ST3001 Assessment

Date: January, 25 2026

Describing and Graphing Data

Part 1 — Identifying Variables in a Published Study

Selected article:

Perming, C., Thurn, A., Garmy, P., & Einberg, E.-L. (2022). Adolescents’ experience of stress: A focus group interview study with 16-19-year-old students during the COVID-19 pandemic. International Journal of Environmental Research and Public Health, 19(15). https://doi.org/10.3390/ijerph19159114

1. In your own words, briefly describe the study and what it covered as if explaining it to someone who has not read the abstract information.

The aim of the study was to investigate stress as experienced by adolescents during the COVID-19 period. The study targeted adolescents age between 16 and 19 in southern Sweden. Data was collected using focus group interviews that targeted students in upper secondary schools. A total of 41 students, including nine male and 32 female students, took part in the study. The study was conducted when schools had resumed on-site education after a period of online classes during the pandemic. The interviews were recorded, transcribed, and analyzed using qualitative content analysis. The analysis determined that there were five categories associated with the stress experience. These included stress in leisure and relationships, school-related stress, manifestation of stress, experiences of counteracting stress, and the positive impact of stress on performance. Distance education contributed to high stress levels. High stress levels among adolescents led to impaired performance, while moderate stress led to improved performance and achievement of educational goals.

2. What sample was used in the study? Explain your answer and provide supporting evidence from the textbook or other resources.

A study sample refers to a group of people selected from a larger population group who take part in a research study (Ahmed, 2024). The sample used in the study comprised of upper secondary school students aged between 16 and 19 from southern Sweden. The participants were accessed through purposive sampling which according to Ahmed (2024), involves selecting participants that meet specific characteristics. The researchers informed school administrations in 3 municipalities about the study. Two schools located in two municipalities agreed to take part in the study. The students and their guardians were provided with written information about the study, and the students who consented took part in the study.

3. What population does this sample best represent? Explain your answer and provide supporting evidence from the textbook or other resources.

Sample populations are representatives of larger population groups with similar characteristics (Ahmed, 2024). The population best represented by the sample is female teenagers aged between 16 and 19 years in upper secondary schools located in southern Sweden. The reason behind this is that most of the participants were female (78%), and the sample was selected from two schools located in two municipalities in southern Sweden. Therefore, conclusions made from the study are generalizable to this population.

4. Identify at least one variable examined in this study. Classify this variable as quantitative or qualitative. Explain your answer and provide supporting evidence from the textbook or other resources.

One of the variables examined in the study is stress, a qualitative variable. According to Bazen et al. (2021), qualitative variables focus on specific characteristics, attributes, or descriptions, while quantitative variables focus on measurements. In the study, stress was a qualitative variable because it focused on the characteristics of stress as described by the participants. The interview guide included questions that focused on describing stress, causes of stress, and its impacts.

5. Explain the level of measure for the variable identified in Section 4. Explain your answer and provide supporting evidence from the textbook or other resources.

The level of measure for stress experiences is nominal variable. According to Shukla (2023), in qualitative studies, nominal variables generally classify data into non-ordered categories without any quantitative value or hierarchy. In the study, the stress variable is identified using thematic categories, not ordered levels or numeric scores. Therefore, it can be defined as a nominal-level variable.

6. Determine if the study is overall a quantitative or qualitative study. Justify your reasoning using at least two key aspects for the type of study you chose. Explain your answer and provide supporting evidence from the textbook or other resources.

The study is a qualitative study. Qualitative studies generally examine the how and the why, and focus on developing an in-depth understanding of specific experiences occurring within natural settings. Qualitative studies also use non-numerical data obtained from observations, interviews, and focus groups (Bazen et al., 2021). The study is a qualitative study because it focused on the adolescents’ experiences with stress during the COVID-19 pandemic. The study also used focus groups as the main data collection method.

Part 2 — Data Analysis

Creating Graphical Displays of Data

Figure 1:

Graph Showing the Number of Smoker Vs Nonsmokers Including Data Labels

Interpretation: In the dataset, the number of smokers is equal to the number of non-smokers.

