L25 - Factors affecting Choice of Statistical Test, Levels of Measurement

Question 1

what are LEVELS OF MEASUREMENT?

Answer 1

LEVELS OF MEASUREMENT are used to try to CATEGORISE OUR DATA into ONE OF THREE TYPES, so that we can CORRECTLY SELECT THE MOST APPROPRIATE STATISTICAL TEST to ANALYSE OUR RESULTS

The THREE TYPES ARE:

NOMINAL
ORDINAL
INTERVAL

Question 2

what is NOMINAL LEVEL DATA?

Answer 2

Can be referred to as CATEGORICAL DATA, it is DISCRETE DATA.

Tends to be WORDED DATA - if pps are asked do they attend SCHOOL or COLLEGE, this is NOMINAL LEVEL DATA - pps are in EITHER ONE CATEGORY OR THE OTHER but NOT BOTH

Question 3

what is ORDINAL LEVEL DATA?

Answer 3

Data is ORDINAL if it is ORDERED IN SOME WAY and the INTERVALS BETWEEN THE DATA ARE NOT EQUAL

For example pps are asked to rate the PREFERENCE OF THEIR LOCAL RESTAURANTS 1 - 1-

The GAP between 1 and 2 for one pp may be COMPLETELY DIFFERENT than it is for another pp. E.g one pp may consider there to be TWO REALLY GREAT RESTAURANTS at 1 and 2 but another pp may think that 1 is WELL CLEAR OF 2

This type of data is MORE SUBJECTIVE and the RATING SCALE KIND OF DEPENDS ON THE PP and HOW THEY VIEW THINGS

Question 4

what is INTERVAL LEVEL DATA?

Answer 4

INTERVAL LEVEL DATA is like ORDINAL in that it refers to data that is ORDERED IN SOME WAY, however the INTERVALS BETWEEN EACH VALUE ARE EQUAL IN VALUE IN INTERVAL LEVEL DATA

This type of data is MUCH MORE OBJECTIVE and SCIENTIFIC IN NATURE AS A RESULT

Examples of INTERVAL LEVEL DATA include TEMPERATURE and TIME - it has an ORDER TO IT, it is NUMERICAL, but it also has EQUAL INTERVALS BETWEEN EACH MEASUREMENT, HEIGHT is ANOTHER EXAMPLE

Question 5

STRENGTHS of NOMINAL LEVEL DATA

Answer 5

• EASILY GENERATED from questionnaires

- the MODE can be applied to NOMINAL DATA

Question 6

LIMITATIONS of NOMINAL LEVEL DATA

Answer 6

• NO SCALE OF REFERENCE for NOMINAL DATA, as it is SIMPLY CATEGORICAL
• DATA is NOT VERY COMPLEX, OVERLY SIMPLISTIC
• NO MEASURE OF DISPERSION which can be APPLIED TO NOMINAL DATA

Question 7

STRENGTHS of ORDINAL LEVEL DATA

Answer 7

• PROVIDES MORE DETAIL THAN NOMINAL DATA as SCORES ARE ORDERED

Question 8

LIMITATIONS of ORDINAL LEVEL DATA

Answer 8

• the INTERVALS BETWEEN SCORES ARE NOT OF EQUAL VALUE
• AVERAGE THEREFORE CANNOT BE USED as a MEASURE OF CENTRAL TENDENCY
• MEDIAN IS MOST OFTEN USED TO OVERCOME THIS LIMITATION

Question 9

STRENGTHS of INTERVAL LEVEL DATA

Answer 9

• INTERVAL LEVEL DATA is considered MORE INFORMATIVE than NOMINAL AND ORDINAL LEVELS of MEASUREMENT
• the GAPS BETWEEN SCORES are of EQUAL VALUE and are THEREFORE MORE RELIABLE

Question 10

LIMITATIONS of INTERVAL LEVEL DATA

Answer 10

• in SOME INSTANCES, the INTERVALS are ARBITRARY - e.g 100 degrees centigrade is NOT TWICE AS WARM as 50 degrees centigrade
• we can only say that the DIFFERENCE BETWEEN 10 and 20 degrees is the SAME as between 30 and 40 degrees