data analysis

Question 1

when is linear regression used?

Answer 1

to improve correlation when measuring associations between continuous exposures and outcomes

Question 2

how can you get a more representative sample?

Answer 2

more data

Question 3

what does statistics allow for?

Answer 3

it allows us to take all data in and summarise it in a way that is understandable and useful

Question 4

what are the two main properties of data that we want to capture through statistics?

Answer 4

where quantitative data sits in numerical space and what categorical data is more or less common, what the values look like and understand the relationship

Question 5

what does the analysis done depend on?

Answer 5

how is the data recorded and how is the data distributed and the research question - does it answer what it is meant to

Question 6

how is categorical data usually recorded?

Answer 6

as text or labels

Question 7

what is ordinal data?

Answer 7

when it is ordered or ranked

Question 8

how can you present categorical data?

Answer 8

counts, percentages, tables and graphs

Question 9

what alters how you present data?

Answer 9

who you are presenting the data to

Question 10

in what order does STATA follow commands?

Answer 10

command name, then argument for command and then further options after comma

Question 11

what are arguments?

Answer 11

they are variables to determine how the command is run i.e. bar

Question 12

when should you add graphics to the bar chart?

Answer 12

only if they provide more information and help to understand the information already given

Question 13

what are the methods for testing relationships?

Answer 13

logistic regression and T tests and chi squared - this is where we have one categorical and one continuous variable

Question 14

what is numerical data?

Answer 14

it is when the data is data is in numbers - can count or measure the values

Question 15

what is discrete?

Answer 15

when the numerical data is whole numbers

Question 16

how can you summarise the size of numerical values?

Answer 16

mean and median

Question 17

how can you summarise the spread of numerical values?

Answer 17

variance, SD and IQR

Question 18

how can we report some sort of extreme in numerical values?

Answer 18

modal value, the minimum and the maximum

Question 19

what do you need to consider when analysis numerical data?

Answer 19

the specific reason for comparing groups or populations

Question 20

what can you get from the simple plot graph?

Answer 20

the range and the mode and understand how the data fits together

Question 21

what do histograms show?

Answer 21

how common the values are relative to each other - where the typical or most common values fall

Question 22

what would you use in normal distribution?

Answer 22

it is symmetrical so mean and SD

Question 23

how do you calculate SD?

Answer 23

you find each value and subtract the mean and then square each result. Add them altogether and divide by one less than the total number of values and take square root

Question 24

what is the mean?

Answer 24

the sum of all values/total number of values

Question 25

what is the SD?

Answer 25

it is the average spread of values around the mean

Question 26

what is left skew?

Answer 26

when the low values are quite rare and the long tail goes to the left - opposite is right skew

Question 27

what is the IQR?

Answer 27

the spread of values around the median - distance between values one quarter of way into the data and 3/4

Question 28

when would you use the IQR and median?

Answer 28

when the data is skewed

Question 29

where is the median when there is a tie?

Answer 29

it lies between them

Question 30

what is true of a normal distribution?

Answer 30

median = mean

Question 31

what does a scatterplot show?

Answer 31

it shows the relationship between two numeric variables - how the x changes relative to the y - how they covary

Question 32

what is a perfect positive and negative correlation?

Answer 32

positive = 1 and negative corr = -1

Question 33

what is the value for no correlation?

Answer 33

0

Question 34

how would you formalise a correlation?

Answer 34

use a correlation test

Question 35

what correlation test would you use for a) a normal distribution and b) a skewed?

Answer 35

a) Pearson

b) Spearman’s Rank

Question 36

what are the limits of correlations?

Answer 36

cannot comment on the exposure: outcome relationship, only use two variables, does not comment on the direction of the correlation, can only test for linear relationship, can be an oversimplification - may show some things as similar when they are not

Question 37

what is Anscombe’s quartet?

Answer 37

it is a set of pairs of variables that all have the same correlation between each other but when looked at individually actually have very different structures - shows how reducing the relationship between two variables to one number may miss detail

Question 38

why must many correlation tests be done?

Answer 38

to see the effect of confounders

Question 39

what is regression analysis good for?

Answer 39

can specify multiple exposures, include non-linear relationships and specify and exposure and outcome

Question 40

what is included in regression analysis?

Answer 40

for the relationship between two variables an intercept value followed by an effect size is given - the effect size shows how for one unit of change per exposure how the outcome is expected to change - can add a best fit to easily calculate this

Question 41

what is R2?

Answer 41

it is the proportion of variation in outcome explained by the exposure

Question 42

what must you include in regression analysis?

Answer 42

the 95% CI and the P value