Figure 2:

Histogram of BMI Values (Bin width of 2)

Interpretation: The histogram of BMI is right-skewed (positively skewed), with most individuals having BMI values between 23.9 and 25.9, and fewer individuals at higher BMI levels.

Figure 3:

Modified Box Plots for BMI: Smoker and Nonsmoker BMI

The summary for the BMI smokers is: Min=17.9, Q₁=24.5, Median = 26.6, Q₃=30.7, Max=45.9. The summary for the BMI nonsmokers is: Min=18.7, Q₁=23.9, Median = 29.4, Q₃=35.3, Max=56.8.

Interpretation: The side-by-side box plots show that the BMI distribution differs between smokers and nonsmokers, with nonsmokers having a higher mean and median BMI and greater variability when compared to smokers. Both datasets have two outliers.

Descriptive statistics

Table 1

Descriptive Statistics: BMI Smokers

BMI Smokers
Mean	28.10164
Standard Error	0.711876
Median	26.6
Mode	25.2
Standard Deviation	5.559931
Sample Variance	30.91283
Kurtosis	1.537114
Skewness	1.193689
Range	28
Minimum	17.9
Maximum	45.9
Sum	1714.2
Count	61

Table 2:

Descriptive Statistics: BMI Nonsmokers

BMI nonsmokers
Mean	30.48525
Standard Error	1.085279
Median	29.4
Mode	23.3
Standard Deviation	8.476297
Sample Variance	71.84761
Kurtosis	0.805326
Skewness	0.93435
Range	38.1
Minimum	18.7
Maximum	56.8
Sum	1859.6
Count	61

Comparing data

Use these statistics to answer the following questions comparing smokers to nonsmokers. Be sure to provide values from your Excel output to support your reasoning.

1. Which group has an BMI that is typically higher? Be sure to write at least one sentence justifying your reasoning including values from the excel output.

Nonsmokers typically have a higher BMI than smokers, with a mean BMI of 30.49 (SD = 1.09) compared to smokers’ mean of 28.10 (SD = 0.71). The median BMI values (29.4 for nonsmokers and 26.6 for smokers) also indicate that the typical nonsmoker has a higher BMI.

2. Which group has greater variation in their BMI? Be sure to write at least one sentence justifying your reasoning including values from the excel output.

Nonsmokers have greater variation in BMI than smokers, as indicated by a higher standard deviation (SD = 1.09), when compared to smokers’ (SD = 0.71) and a wider range of BMI values (18.7–56.8 for nonsmokers compared to 17.9–45.9 for smokers). This data that nonsmokers’ BMI values are more spread out around the mean than smokers’ values.

3. Do you suspect any outliers are present in the BMI for each group? Be sure to justify your reasoning.

There appears to be outliers in the BMI values for both the smokers and non-smokers.

For smokers:

1^st Quartile = 24.5, 3^rd Quartile = 30.7, interquartile range (IQR) = 6.2

Upper threshold = 30.7+(1.5*6.2) = 40

For smokers, there are two values which are greater than 40 which are outliers.

For non-smokers:

1^st Quartile = 23.85, 3^rd Quartile = 35.3, interquartile range (IQR) = 11.45

Upper threshold = 35.3+(1.5*11.45) = 52.475

For non-smokers, there are two values greater than 52.475 in the data. These are outliers.

More evidence:

Each of the modified boxplots for smokers and non-smokers BMI have two points above their boxes. This indicates that two people in each group have unusually high BMI values compared to the rest of the group.

References

Ahmed, S. K. (2024). How to choose a sampling technique and determine sample size for research: A simplified guide for researchers. Oral Oncology Reports, 12(1), 100662. https://doi.org/10.1016/j.oor.2024.100662

Bazen, A., Barg, F. K., & Takeshita, J. (2021). Research techniques made simple: an introduction to qualitative research. Journal of Investigative Dermatology, 141(2), 241-247. https://doi.org/10.1016/j.jid.2020.11.029

Shukla, D. (2023). A narrative review on types of data and scales of measurement: An initial step in the statistical analysis of medical data. Cancer Research Statistics and Treatment, 6(2), 279–283. https://doi.org/10.4103/crst.crst_1_23