Statistics

BS-EBM Unit 22: Assessment Questions 1 to 10



The sample size was 26 matched pairs consisting of 52 women, n = 26 depotmedroxyprogesterone acetate (DMPA) and n = 26 copper intrauterine device (TCu 380A IUD), as indicated by the study narrative and Table 2. Yes, the number of subjects in each group was adequate based on the power analysis recommendation of a minimum of 20 subjects per group (Aberson, 2019; Gray, Grove, & Sutherland, 2017). The groups were of equal size, which is another study strength (Grove & Gray, 2019).
According to Table 2 and the study narrative, both parametric paired samples ttest (Student’s t-test paired) and nonparametric Wilcoxon signed-rank test were conducted to examine differences in these paired samples. On Table 2, t-test results are labeled with an “a” and Wilcoxon results are labeled with a “b.” Two types of pairs were examined: differences in baseline measurements and 12 months measurements (pretest and posttest measures) as well as differences between DMPA and TCu 380A IUD matched pairs. Wilcoxon signed-rank test p values for differences from baseline to 12 months for the DMPA group are reported in the DMPA column in Table 2 and differences from baseline to 12 months for the TCu 380A IUD group are reported in the TCu 380A IUD column in Table 2. Wilcoxon signed-rank test p values for differences between the DMPA group and TCu 380 IUD are reported in the p value column in Table 2.
The mean value for baseline weight is 65.0 kg with a standard deviation (SD) ± 12.8, and the mean value for weight at 12 months is 66.9 kg with an SD ± 13.7 for the DMPA group. The mean change in weight gain was 1.9 kg with an SD ± 3.5 for the DMPA group.
For the DMPA group, the Wilcoxon signed-rank test resulted in p = 0.02 for the change in weight gain from baseline to 12 months, meaning weight (kg) was significantly greater 12 months after initiating DMPA use when compared with baseline weight. The value for statistical significance for this study was set at α = 0.05. Thus, the results for the change in weight gain for the DMPA sample is statistically significant because p = 0.02 is less than α = 0.05 (Grove & Gray, 2019).
For the TCu 380A IUD group, the Wilcoxon signed-rank test resulted in p = 0.15 for the change in weight gain, meaning weight (kg) was not significantly changed 12 months after initiating the TCu 380A IUD when compared with baseline weight. The value of p = 0.15 is not statistically significant because this p value is greater than α = 0.05 set for this study (Pett, 2016).
Null hypothesis: There is no variation in fat mass from baseline to 12 months for the DMPA group. The Wilcoxon signed-rank test resulted in p = 0.03 for variation in fat mass from baseline to 12 months for the DMPA group, which is significant because it is less than α = 0.05. When the results are significant, the null hypothesis is rejected (Grove & Gray, 2019).
Null hypothesis: There is no variation in central-to-peripheral fat ratio from baseline to 12 months for the DMPA group. The Wilcoxon signed-rank test resulted in p = 0.96 for variation in central-to-peripheral fat ratio from baseline to 12 months for the DMPA group. Because this p value is greater than α = 0.05, the result was nonsignificant and the null hypothesis was accepted (Pett, 2016).
The Wilcoxon signed-rank test result for variation in fat mass (kg) for DMPA and TCu 380A IUD group in Table 2 is p = 0.14. This p value is greater than α = 0.05 set for this study so this result is not statistically significant.

Answers may vary. Clinical implications may include patient education on the potential risk of weight gain for DMPA users or the potential benefit of exercise in maintaining weight for TCu 380A users. The Centers for Disease Control and Prevention (CDC) has contraception information for consumers and healthcare providers at http://www.cdc.gov/reproductivehealth/UnintendedPregnancy/Contraception.html and obesity, weight, and healthy lifestyle information at http://www.cdc.gov/obesity/index.html. The National Institutes of Health (NIH) has a healthy weight resource that contains family and provider information including BMI calculator at http://www.nhlbi.nih.gov/health/education/lose_wt/index.htm.

