Week One: Variable Is The Levels Of Measurement And Descriptive statistics

Question 1

What are the four levels of measurement

Answer 1

Nominal/categorical, ordinal, interval and ratio.

Question 2

What is meant by nominal level of measurement

Answer 2

This is the most basic level of measurement. The data is placed into categories where there is no clear order. For example type of pet. The only data that we can collect is frequency data of counts in each category

Question 3

What is a binary variable

Answer 3

This is a special kind of nominal variable in which there are only two possible categories such as a yes or no

Question 4

What is an ordinal level of measurement

Answer 4

This is where there is a clear order between categories however there is not a meaningful numerical difference in between the categories. An example would be coming in first and second we don’t know how much faster someone was just simply that they arrived first

Question 5

What is meant by an interval level of measurement

Answer 5

This is where there are meaningful numerical differences on the scale between points however there is not a true zero. With this level of measurement the only mathematical operations we can do is addition and subtraction. And example of interval level of measurement would be temperature as there are meaningful differences between one and 2° however you can go lower than zero so there is not a true zero.

Question 6

What is meant by ratio level of measurement

Answer 6

This is where there are equal intervals between points on a scale that are meaningful numerically however unlike interval level of measurement it does have a true zero.
Addition subtraction multiplication and division can all be performed on ratio level of measurement
And example of this would be height you cannot get shorter than 0 cm.

Question 7

What are the types of central tendency

Answer 7

There are three types of central tendency mean median and mode. They provide a midpoint in the data

Question 8

How is mean calculated

Answer 8

The sum of each individual score is divided by the total number of scores in the data

Question 9

How do you calculate the median

Answer 9

You order the scores and identify the middle score in the series. If there are even number of scores there will be two middle scores from this you will calculate the value of halfway between these two numbers this will be your median.

Question 10

How do you calculate the mode

Answer 10

The mode is the most frequent number appearing in a dataset however the mode will not be produced if there isn’t any values that are repeated

Question 11

Which measure of central tendency is is appropriate for nominal data

Answer 11

Mode

Question 12

Which measure of central tendency is is appropriate for ordinal level of data

Answer 12

Median or mode

Question 13

Which measure of central tendency is appropriate for interval level of data

Answer 13

Mean median and mode

Question 14

Which measure of central tendency is appropriate for ratio level of data

Answer 14

Mean median and mode

Question 15

Which measure of central tendency is sensitive to outliers

Answer 15

Mean

Question 16

What is an outlier

Answer 16

An outlier is a school that is numerically very far apart from the rest of the data and seems as though it doesn’t belong in that data set

Question 17

What is a measure of dispersion

Answer 17

These are ways of measuring how to spread out the date is

Question 18

What are the types of measures of dispersion

Answer 18

Range, interquartile range, variance and standard deviation

Question 19

How do you calculate range

Answer 19

You subtract the lowest score in the data from the highest score in the data

Question 20

Problems with the range

Answer 20

It is a very crude measure
Ranger only tells us about the most extreme scores not the spread within these extremes
Are strongly affected by outliers
Range tends to increase as sample size increases

Question 21

How do you calculate the interquartile range

Answer 21

First you identify the median then you identify a median for the scores below the original median and above the original median the difference between these two scores is the interquartile range

Question 22

What are the advantages of the interquartile range

Answer 22

It gives the central grouping of the values in a dataset and therefore is less affected by outliers
It is the best measure of dispersion for ordinal data

Question 23

What is the disadvantage of the interquartile range

Answer 23

It does not use all the scores in a set for the calculation

Question 24

How do you calculate variance

Answer 24

First you calculate the mean
Secondly you subtract the mean from each individual score then square it
Thirdly add all of these values together
Finally divide the sum of squares by the number of scores -1

Question 25

Advantages of variance

Answer 25

It is based on every score in the dataset

Question 26

Disadvantages of variance

Answer 26

Due to the fact that it has been squared it is not immediately meaningful

Question 27

How do you calculate standard deviation

Answer 27

First you calculate the variance | Then you square root it

Question 28

Advantages for standard deviation

Answer 28

It is based on all the scores in the dataset The value is meaningful in terms of the units for example it is not squared like variance It's often the best measure for interval and ratio data

Question 29

Disadvantages for standard deviation

Answer 29

It is not meaningful for ordinal data | It can be distorted by extreme values in a dataset