Complex Survey Data Analysis: A Comparison of SAS, SPSS and STATA

Oyeyemi, Gafar Matanmi; Adewara, A. A.; Adeyemi, Rasheed A.

doi:10.3923/ajms.2010.33.39

Cited by 15 publications

(9 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To examine if the differences in the distribution of these variables between the survey years were significant we used Chi-square tests. Because the Child Monitor survey utilized a complex sample design, a sample weight was assigned to each person sampled and therefore complex samples statistics were used to produce an unbiased regional estimate [27,31].…”

Section: Discussionmentioning

confidence: 99%

Parents’ underestimation of their child’s weight status. Moderating factors and change over time: A cross-sectional study

et al. 2020

View full text Add to dashboard Cite

BackgroundParents' underestimation of their child's weight status can hinder active participation in overweight prevention programs. We examined the level of agreement between the parents' perception of their child's weight status and the child's actual weight status, moderating factors, and change over time. MethodsThis cross-sectional study used data collected in 2009 (n = 8105), 2013 (n = 8844) and 2017 (n = 11,022) from a community-based survey conducted among parents of children age 2-12 years in the Netherlands. Parents classified their perception of their child's weight status on a 5-point Likert scale. In 2009 and 2013, the child's BMI was calculated from selfreported data by parents. The level of agreement between the parent's perception of the weight status and the actual weight status was examined using Cohen's kappa. The role of demographic factors on parents' perception were examined using logistic regression.

show abstract

Section: Discussionmentioning

confidence: 99%

Parents’ underestimation of their child’s weight status. Moderating factors and change over time: A cross-sectional study

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The complex sample survey capabilities of SPSS were used to analyze the data, after specifying that there were 7 strata and that the PSUs in these strata were households. 20 , 21 The sampling weights used to adjust for probability of selection during sampling were computed using the process described by Lameshow and colleagues. 21 All statistical analyses were performed using SPSS software version 15.0 (SPSS Inc., Chicago, IL, USA).…”

Section: Methodsmentioning

confidence: 99%

Prevalence of Physical Activity Among Adults in a Metropolitan Nigerian City: A Cross-Sectional Study

Oyeyemi¹,

Oyeyemi²,

Jidda³

et al. 2013

Journal of Epidemiology

View full text Add to dashboard Cite

BackgroundBaseline information on physical activity is relevant to controlling the epidemic of chronic noncommunicable diseases occurring in many African countries. However, standardized data on physical activity are lacking in Nigeria. We assessed the prevalence of physical activity and its relationships with sociodemographic characteristics in a subnational sample of Nigerian adults.MethodsA cross-sectional survey was conducted among a representative sample of 934 adults (age, 20–82 years) living in metropolitan Maiduguri, Nigeria. Physical activity was measured using the validated Nigerian version of the International Physical Activity Questionnaire (Hausa IPAQ-SF). Using the World Health Organization (WHO) guideline, participants were classified as sufficiently active or insufficiently active. Sociodemographic correlates of sufficient physical activity were identified using multinomial logistic regression.ResultsOverall, 68.6% of Nigerian adults were sufficiently active. There was no significant difference (P > 0.05) in prevalence of physical activity between men (68.0%) and women (69.3%), but physical activity tended to decrease with increasing age category, especially among men. Physical activity prevalence was positively associated with being married (OR = 1.52, CI = 1.04–4.37) and blue collar work (OR = 2.19, CI = 1.16–4.12) and negatively associated with car ownership (OR = 0.38, CI = 0.17–0.86) and higher income (OR = 0.54, CI = 0.10–0.95).ConclusionsThe prevalence of physical activity varied between sociodemographic subgroups of Nigerian adults; thus, public health policies and interventions based on ecologic models of health behaviors may be warranted in promoting physical activity in Nigeria.

show abstract

“…Variance estimates within this complex survey design analysis was correctly accounted for using SAS survey procedures (Oyeyemi et al, 2010). Initially, χ 2 tests were used to examine differences in subject characteristics, stratified by gender.…”

Section: Methodsmentioning

confidence: 99%

Gender and prescription opioids: Findings from the National Survey on Drug Use and Health

Back

Payne

Simpson

et al. 2010

Addictive Behaviors

213

164

View full text Add to dashboard Cite

Background Significant gender differences in drug and alcohol use have been reported, however little is known about gender differences in prescription opioid misuse and dependence. This study compared correlates, sources and predictors of prescription opioid non-medical use, as well as abuse or dependence among men and women in a nationally-representative sample. Methods Participants were 55,279 (26,746 men, 28,533 women) non-institutionalized civilians aged 12 years and older who participated in the National Survey on Drug Use and Health. Results Rates of lifetime and past year non-medical use of prescription opiates were 13.6% and 5.1%, respectively. Significantly more men than women endorsed lifetime (15.9% vs. 11.2%) and past year use (5.9% vs. 4.2%; ps < .0001). Among past year users, 13.2% met criteria for current prescription opiate abuse or dependence, and this did not differ significantly by gender. Polysubstance use and treatment underutilization were common among both men and women, however significantly fewer women than men had received alcohol or drug abuse treatment (p = .001). Men were more likely than women to obtain prescription opioids for free from family or friends, and were more likely to purchase them from a dealer (ps < .01). Gender-specific predictors of use as compared to abuse/dependence were also observed. Conclusions The findings highlight important differences between men and women using prescription opiates. The observed differences may help enhance the design of gender-sensitive surveillance, identification, prevention and treatment interventions.

show abstract

Complex Survey Data Analysis: A Comparison of SAS, SPSS and STATA

Cited by 15 publications

References 0 publications

Parents’ underestimation of their child’s weight status. Moderating factors and change over time: A cross-sectional study

Parents’ underestimation of their child’s weight status. Moderating factors and change over time: A cross-sectional study

Prevalence of Physical Activity Among Adults in a Metropolitan Nigerian City: A Cross-Sectional Study

Gender and prescription opioids: Findings from the National Survey on Drug Use and Health

Contact Info

Product

Resources

About