Statistical Technique in Review

Most research reports describe the subjects or participants who comprise the study sample. This description of the sample is called the sample characteristics, which may be presented in a table and/or the narrative of the article. The sample characteristics are often presented for each of the groups in a study (i.e., intervention and control groups). Descriptive statistics are calculated to generate sample characteristics, and the type of statistic conducted depends on the level of measurement of the demographic variables included in a study (Grove, Burns, & Gray, 2013). For example, data collected on gender is nominal level and can be described using frequencies, percentages, and mode. Measuring educational level usually produces ordinal data that can be described using frequencies, percentages, mode, median, and range. Obtaining each subject's specific age is an example of ratio data that can be described using mean, range, and standard deviation. Interval and ratio data are analyzed with the same statistical techniques and are sometimes referred to as interval/ratio-level data in this text.

Research Article

Source

Oh, E. G., Yoo, J. Y., Lee, J. E., Hyun, S. S., Ko, I. S., & Chu, S. H. (2014). Effects of a three-month therapeutic lifestyle modification program to improve bone health in postmenopausal Korean women in a rural community: A randomized controlled trial. Research in Nursing & Health, 37(4), 292-301.

Introduction

Oh and colleagues (2014) conducted a randomized controlled trial (RCT) to examine the effects of a therapeutic lifestyle modification (TLM) intervention on the knowledge, self-efficacy, and behaviors related to bone health in postmenopausal women in a rural community. The study was conducted using a pretest-posttest control group design with a sample of 41 women randomly assigned to either the intervention (n = 21) or control group (n = 20). "The intervention group completed a 12-week, 24-session TLM program of individualized health monitoring, group health education, exercise, and calcium-vitamin D supplementation. Compared with the control group, the intervention group showed significant increases in knowledge and self-efficacy and improvement in diet and exercise after 12 weeks, providing evidence that a comprehensive TLM program can be effective in improving health behaviors to maintain bone health in women at high risk of osteoporosis" (Oh et al., 2014, p. 292).

Relevant Study Results

 "Bone mineral density (BMD; g/cm2) was measured by dual energy x-ray absorptiometry (DXA) with the use of a DEXXUM T machine . . . . A daily calibration inspection was performed. The error rate for these scans is less than 1%. Based on the BMD data, the participants were classified into three groups: osteoporosis (a BMD T-score less than -2.5); osteopenia (a BMD T-score between -2.5 and -1.0); and normal bone density (a BMD T-score higher than -1.0)" (Oh et al. 2014, p. 295).

"Characteristics of Participants

The study participants were 51-83 years old, and the mean age was 66.2 years (SD = 8.2). The mean BMI was 23.8 kg/m2 (SD = 3.2). Most participants did not consume alcoholic drinks, and all were nonsmokers. Antihypertensives and analgesics such as aspirin and acetaminophen were the most common medications taken by the participants. Less than 20% of participants had a regular routine of exercise at least three times per week. Daily calcium- and vitamin D-rich food intake (e.g., dairy products, fish oil, meat, and eggs) was low. Seventy-five percent (n = 31) of the participants had osteoporosis or osteopenia. There were no differences in the baseline characteristics of the groups (Table 2). The adherence rate to the TLM program was 99.6%" (Oh et al., 2014, p. 296).

