14. Descriptive Statistics and Distributions

Question 1

A scientist is trying to find the the most reliable way to measure central tendency for biomarker measurements which measurement should he use?

A. Median
B. Mode
C. Mean

RFA

Answer 1

Ans. A Median- used to minimize affect of extra values biomarkers you can have non so average not reliable also Income is use Median, a few billionaires and bums can through it off.

B. Mode- not at all effected by extreme values use for nominal data and Detection of mixed pop.

C. Mean: School grades anthropometric values like height and weight where zero isn’t and infinity are not possible

Question 2

With the Dataset 2,9,6,9,,4,4,1 find the interquartile range.

A. 7.5-2
B. 7.5-3
C. 6-3
D.4-2
E. 5-1.5
F. 8-4.5
G. 8.5-3

RFA

Answer 2

Ans. B 7.5-3

put in order

1,2,4,4,6,9,9 find median (4)

split in two 1,2,4,4 find median odd so find mean of middle two 4+2/2=3 Q1

4,6,9,9 6+9/2=7.5 Q3

Q3-Q1= 7.5-3

Question 3

A study is examining morning fasting blood glucose values in a random sample of males and females with Type 2 DM. All subjects take Metformin. Which type of graph is best to display the distribution of data?

A. Histogram
B. Bar graph
C. Boxplot
D. Frequency Table
E. Pie-chart 

SZ

Answer 3

A. A Histogram

Histogram is used for continuous variables. There is detailed information within-group variability.

Bar graphs summarize averages of 2 or more categories. No information within-group is displayed.

Question 4

Which of the following is the correct definition/calculation of variance?

A. Measure of distance each point is from the mean
B. Sum of squared deviations from the mean, divided by the total sample size
C. Typical variability which examines half of all values within a specific range
D. Total variability, indicating extreme values

SZ

Answer 4

Ans. B

Variance highlights typically squared variability. It is found by summing the squared deviations from the mean, and dividing it by the total sample size.

A. Standard deviation is measure of distance from the mean.
C. Interquartile range examines typical variability.
D. Range is total variability indicating extreme values.

Question 5

You are looking at a population of female runway models walking in one show. Very few of the models are plus size models. You plot a histogram of the weights of the models. Which of the following is true? (MG)

A. The mean weight is lower than the median weight
B. The median weight is lower than the mean weight
C. The mean and median weights are roughly the same

Answer 5

B. The median weight is lower than the mean weight

The vast majority of the models weigh very little, bringing the median low. However, the plus size models are skewing the mean higher, thus the mean is higher than the median

Question 6

You are given two different data sets plotted as histograms. These data sets have the same mean and median, and the mean = median. What is most likely to be different between the two sets? (MG)

A. Mode
B. Range
C. IQR
D. Second mode

Answer 6

B. Range

The data sets could be centered around the same mean and median but one might be more spread out than the other- thus having a different range.

The mode is likely to be similar since the median and mean are the same. The IQR will neglect the more extreme values in a wider spread set, so it should be roughly the same.

Since the mean and median are the same for both sets, a second mode would have to be the same/similar between the sets