data handling and anaylsis

What are primary and secondary data?

Primary: authentic data obtained from the participants themselves for the purpose of a particular investigation

Secondary: data that has already been collected before

What is qualitative data?

Non-numerical,usually written or a transcript of spoken word or behaviour, and provides insights into feelings and thoughts that quantitative data cannot

• Can be derived from a variety of media

What are examples of qualitative data in clinical psychology?

• Nurses observations in daily reports

• Results of clinical interviews

• Diary analysis

What is quantitative data?

Numerical values, statistics, data…

What are the levels of measurement?

Nominal data: most basic and least precise

• Data is put into tally charts/categories - categorical data

• Gives very little information

Ordinal data:

• Data is put into rank order

• But, units of measurement are not equal, definable size

• Questionnaires that yield a numerical value are ordinal

Internal data: most precise

• Equal gap between each unit of measurement (e.g. cm, m, kg…)

What is correlation? How to describe them?

Correlation states the strength and direction of an association/link between 2 or more co-variables

• these are plotted on scattergrams

Positive correlation: as one variable rises, the other rises too

Negative correlation: as one variable rises, the other falls

Zero/no correlation: no link between co-variables at all

Co-variables: the variables investigated within a correlation

• investigates a link between variables, instead of cause and effect relationship (causal relationship)

What are correlation coefficients?

A statistical method for assessing the strength of a correlation

• the sign (+ or -) gives the direction

• The number (between 0 and 1) gives the strength

• (E.g. -1: strong negative correlation, 0: no correlation, +1: strong positive correlation)

Statistical tests:

• Spearman’s rank

• Pearson’s product moment correlation

What type of statistical test is suitable for what type of data?

Ordinal

Spearman’s

Internal

Pearson’s

(Ordinal data = Spearman’s Rho, Internal data = Pearson’s Product Moment Correlation)

If one co-variable is ordinal and other one is internal, go with Spearman’s)

What are the strengths and limitations of correlations? -evaluation

Strengths:

• Precise and quantifiable measure of how 2 co-variables are related

• May suggest possible further research if variables are strong related

• Used as a starting point to access possible patterns between variables

• Relatively quick and economical to carry out

Limitations:

• Lack of experimental manipulation and control - cannot tell why variables are related

• Cannot demonstrate causal relationship between variables - don’t know which variable is causing change

• Third variable problem: another untested variable is causing the relationship between the 2 co-variables - an influencing variable =correlations an be misused or misinterpreted

What is coding in content analysis?

• Coding unites: the catagories

• Coders: records the data in the categories (e.g. the number of occurrences of a particular coding category) - nominal level of measurement (frequencies)

What are descriptive statistics? What are the 2 types of measures?

Descriptive statistics describe features of the data - How spread out is the data? How is the data clustered together?

• Measures of dispersion: range, standard deviation

• Measures of central tendency: mean, median, mode

What is the mode? How to calculate it? What are the advantages and disadvantages?

The mode is the value or event that occurs the most frequently

• It is the most suitable measure of central tendency for nominal data

+: Not influenced by extremes values

+: Useful to show most popular value

-: Crude measure of central tendency

-: Not useful if many equal modes

What is the median? How to calculate it? What are the advantages and disadvantages?

The middle value when all values are placed in rank order

• The most suitable measure of central tendency for ordinal data

+: Not distorted by extreme freak values

-: Can be distorted by small samples

-: Less sensitive

What is the mean? How to calculate it? What are the advantages and disadvantages?

The average value of all scores

• The most suitable measure of central tendency for interval or ratio data

+: Most sensitive measure of central tendency of all data

-: Can be distorted by extreme freak values

What is the range? How to calculate it? What are the advantages and disadvantages?

The difference between the smallest and largest value

+: Quick and easy to calculate

-: Distorted by extreme freak values

What is the standard deviation? What are the advantages and disadvantages?

The average amount all values deviate from the mean

-3 -2 -1 mean(0) 1 2 3

+: The most sensitive measure of dispersion, using all the data available

+: Can be used to relate the sample to the population’s parameters

-: A little more time consuming to calculate but no important disadvantages

What are the types of graphical descriptive statistics?

Nominal data

• Bar charts

• Pie charts

Ordinal / Interval data - continuous data

• Histograms

• Frequency polygon

Correlations

• Scattergrams

They display quantitative data

What is normal distribution?

• Bell shapes - the Bell Curve

• Symmetric at the midpoint where the mode, media and mean all fall

• The percentage of values covered by the areas between the standard deviations of the curve are known

• Never touched the x axis

What is a positive skewed distribution?

X-axis: mean > median > mode

Mean, median and mode, going up the road

What is a negative skewed distribution?

X-axis: mean < median < mode

Mean, median an mode, going up the road