Ms Exercise
Answer No1
Skewness measures distribution symmetry, with a value of 0 indicating perfect symmetry or
normal distrbution.
Negative skewness (less than 0) implies a left-skewed distribution, with more values on
the lower end.
Positive skewness (greater than 0) implies a right-skewed distribution, with more values
on the higher end.
In our data
totalstatsscore: Skewness is approximately -0.628.
totalrmscores: Skewness is approximately -0.371.
Ranges
Highly skewed: Skewness less than -1 or greater than 1.
Moderately skewed: Skewness between -1 and -0.5, or between 0.5 and 1.
Approximately symmetrical: Skewness between -0.5 and 0.5.
Interpretation
For totalstatsscore: Skewness is approximately -0.628, indicating a moderately skewed
distribution with more values on the lower end, although not highly skewed.
For totalrmscores: Skewness is approximately -0.371, suggesting an approximately
symmetrical distribution with a skewness value near zero, indicating a balanced
distribution of values around the mean.
Kurtosis measures distribution's peakedness compared to normal distribution, with 0 or 3
indicating normal (mesokurtic).
Negative kurtosis (less than 0 or 3) indicates a flatter distribution (platykurtic) with fewer
extreme values.
Positive kurtosis (greater than 0 or 3) indicates a sharper peak (leptokurtic) with more
extreme values.
Ranges
Normal Kurtosis: The range of kurtosis values for normal distributions is close to 0.
Moderate Kurtosis: Moderate kurtosis values fall between -1 and -2, or between 1 and 2.
High Kurtosis: High kurtosis values are below -2 or above 2.
In our data
totalstatsscore: Kurtosis is approximately -0.023(close to zero/ mesokutic)
totalrmscores: Kurtosis is approximately -0.710 (moderate kurtosis/Platykurtic
Interpretation
Both distributions exhibit negative kurtosis values, indicating that they are flatter than a
normal distribution. However, since the kurtosis values are within the range of normal kurtosis,
the distributions are considered relatively close to normal in terms of shape, with only slight
departures from the ideal normal distribution.
Answer no 2
Skewness
For totalstatsscore Skewness is approximately -0.628.
For totalrmscores Skewness is approximately -0.371
Both skewness values fall within the range of approximately -1 to 1, indicating that the
distributions are moderately skewed. While they are not perfectly symmetrical, the skewness
values are not highly bothersome as they do not exceed the thresholds for high skewness.
Kurtosis
For totalstatsscore Kurtosis is approximately -0.023.
For totalrmscoresKurtosis is approximately -0.710.
Both kurtosis values are close to 0, indicating a slight departure from normality. However,
they are within the range of normal kurtosis. Therefore, they are not highly bothersome,
suggesting that the distributions are relatively close to normal in terms of shape.
Answer 4
Based on the tests of normality:
For totalrmscores:
Kolmogorov-Smirnov test statistic: 0.082
Shapiro-Wilk test statistic: 0.955
For totalstatsscore:
Kolmogorov-Smirnov test statistic: 0.113
Shapiro-Wilk test statistic: 0.948
In both cases, the p-values for the Shapiro-Wilk tests are greater than 0.05, indicating that we
fail to reject the null hypothesis of normality. However, the p-values for the Kolmogorov-
Smirnov tests are also greater than 0.05, suggesting that the distributions do not significantly
depart from normality.
Therefore, based on these normality tests, there is no evidence to suggest that the
distributions of totalrmscores and totalstatsscore significantly deviate from normality. This
supports the interpretation that the skewness and kurtosis values for both variables are not highly
bothersome.
1. Shapiro-Wilk Test:
This test evaluates whether a dataset comes from a normally distributed
population.
The null hypothesis (H0) of the Shapiro-Wilk test is that the data are normally
distributed.
If the p-value from the Shapiro-Wilk test is greater than 0.05 (commonly chosen
significance level), we fail to reject the null hypothesis.
In our data, both totalrmscores and totalstatsscore have p-values greater than 0.05
for the Shapiro-Wilk test, indicating that there is not enough evidence to reject the
null hypothesis. Therefore, we conclude that the data are likely normally
distributed.
2. Kolmogorov-Smirnov Test:
This test assesses whether a sample comes from a population with a specified
distribution (in this case, the normal distribution).
The null hypothesis (H0) of the Kolmogorov-Smirnov test is that the sample
distribution is the same as the specified distribution (normal distribution).
If the p-value from the Kolmogorov-Smirnov test is greater than 0.05, we fail to
reject the null hypothesis.
In our data, both totalrmscores and totalstatsscore have p-values greater than 0.05
for the Kolmogorov-Smirnov test, suggesting that there is not enough evidence to
reject the null hypothesis. Therefore, we conclude that the distributions of the data
do not significantly depart from normality.
In summary, both the Shapiro-Wilk and Kolmogorov-Smirnov tests indicate that the data are
not significantly different from a normal distribution, as the p-values are greater than 0.05.
Therefore, we can reasonably assume that the data are approximately normally distributed.
Answer 5
Skewness and Kurtosis Analysis:
Both totalstatsscore and totalrmscores
exhibit moderate skewness, falling within the range of approximately
-1 to 1. This indicates moderately skewed distributions, with
totalstatsscore
being slightly more left-skewed (-0.628) than totalrmscores (-0.371).
In terms of kurtosis, both distributions
have negative values, indicating slight departures from the normal
distribution.
However, these values are close to 0, suggesting relatively normal
distributions,
with totalstatsscore being mesokurtic (-0.023) and totalrmscores showing
moderate platykurtic behavior (-0.710).
Normality
Tests:
The Shapiro-Wilk test and the
Kolmogorov-Smirnov test were conducted to assess normality.
For both totalstatsscore and totalrmscores,
the p-values from both tests are greater than 0.05.
This indicates that there is no
significant evidence to reject the null hypothesis of normality for
either distribution.
QQ
Plots and Histogram Interpretation:
QQ plots were utilized to visually
compare the distributions of totalstatsscore and totalrmscores to a
normal distribution. If the points on the plot closely follow the diagonal
line, it suggests similarity to a normal distribution.
Histograms were examined to assess
the shape of the distributions. A symmetric, bell-shaped curve in the
histograms is indicative of normality. However, given the moderate
skewness
and kurtosis values observed in the data, deviations from this shape
indicate the presence of moderate skewness and kurtosis in the
distributions,
which may result in departures from perfect normality.
Based on the analyses, both distributions
appear reasonably close to normal. This suggests that statistical analyses
relying on the normality assumption are likely valid for these datasets.
To ensure that the variance of achievement scores in statistics is homogeneous across the two
samples of male and female students, we can perform Levene's test for equality of variances.
This test evaluates whether the variance of the dependent variable (achievement scores) is equal
across different groups (male and female students).
Formulate Hypotheses:
Null Hypothesis (H0): The variances of achievement scores in statistics are equal
across male and female students.
Alternative Hypothesis (H1): The variances of achievement scores in statistics are
not equal across male and female students.
Based on the results of Levene's test for homogeneity of variances, the p-values for the
totalstatsscore variable are all greater than 0.05 (p > 0.05). This indicates that we fail to reject the
null hypothesis of homogeneity of variances across male and female students. Therefore, we can
assume that the variance of achievement scores in statistics is homogenous across the two
samples of male and female students.