AAA 3102 RESEARCH METHODOLOGI Lecture 9 Choosing the

  • Slides: 13
Download presentation
AAA 3102 RESEARCH METHODOLOGI Lecture 9 Choosing the correct statistical procedure or test

AAA 3102 RESEARCH METHODOLOGI Lecture 9 Choosing the correct statistical procedure or test

Nominal or Categorical �Sorting elements with respect to certain characteristics, similarity �Simplest and lowest

Nominal or Categorical �Sorting elements with respect to certain characteristics, similarity �Simplest and lowest level of measurement �Classification, naming, labeling �Poses the property of symmetry – (a=b, b=a) and transitivity (a=b, b=c, a=c)

Ordinal �Grouping or classification of elements with degree of order or ranking; arranged in

Ordinal �Grouping or classification of elements with degree of order or ranking; arranged in single continuum �May not be able to say exactly how much they posses �Poses the property of symmetry, transitivity and asymmetrical (a>b cannot be b>a)

Interval �Ordering elements with respect to degree which they posses �Indicate the exact distance

Interval �Ordering elements with respect to degree which they posses �Indicate the exact distance between them �Need to establish some sort of physical unit of measurement as a common standard �Zero does not mean absence of

Ratio �Ordering elements with respect to degree which they posses �Indicate the exact distance

Ratio �Ordering elements with respect to degree which they posses �Indicate the exact distance between them �Need to establish some sort of physical unit of measurement as a common standard �Zero mean absence of, absolute �Zero as fixed reference point

Statistical presentation �Nominal – frequency, cumulative frequency, ratio, proportion, percentages - cannot do add,

Statistical presentation �Nominal – frequency, cumulative frequency, ratio, proportion, percentages - cannot do add, subtract, multiply, divide, more and less �Ordinal – all of Nominal - can do more and less �Interval and Ratio – all Nominal and Ordinal - can do add, subtract, multiple and divide

Measure of central tendency (MCT) �Statistics that summarize a distribution of scores by reporting

Measure of central tendency (MCT) �Statistics that summarize a distribution of scores by reporting the most typical or representative value of the distribution �Mode �Median �Mean

�Mode: The most common value in a distribution or the largest category of a

�Mode: The most common value in a distribution or the largest category of a variable, symbol Mo �Median: The point in a distribution of scores above and below which exactly half the cases fall, symbol Md �Mean: The arithmetic average of the score, symbol x

General guides �Use mode when: - variables are nominal - want to report most

General guides �Use mode when: - variables are nominal - want to report most common score - want to present quick and easy measure for ordinal, interval and ratio variables

�Use median when: - variables are ordinal - want to report the central score

�Use median when: - variables are ordinal - want to report the central score - the scores measured at interval and ratio levels have badly skewed distribution

�Use mean when: - variables are interval or ratio (except badly skewed distribution) -

�Use mean when: - variables are interval or ratio (except badly skewed distribution) - want to report typical score - anticipate additional statistical analysis

Measure of dispersion (MD) �Statistics that indicate the amount of variety or heterogeneity in

Measure of dispersion (MD) �Statistics that indicate the amount of variety or heterogeneity in a distribution of scores - Range - Standard deviation - Variance

�Range: The difference between the highest score and the lowest score or the highest

�Range: The difference between the highest score and the lowest score or the highest score minus the lowest score �Standard deviation: The square root of the squared deviations of the scores around the mean divided by N, symbol s �Variance: The square of standard deviation, symbol s²