The Moore et al. (2018) study result of p = 0.012 for perceptions of teamwork indicated that the clinical simulation intervention was significantly effective in promoting the nursing staff’s perceptions of teamwork. The result was significant because p = 0.012 is less than alpha set a 0.05 for this study.

BS-EBM Unit 21: Assessment Questions 1 to 10



The Mann-Whitney U test is a nonparametric statistical technique used to detect differences between two independent samples (Kim & Mallory, 2017; Knapp, 2017; Plichta & Kelvin, 2013). You might use a variety of statistical sources for documenting your answer.
b. Interval/ratio-level data with a non-normal distribution of scores on a study variable is correct. The Mann-Whitney U test is appropriate for analyzing interval/ratio-level data when the requirements for conducting a parametric test cannot be satisfied, i.e., when the collected data have a non-normal or skewed distribution. The Mann-Whitney U test is designed to determine differences between groups and not test for relationships between variables. The Mann- Whitney U test is to be used with independent and not dependent or paired groups and is for at least ordinal-level data and not nominal-level data (Pett, 2016).
The t-test for independent groups is the most appropriate analysis technique. The CES-D Scale is a Likert scale, and the data from these scales are considered interval level (see Unit 1; Gray et al., 2017; Kim & Mallory, 2017). Since the data were normally distributed and at the interval level of measurement, parametric analyses can be conducted on the data. The two groups are independent because the study participants were randomly assigned to the intervention and comparison groups (Kazdin, 2017). The focus of the analysis is difference between two groups, so the most appropriate analysis technique is the t-test for independent groups (see the algorithm in Unit 12).
The null hypothesis: There are no differences between the moderate and severe airflow limitation groups for reported psychological symptoms.
The null hypothesis was accepted because no significant differences were found between the moderate and severe airflow limitation groups for psychological symptoms. Eckerblad et al. (2014) indicated in their study that the significance level was set at p ≤ 0.05. Review the p values in Table 3 for the psychological symptoms. All the p values are >0.05, indicating no statistically significant differences between the groups for psychological symptoms.
Sample size N = 91 for the study. The sample size might have been too small to detect small differences between the moderate and severe airflow limitation groups for the physical and psychological symptoms. The Eckerblad et al. (2014) study did not include power analysis results to identify the appropriate sample size. Descriptive studies require larger samples when several variables are being examined as in this study. Thus, the study would have been stronger if power analysis results were included and the study was conducted with a larger sample (Aberson, 2019; Cohen, 1988).
The lack of energy for the total sample had mean = 1.3 and SD ± 1.3. Answer is in the narrative results for the study. Lack of energy was one of six symptoms that had high MSAS symptom burden score. However, shortness of breath, dry mouth, cough, and sleep problems had higher MSAS symptom burden scores than lack of energy.
There was no significant difference between the moderate and severe airflow limitation groups for lack of energy as indicated by p = 0.10 (see Table 3). This result is not statistically significant since it is greater than the level of significance for this study that was set at p ≤ 0.05.
Difficulty sleeping was the psychological symptom that had the highest burden scores as indicated by mean = 1.26 for the moderate airflow limitation group and a mean = 1.44 for the severe airflow limitation group. Difficulty sleeping had the highest means in both groups, and the higher the mean the greater the burden scores for the participants in these groups (Grove & Gray, 2019).

The clinical importance is that patients with COPD who have either moderate or severe airflow limitations have identified difficulty sleeping as their number one psychological symptom. Management of these patients requires assessment, diagnosis, and management of sleeping disorders. The Global Initiative for Chronic Obstructive Lung Disease website is an excellent resource for evidence-based guidelines at http://www.goldcopd.org/Guidelines/guidelinesresources.html. Cochrane Library in England has a large collection of systematic reviews and evidence-based guidelines and includes several resources on COPD (see http://www.cochrane.org and search for COPD). You might document with other websites, research articles, or textbooks that focus on generation of research evidence for practice (Melnyk & Fineout-Overholt, 2019).

