IPR Revision Notes PDF

IPR revision notes Types of validity: 1. Face- it appears to measure what it’s meant to 2. Construct- it appears to measure the theory/construct it’s meant to 3. Criterion- how well one measures/predicts an outcome based on another measure 4. External- findings can be generalis...

IPR revision notes Types of validity: 1. Face- it appears to measure what it’s meant to 2. Construct- it appears to measure the theory/construct it’s meant to 3. Criterion- how well one measures/predicts an outcome based on another measure 4. External- findings can be generalised to other contexts Types of case studies: 1. Exploratory- to explore a new area of research or generate hypothesis 2. Descriptive- detailed account of a specific case 3. Explanatory- explains the reasons behind a particular phenomenon 4. Intrinsic- focuses on specific case emphasizing its uniqueness or significance 5. Instrumental- provides an insight into a broader issue 6. Collective- multiple cases studied Ethnography-study those in their natural environments Types of thematic analysis: 1. Thematic analysis- identify patterns or ideas across multiple data sets 2. Content analysis- analysing various sources of data 3. Narrative analysis- examines stories from individuals 4. Grounded analysis- to develop a theory grounded in data collection 5. Discourse analysis- to study language and communication 6. Interpretative Phenomenological Analysis (IPA) lived experiences of individuals Proces of conducting a thematic analysis: 1. Familiarise yourself with data 2. Generate initial codes 3. Search for themes 4. Review themes 5. Define and name themes 6. Produce a report Content analysis- deductive (predefined) or inductive (emerging) categories Cohen’s kappa- a test statistic that considers chance agreement True zero- complete absence of a measure Data types:  Time series data- data collected at specific time intervals Hierarchal data- data is organised in a multi-level structure Cross sectional data- data collected at a single point in time Variance- compares participants original score to the mean- overall spread of data points - Find mean of the data set - For each data point, subtract the mean (and square it) Called squared deviations - Sum these squared deviations and divide by N (for population variance) or divide by N-1 (for sample variance) Standard deviation- square root variance- average spread of data points (Both measures tell us how consistent the data is within our data set- useful when comparing conditions) When to use each graph: Histogram- visualize distribution- frequency of data Box plot- summarise and compare distributions and identify outliers Violin plot- distribution and variability in more detail Bar chart- compare values or densities across categories Bimodal distribution- where there is a divide in the data set Descriptive statistics: - Measures of central tendency- mode, median, mean - Measures of dispersion- Range, IQR, variance, standard deviation Skewness  Kurtosis- the shape of the distribution- measures the tailedness (peak) of distribution Types of hypotheses: - Null hypothesis- there will be no effect or relationship (we reject the null hypothesis) (we fail to reject the null hypothesis) - Alternative hypothesis- there will be an effect or relationship (one tailed- direction specific, two tailed- direction not specified) - P value- the probability of obtaining the observed data - Z score- how far a single data point is from the mean- used to compare different data points Type 1 error: false positive- we reject the null hypothesis when the null hypothesis is true Type 2 error: false negative- we fail to reject the null hypothesis when the null hypothesis is false  Chi squared test assumptions: (all are two tailed tests- direction not specified) 1. Data type- nominal or ordinal data 2. Mutual exclusivity- categories/variables should be mutually exclusive (independent) 3. Expected frequency- should be more than 5 for each cell to ensure validity of chi-squared test 4. Independence of observations- every observation in the dataset is independent 5. Random sampling- data from a random sample to ensure representativeness and avoid bias Goodness of fit test (one variable) - Frequency tables - The bigger the chi squared value- the greater the difference between the observed and expected frequencies - Small chi squared value- smaller difference between observed and expected frequencies - Degrees of freedom (df) room of variation allowed to satisfy the tests Repeat for all categories and sum to find the chi squared value Test of association (two variables) - Calculate the expected frequencies for each cell using the formula below Then apply expected value to the chi squared formula Alpha threshold-.05- determines the threshold for rejecting the null hypothesis Power- 80- 20% chance of making type 2 error Remember- standard deviation is not a measure of central tendency!!!