Introduction
The use of descriptive statistics aims to investigate trends and patterns prevalent in the distribution of a variable. The tools of such statistics include measures of central tendency, measures of variability, frequency distributions, and the construction of appropriate diagrams. In this way, using only descriptive statistics, a researcher can identify patterns in the distribution of a variable, draw initial conclusions, and prepare material for more in-depth analysis in the future.
In the present work, data were collected on the consumption of different fruits during the month, so that the final array represented the number of each fruit type consumed. A total of 10 different types of fruit were consumed, including Apple, Banana, Orange, Guava, Pineapple, Grapes, Cherry, Blueberry, Kumquat, and Pear. The present work aims to conduct a descriptive analysis of the collected data.
Data Visualization
First, it was necessary to construct a visual representation of the collected data to evaluate existing trends. The choice of a bar chart was justified because the consumption frequencies were collected for a categorical variable (fruit type). As shown in Figure 1, the most fruits eaten were bananas (n = 10), blueberries (n = 8), and grapes and pears (both n = 6). In contrast, the lowest consumption frequency was for guava and kumquat (both n = 1). These data allow us to make initial assumptions about the distribution of the variable: bananas were the most popular fruit.
Measuring Central Tendency and Variability
The second level of descriptive statistics involves calculating measures of central tendency and measures of variability. Strictly speaking, measures of central tendency describe the central positions of a distribution, including the mean, median, and mode (Khorana et al., 2023). In contrast, measures of variability indicate how scattered and distributed a variable is, and specific instruments include variance, standard deviation, and range.
Obviously, for a categorical variable like fruit, such metrics are not practical, so the results cannot be used to construct a frequency distribution. As shown in Table 1, the mean number of fruits for the sample (N = 43) was 4.3 (SD = 3.09). This indicates that, on average, 4.3 units of each of the ten fruit types were eaten. On the other hand, the standard deviation score indicates that, on average, the frequency of each of the ten fruit types differed by 4.3 to 3.09 units.
Table 1. Results of descriptive statistics
Additionally, Table 1 shows that the median fruit consumed is 3.5, indicating that 50% of the frequency distribution lies above and below this value. The most frequent mode of distribution was equal to 1, as observed for kumquat and guava. In terms of measures of variability, the range was 9, which indicates the distance between the maximum and minimum levels of fruit consumption. Thus, the distribution is quite scattered, and homogeneity is not noticed.
Conclusion
In conclusion, descriptive statistics are used to summarize primary results and examine trends and patterns in the data. Within the scope of this paper, demonstration data were used to show the frequency of consumption of 10 different fruits over a month. As the results showed, the frequency distribution was quite scattered, with banana being the most frequently consumed fruit, followed by kumquat and guava. On average, each fruit type accounted for 4.3 units. These data can be used in further analysis to gain deeper insights, explore potential relationships, and identify differences between groups.
Reference
Khorana, A., Pareek, A., Ollivier, M., Madjarova, S. J., Kunze, K. N., Nwachukwu, B. U., & Williams III, R. J. (2023). Choosing the appropriate measure of central tendency: Mean, median, or mode?Knee Surgery, Sports Traumatology, Arthroscopy, 31(1), 12-15.