Introduction to Biostatistics

Question 1

What is biostatistics?

Answer 1

Statistical tools we apply to research-based problems

Question 2

What are three types of descriptive statistics?

Answer 2

1. Measures of central tendency
2. Measures of spread
3. Relative Position

Question 3

What are the three measures of central tendency?

How do we determine which to use?

Answer 3

1. Mean
2. Median
3. Mode
4. Geometric Mean

The mean is ideal for roughly symmetric data because it gives a pretty precise measurement of the distribution of the data.
However, the mean is highly influenced by skewed data, in which case it is better to use the median as a central value.
Geometric mean is ideal for right skewed data
The mode does not tell us much of anything unless the data is categorical

Question 4

What are the benefits of the geometric mean?

Answer 4

The geometric mean is good for right skewed data, but not left. It is more commonly employed in public health.
It has the positive properties of the x-bar mean while taming extreme values. However, it does not define values less than zero so it is not a good source for left skewed data

Question 5

How do you get the geometric mean?

Answer 5

Take the log of xi and sum them and divide by n. then you take the reverse log of that number

Question 6

What are the measures of spread?

When do we use them?

Answer 6

1. Interquartile Rage (IQR)
2. Range
3. Standard Deviation
   IQR is better for skewed data while standard deviation is better for more symmetrical data.
   The range is pretty unreliable.

Question 7

What is right skewed?

Also called positively skewed

Answer 7

most of the data values fall to the left of the mean

the TAIL IS TO THE RIGHT.

Question 8

What is left skewed distribution?

also called negatively skewed

Answer 8

Most of the data values fall to the right of the mean

the TAIL IS TO THE LEFT

Question 9

When is a distribution symmetrical?

Answer 9

When all the data values are evenly distributed on both sides of the mean.
Also if it is unimodal - the mean median and mode are all equal to one another and at the center of the distribution.

Question 10

How do we calculate a percentile?

Answer 10

1. Order the data set from smallest to largest
2. Compute the position (c) of the percentile (k).
   c= n(k)/100
3. If c is not a whole number round up to the next whole number and this location is the required percentile.
   If it is not a whole number find the number between c and c+1 in the ordered set. This number will be the percentile.

Question 11

What is an outlier?

Answer 11

It is an extremely small or large data value in comparison to the remaining values.

Question 12

How do you calculate if a value is an outlier?

Answer 12

Q1 - 1.5(IQR)
and
Q3 + 1.5(IQR)

To identify an extreme outlier