TABLE 2

BASELINE CHARACTERISTICS AND HOMOGENEITY OF THE TREATMENT AND CONTROL GROUPS

Intervention (n = 21)Control (n = 20)CharacteristicMean ± SD Mean ± SD t or χ2 a

Anthropometric Age (years)65.95 ± 8.5966.35 ± 7.940.154 Height (cm)152.33 ± 6.53150.57 ± 6.010.896 Weight (kg)57.90 ± 10.8554.66 ± 9.481.016 BMI (kg/m2)24.17 ± 3.1423.38 ± 3.320.782Lifestyle Years since menopause20.21 ± 10.4417.5 ± 11.050.767 Calcium-rich food intake (times/week)27.3 ± 11.423.8 ± 8.81.110 Vitamin D-rich food intake (times/week)2.4 ± 2.53.1 ± 3.10.705Intervention (n = 21) Control (n = 20) Characteristic n  %  n  % t or χ2  a   History of fracture8385251.026 Regular exercise (≥3 times/week)4194200.006 Non-drinker (alcohol)2095201000.024 Non-smoker21100201000.024Bone statusb   Normal (T ≥ -1.0)6294201.995 Osteopenia (-1.0 > T > -2.5)8381260 Osteoporosis (T ≤ -2.5)733420Intervention (n = 21) Control (n = 20) Characteristic Mean ± SD  Mean ± SD  t or χ2  a   BMD Lumbar 2-40.83 ± 0.120.85 ± 0.200.526 Femur neck0.67 ± 0.150.67 ± 0.130.055Bone biomarkers Serum osteocalcin (ng/ml)13.97 ± 4.9015.85 ± 5.641.135 Serum calcium (mg/dl)9.47 ± 0.409.54 ± 0.590.405 Serum phosphorus (mg/dl)3.68 ± 0.443.70 ± 0.500.165 Serum alkaline phosphatase (IU/L)68.43 ± 21.5266.70 ± 13.240.308 Serum 25-OH-Vitamin D (ng/ml)14.03 ± 4.3412.38 ± 4.651.177 Urine deoxypyridinoline (nM/mM creatinine)5.70 ± 1.705.95 ± 1.120.555

a. All group differences p > 0.05.

b. Defined from T-score of femur neck site based on World Health Organization criteria.

 Note. SD, standard deviation; BMD, bone mineral density (g/cm2).

Oh, E. G., Yoo, J. Y., Lee, J. E., Hyun, S. S., Ko, I. S., & Chu, S. H. (2014). Effects of a three-month therapeutic lifestyle modification program to improve bone health in postmenopausal Korean women in a rural community: A randomized controlled trial. Research in Nursing & Health, 37(4), p. 297.

Study Questions:

1. What demographic variables were described in this study?

2. Which variable was measured at the ordinal level? Provide a rationale for your answer.

3. What level of measurement is the data for history of fracture? Provide a rationale for your answer.

4. What statistics were calculated to describe history of fracture? Were these appropriate? Provide a rationale for your answer.

5. Could a mean be calculated on the history of fracture data? Provide a rationale for your answer.

6. What statistics were calculated to describe the regular exercise (≥3 times per week) for the intervention and control groups? Calculate the frequency and percentage of the total sample who exercised regularly. Round your answer to the nearest tenth of a percent.

7. What statistics were calculated to describe age in this study? Were these appropriate? Provide a rationale for your answer.

8. Were the intervention and control groups significantly different for age? Provide a rationale for your answer.

9. What was the mode for bone status for the total sample (N = 41)? Determine the frequency and percentage for the bone status mode for the sample. Round your answer to the nearest whole percent. Why is this clinically important?

10. Based on the bone status of the study participants, discuss the clinical importance of this study. Document your response.

EXERCISE 10 Questions-

1. What demographic variables were measured at the nominal level of measurement in the Oh et al. (2014) study? Provide a rationale for your answer.

2. What statistics were calculated to describe body mass index (BMI) in this study? Were these appropriate? Provide a rationale for your answer.

3. Were the distributions of scores for BMI similar for the intervention and control groups? Provide a rationale for your answer.

4. Was there a significant difference in BMI between the intervention and control groups? Provide a rationale for your answer.

5. Based on the sample size of N = 41, what frequency and percentage of the sample smoked? What frequency and percentage of the sample were non-drinkers (alcohol)? Show your calculations and round to the nearest whole percent.

6. What measurement method was used to measure the bone mineral density (BMD) for the study participants? Discuss the quality of this measurement method and document your response.

7. What statistic was calculated to determine differences between the intervention and control groups for the lumbar and femur neck BMDs? Were the groups significantly different for BMDs?

8. The researchers stated that there were no significant differences in the baseline characteristics of the intervention and control groups (see Table 2). Are these groups heterogeneous or homogeneous at the beginning of the study? Why is this important in testing the effectiveness of the therapeutic lifestyle modification (TLM) program?

9. Oh et al. (2014, p. 296) stated that "the adherence rate to the TLM program was 99.6%." Discuss the importance of intervention adherence, and document your response.

10. Was the sample for this study adequately described? Provide a rationale for your answer.