Objectives

Topics 1
Research Design

Topic 2
Designs for Nursing Research

Topic 3
Concepts Relevant to Design

Topic 4
Design Validity

Topic 5
Good Study Design

Topic 6
Modeling study design

References

TOPIC 3:
Concepts Relevant to Design

Causality, multicausality, and probability

• Causality – This describes a relationship between two variables in which the presence or absence of one variable (the cause) determines the presence or absence, or the value, of another variable (the effect). For a relationship to be causal three conditions must be met:
  • A strong correlation must exist between the proposed cause and the effect.
  • The proposed cause must occur before the effect.
  • The cause must always be present when the effect occurs.

For example, the authors of a study designed to help improve functional health status of older women with CHD wished to show that their special intervention (SI), based on the theory of self-regulation, was responsible for any improvements (Clark, Janz, Dodge, et al., 2000). In other words, they wished to show that their SI (the IV) caused the effects on older women’s functional health status (the DV). To demonstrate that relationship, they had to control other variables or other competing possible causes of women’s improvements in functional health status. This control can be accomplished by inclusion and exclusion criteria that determine who can be in the study. Making study participants as similar as possible on selected characteristics minimizes the competing possible causes.

In the basic sciences the assumption that a single cause brings about a single effect may hold true. But, in the applied sciences research conducted with human beings indicates that the relationships between cause and effect variables are much more complex and that multicausality is a better perspective from which to explore human behavior.

• Multicausality – This perspective acknowledges that more than one variable can be the cause of an effect. In the above example, after finding that the SI indeed caused the effect of improving the functional health status of older women with CHD, the researchers could expand their understanding to include other causal factors by providing the SI to other groups of patients, such as older women with diabetes or older men with CHD. As the evidence in support of other causes of the effect accumulates, so does support for the theory of multicausality. Characteristics of studies examining multicausality include:
  • Inclusion of more independent variables than a study based on causality
  • Complex hypotheses with two or more independent variables.
    
    
• Probability – This perspective also addresses the cause and effect relationship but looks at it from a relative versus an absolute standpoint. Rather than saying that X always causes Y, in probability theory X causes Y under specified circumstances. Using the example of the SI designed to improve older women’s functional health status, the researchers could plan to evaluate the effect of the SI given at varying points in the trajectory of cardiac illness (after a first MI or with a diagnosis of congestive heart failure) and in women who were partnered or without partners. They may conclude that the SI is more effective in partnered women who have experienced an MI. Characteristics of a study from the perspective of probability theory would include:
  • Inclusion of multiple independent variables.
  • Complex hypotheses with multiple independent variables.