SOAN 3120 Midterm Review
Data – indentify individuals and variables in a data set. Identify each variable as
categorical or quantitative; indentify the units
Display distributions – pie chart can/can not be used
Making bar graphs
Characteristics of histogram (positively skewed, negatively skewed)
Decide which measures of centre and spread are more appropriate: mean, standard
deviation or 5number summary (skewed)
recognize outliers and give plausible explanations for them.
find median and quartiles q1 and q3
find the 5number summary: asses centre and spread, outliers (through fences)
min q1 Md q3 Max
Find the mean
Find the standard deviations s (variance from mean)
Recognize that skewness in distribution moves the mean away from the median towards
the long tail
what is the smallest standard deviation you can figure? And when wold that happen?
A: it can’t be negative because of the squaring of calculation; so the lowest it can be is 0.
This only happens when there is no deviation (all observations have the exact same
value.) eg. 2,2,2,2,2,2
Choose 4 numbers from one to give, with reputations allowed to create the largest
standard deviation possible.
A: 1, 1, 5, 5, this has the largest std deviations because these numbers are as far as
possible from the mean.
know that areas under a density curve represent proportions of all observations and that
the total area = 1
Locate the median and mean
Use the 689599.7 rule and symmetry to state what percent of observations from a
normal distribution fall between two pints shown the points lie on the standard deviation
Suppose a normal distribution data set has a mean of 10 and a standard deviation of 2
A) About what percentage of the data should lie between 8 and 12? B) About what percentage of the data should lie above 10?
Find the standardized value (zscore) or an observation (x – u/o)
Interpret zscores and understand that any normal distribution becomes N(0,1) when
Given that a variable has a normal distribution with a states mean u and standard
Know how to calculate the proportion values above a stated number below a stated
number, or between two stated numbers on normal distribution
Know who to calculate the point having stated proportion (%) of all values above it or
below it on normal distribution (x=zo+u)
if athabys weight is at the median what is her percentile?
A: 50 percentile (middle)
Clint, not a student in university on average sleeps and average of 8 hours per night with
a standardized deviation of 15 minutes. What’s the chance