|
...different trailheads at two different parks, trailhead might be treated as factor that is nested within a "park" factor. Much more familiar "crossed" designs transpire when all levels of one factor of a design occur under all levels of another factor. Such a design might occur if we collected data under two different experimental conditions at each of two trailheads. Figures 1a and 1b contrast these two designs in two different types of studies. In the nested design in Figure 1a, each of four courses (i.e., four different groups of participants) is only present under a single program type (e.g., land-based vs. water-based adventure). In the crossed design (Figure 1b), each of the two instructors is present within both of the program types. Although myriad research contexts in parks, recreation, and tourism give rise to the recognition and modeling of nested effects, only very rarely are they acknowledged and incorporated into research designs (e.g., Caldwell, Darling, Payne, & Dowdy, 1999; Long, Ellis, Trunnell, Tatsugawa, & Freeman, 2001).
[FIGURE 1 OMITTED]
A few examples provide evidence of the great breadth of these applications. A recreation researcher investigating natural resource settings who samples visitors at multiple park sites within different parks might incorporate "site" as a factor nested within the independent variable that is of interest (e.g., ethnicity, outdoor recreation behavior; Carr & Williams, 1993). Nesting might also be inherent in certain studies of employees in recreation management contexts. An investigator studying the effects of different management strategies, for example, might collect data from various work groups, such as park maintenance, recreation center managers, special services employees, and others. In this example, work group would be nested within management strategy because each work group would be exposed to only one management strategy. A study of effects of a specific therapeutic recreation intervention might involve clients nested within cohorts or assigned treatment groups, diagnostic groups, or therapists (Wells, 2001).
Experience sampling studies and studies that use time diary methods (e.g., Caldwell et al, 1999; Csikszentmihalyi & Csikszentmihalyi, 1988; Ellis, Voelkl, & Morris, 1994) provide yet another example of nested effects. Daily experiences of participants in these studies, may be sampled on numerous occasions over the course of two or more days. The effects of daily experience predictor variables that are of interest are thus nested within "participant" and "day" variables. In some instances of time diary and ESM research, predictor variables are of interest at both the level of the experience and at the level of the individual. Caldwell, et al. (1999), for example, conducted a time diary study to examine the relationship between select situational (daily experience) variables, individual difference variables (intrinsic motivation, parental monitoring, and gender), and boredom. That design allowed testing the effects of the situational variables that were nested within participants as well as testing the effects of the individual differences variables. A substantial potential exists for incorporating nested effects into park, recreation, and tourism research designs and for understanding these predictors at different, hierarchically arranged levels.
Neglecting to include nested effects in designs creates a number of undesirable consequences. Two of the most notable of these are failure to account for important sources of variance and violation of the statistical assumption of independence of observations. With respect to the first of these issues, variance that could be explained by the nested effects is unaccounted for and is relegated to error terms. The result is a design that is less than optimal in efficiency (i.e., statistical power is compromised) and does not provide insight into the role of the nested variable in influencing the dependent variable of interest. Further, in many instances, failure to incorporate the nested effect into the design is a direct violation of the independence assumption that underlies key test statistics such as the F ratio and the t ratio. Individuals who are part of a single group that receives treatment collectively influence one another's experiences. In such circumstances, observations are...
NOTE: All illustrations and photos
have been removed from this article.
More articles from Journal of Leisure Research
Leisure expenditures of retired and near-retired households., January 01, 2004
Sport and Social Exclusion.(Book Review), January 01, 2004
Black Recreation: a Historical Perspective.(Book Review), January 01, 2004
Leisure Life: Myth, Masculinity and Modernity.(Book Review), January 01, 2004
Looking for additional articles?
Search our database of over 3 million articles.
Looking for more in-depth information on this industry?
Search our complete database of Industry & Market reports by text, subject, publication
name or publication date.
About Goliath
Whether you're looking for sales prospects, competitive information, company
analysis or best practices in managing your organization,
Goliath can help you meet your business needs.
Our extensive business information databases empower business
professionals with both the breadth and depth of credible,
authoritative information they need to support their business
goals. Whether it be strategic planning, sales prospecting,
company research or defining management best practices -
Goliath is your leading source for accurate information.
|
