Scribd
Upload
7 views2 pages

Variance, Standard Deviation, and Error

The document explains the differences between variance and standard deviation, highlighting that variance measures the squared deviation from the mean while standard deviation provides a more interpretable value. It also contrasts measurement error, which is the difference between true and observed values, with standard error, which indicates how much a sample mean may vary from the population mean. Examples are provided to illustrate these concepts using exam scores and apple weights.

Uploaded by

m4sh4o22
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
7 views2 pages

Variance, Standard Deviation, and Error

The document explains the differences between variance and standard deviation, highlighting that variance measures the squared deviation from the mean while standard deviation provides a more interpretable value. It also contrasts measurement error, which is the difference between true and observed values, with standard error, which indicates how much a sample mean may vary from the population mean. Examples are provided to illustrate these concepts using exam scores and apple weights.

Uploaded by

m4sh4o22
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Applied Statistics BS PSY 2k22 - Mashal Guluna (404429)

Assignment 01

Variance vs. Standard Deviation


Variance is the expected squared variation value of the scores from the mean value. It
measures how different (more or less than) an individual score is from the accumulated mean
score, but in squared terms. The squared value is useful in mathematical calculations but is
difficult to interpret. To tackle this shortcoming, statisticians have introduced another way of
calculating the spread of an individual score, “standard deviation.” It is identical to
variance, except that the values are enclosed within a square root. This gives a true value of
the deviation of the individual scores from the mean.​
​
Example: Dataset of exam scores (out of 100) for 5 students:​
Scores = [70, 80, 90, 60, 85]

Step 1: Mean = (70 + 80 + 90 + 60 + 85) / 5 = 385 / 5 = 77

Step 2: Variance
It is the average of the squared differences from the mean.
➔​ Squared differences:
◆​ (70 - 77)² = (-7)² = 49
◆​ (80 - 77)² = (3)² = 9
◆​ (90 - 77)² = (13)² = 169
◆​ (60 - 77)² = (-17)² = 289
◆​ (85 - 77)² = (8)² = 64
➔​ Sum = 49 + 9 + 169 + 289 + 64 = 580
➔​ Variance = Sum of squared differences / number of data points = 580 /
5 = 116

Step 3: Standard Deviation


It is the square root of the variance. √116 ≈ 10.77

While variance holds mathematical and statistical significance, i.e.; Regression Analysis,
Hypothesis Testing and Defining Probability Distributions, standard deviation serves a
purpose of ease in interpretation/communication of the scores as they have the same units as
the data.
Measurement vs. Standard Error
Measurement error is the difference between the true value (actual value) and the observed
value (the value that we measure using measuring instruments). The error results from the
faulty or inaccurate measurement process (could be human error, instrumental or
environmental error). In contrast, a standard error is how different the population mean is
likely to be from a sample mean. It tells us how much a sample mean would vary were we to
repeat the study using another sample from the same population. Standard error helps us
understand and predict how well our sample represents the whole population.

Example: Weighing Apples

Step 1: Measurement Error


We have 5 apples, each with a true weight of 100 grams. However, our kitchen scale
is slightly faulty, so the measured weights would be: Apple 1 (102 g), Apple 2 (98
g), Apple 3 (101 g), Apple 4 (99 g), Apple 5 (100 g)

Difference:
●​ Apple 1: 102 - 100 = +2 grams
●​ Apple 2: 98 - 100 = -2 grams
●​ Apple 3: 101 - 100 = +1 gram
●​ Apple 4: 99 - 100 = -1 gram
●​ Apple 5: 100 - 100 = 0 grams

These errors arise because the scale is not perfectly accurate.

Step 2: Standard Error


➔​ Standard Deviation = √2 ≈ 1.41 grams
➔​ Standard Error = S.D / √n (Where n is the sample size; 5).​
Standard Error = 1.41 / √5 ≈ 0.63 grams

We obtain different sample mean calculations for 5 apple samples when repeatedly measured
because each calculation will cluster around the actual mean weight of 100 grams with a
standard deviation at 0.63 grams.

You might also like