BS-EBM Unit 19: Assessment Questions 1 to 10



The sample size is N = 201 with n = 111 (55%) RAAPS users and n = 90 (45%) RAAPS nonusers as indicated in the narrative results. Answers might vary because the sample size is limited for an online survey with only 35% of the providers responding. However, many of the chi-square values were significant, indicating a decreased potential for a Type II error. In addition, the group sizes were fairly equal, which is a study strength (Gray et al., 2017).

The null hypothesis is: There is no difference in provider type for the users and nonusers of the RAAPS screening tool. The χ2 = 12.7652 and df = 2 for provider type as presented in Table 2.

The p = < .00 for the provider type. Yes, the χ2 = 12.7652 for provider type is statistically significant as indicated by the p value presented in Table 2. The specific χ2 value obtained could be compared against the critical value in a χ2 table to determine the significance for the specific degrees of freedom (df), but readers of research reports usually rely on the p value provided by the researcher(s) to determine significance. Many nurse researchers set the level of significance or alpha (α) = 0.05 (Grove & Gray, 2019). Since the p value is less than alpha, the result is statistically significant. The null hypothesis is rejected when study results are statistically significant (Gray et al., 2017; Pett, 2016). You need to note that p values never equal zero as they appear in this study. The p values would not be zero if carried out more decimal places.

No, a statistically significant χ2 value does not provide evidence of causation. A statistically significant χ2 value indicates a significant difference between groups exists but does not provide a causal link (Grove & Gray, 2019; Shadish, Cook, & Campbell, 2002).
The χ2 = 1.2865 for race. Since p = .53 for race, the χ2 value is not statistically significant. The level of significance is set at α = 0.05 and the p value is larger than alpha, so the result is nonsignificant (Grove & Gray, 2019; Pett, 2016).

Yes, there is a statistically significant difference between RAAPS users and RAAPS nonusers with regard to percentage of adolescent patients. The chi-square value = 7.3780 with a p = .01, which is less than alpha = 0.05. You might expect that nurses caring for more adolescents might have higher RAAPS use as indicated in Table 2. However, nurses need to be knowledgeable of assessment and care needs of populations and subpopulations in their practice even if not frequently encountered. Two valuable sources for adolescent care include the Centers for Disease Control and Prevention (CDC) Adolescent and School Health at http://www.cdc.gov/HealthyYouth/ and the World Health Organization (WHO) adolescent health at http://www.who.int/topics/adolescent_health/en/.

The df = 3 for U.S. practice region is provided in Table 2. The df formula, df = (R − 1) (C − 1) is used (Kim & Mallory, 2017; Pett, 2016). There are four “R” rows, Northeastern United States, Southern United States, Midwestern United States, and Western United States. There are two “C” columns, RAAPS users and RAAPS nonusers. df = (4 − 1)(2 − 1) = (3)(1) = 3.

The null hypothesis: There is no difference between RAAPS users and RAAPS nonusers for providers with ≤5 years of practice and those with >5 years of practice.

The null hypothesis for years in practice stated in Questions 8 should be rejected. The χ2 = 6.2597 for years in practice is statistically significant, p = .01. A statistically significant χ2 indicates a significant difference exists between the users and nonusers of RAAPS for years in practice; therefore the null hypothesis should be rejected (Kim & Mallory, 2017).

The Bhatta et al. (2018) results were statistically significant with female adolescents reporting significantly more sleep problems (χ2 = 9.147, p = 0.002) and tiredness (χ2 = 6.165, p = 0.013) than male adolescents. The results are statistically significant because the p values are less than alpha set at 0.05. The results are clinically important because the sleep and tiredness outcomes vary based on gender and additional screening and interventions are needed to manage these health problems in females.