BURGOS, Maryden Ley V.

BS ACCOUNTANCY 3-1 | STAT 101A – Statistical Analysis with Software Application

Descriptive Statistics

SCORES

Valid 24
Missing 0
Mode 38.000 ᵃ
Median 40.000
Mean 39.833
Standard Deviation 3.199
Coefficient of Variation 0.080
Variance 10.232
Minimum 34.000
Maximum 46.000
25th Percentile 38.000
50th Percentile 40.000
75th Percentile 41.250

ᵃ The mode is computed assuming that variables are discreet.

Figure 1. Measurement of central tendency for the 24 data points of gathered midterm scores from
BS Accountancy 3-1

Frequencies of Scores

SCORES Frequency Percent Valid Percent Cumulative Percent

34 1 4.167 4.167 4.167

36 2 8.333 8.333 12.500
37 2 8.333 8.333 20.833
38 6 25.000 25.000 45.833
40 5 20.833 20.833 66.667
41 2 8.333 8.333 75.000
42 1 4.167 4.167 79.167
44 3 12.500 12.500 91.667
46 2 8.333 8.333 100.000
Missing 0 0.000
Total 24 100.000

Figure 2. Frequency Distribution Table for the 24 data points of gathered midterm scores from BS
Accountancy 3-1
INTERPRETATION
Figure 1. Measurement of central tendency for the 24 data points of gathered midterm scores from
BS Accountancy 3-1
Mean being the average score of the dataset tells that most of the scores are clustered around 40.000. This
central value, compared to the median, is more sensitive to the values in the dataset, especially if there are
outliers involved. If there are outliers or the dataset could be non-normal or skewed wherein for example, one
or two of the scores are 15 while the rest are ranging from 38 to 46, the mean will be pulled downwards
causing a Negative Skew. This will also result in this relationship: Mean < Median < Mode. However, for this
dataset, it has a normal distribution. Meaning to say, no outliers are involved. Hence, the values of the mean
and median (39.833) are almost equal. Regarding the mode, this just tells which value has the highest
frequency. In the dataset, mode is valued at 38 which means that this score is the most common among the
values in the dataset.
Moving forward with the Standard Deviation, Coefficient of Variation, and Variance. Well, these values
basically tell how spread out the scores are from the mean. With Standard Deviation at 3.199, this is pretty
good if the situation is looking for more stable or predictable data. For this dataset, given that it is a set of
scores of the students, it can tell whether the performance of the students is consistent and if they collectively
aced the examination. With Mean being 40.000 and the Standard Deviation at 3.199, this means that the
scores are at least 3.199 points above or below 40. Moreover, the Coefficient of Variation as it deals with
variability or the fluctuation of the data, the 8% value indicates that the dataset are consistent and close to
the mean. Overall, with the said observations, it can be asserted that the performance of the students is
consistent with one another and majority of them achieved positive results in the examination.
The dataset of 24 student scores ranges from a minimum of 34 to a maximum of 46, representing the lowest
and highest scores, respectively. Percentiles are used to divide the dataset into 100 equal parts, helping to
understand the relative position of each score within the dataset. This is a value below which a certain
percentage of scores in the dataset falls.
The 25th percentile is valued as 38, this means that the 25% of the students scored 38 or below, while the
remaining 75% scored higher. Similarly, the 75th percentile is 41.250 which indicates that 75% of the students
scored 41.250 or lower, while the remaining 25% scored above 41.250. The 50th percentile (median) is 40,
which represents the middle point of the dataset, dividing it into two equal halves—50% of the students scored
below 40, and 50% scored above 40.

Figure 2. Frequency Distribution Table for the 24 data points of gathered midterm scores from BS
Accountancy 3-1
A Frequency Table provides illustration of how the data spread across categories and intervals. This also
reveals significant patterns and trends through indicating which values occurred most or least often. The
Percent and Valid Percent columns are concerned with how frequently the values occur as part of the whole
dataset to determine their specific significance or weight when compared to the total number of observations
or dataset. The difference between these two lies in the existence of missing data. The Percent Column
accounts for the entire dataset, including the missing data. While the Valid Percent only covers the Valid Data,
excluding the missing data (non-valid data). In this dataset, since there is no missing data, the Percent and
Valid Percent are identical.
Taking a closer look at the distribution highlights, scores between 38 and 40 evidently dominate the dataset
with a cumulative percentage of 66.667%. The most frequent score having a total of 6 students (25%) from
the dataset is 38, while the least frequent on the other hand are 34 and 42. Lastly, the Cumulative Percent
column indicates at which range is the data most concentrated and helps set thresholds or quartiles.
However, confusion may arise when finding where concentration happens in the dataset as the values
presented in the Cumulative Percent equates to the summation of previous percentages. Having the highest
Cumulative Percent does not exactly mean that this is where most of the values are concentrated. Instead,
the most frequent data is where the concentration happens. In this case, 38 having the highest individual
frequency indicates that the data are most concentrated here.