other aspects (with above-average levels of mastery). The work control profile (n = 793) had higher levels of control over work and finances, lower levels of control over family relationships with children and spouses, and above-average levels of mastery and below-average levels of control. The high domain-specific control profile (n = 608) had high levels of control over all aspects of domain-specific control but had average levels of mastery and constraints.

Figure 2.

Contextualized effect sizes of profile differences on regressed change in executive functioning. Estimates suggested rates of 9-year decline in executive functioning were respectively reduced by approximately 22% and 24% for the family control profile versus the low control and domain-specific control profiles. Predicted values were adjusted for model covariates and for (raw) average sample declines of −0.256 units in executive functioning. ^†22% reduction in rate of decline. ^††24% reduction in rate of decline.

Figure 3.

Age × Work Control interaction predicting 9-year regressed change in executive functioning. Predicted values were adjusted for model covariates and for (raw) average sample declines of −0.256 units in executive functioning.