Research things

• Independent variable is the one being manipulated that will have a causal effect on another variable
• Dependent variable is what the researchers generally measured and that is influenced by another variable that was manipulated
• High probability means that the results of the study are due to chance
• Low probability means that results of the study are due to the proposed hypothesis
• Nominal variable names something that has no meaningful order, it is just words & it is qualitative
• Ordinal variable classifies data int ordered categories but does not convey the degree or magnitude of difference between the categories, also qualitative
• Interval variable measures the difference between values on a scale, you can also add or substract those number and it has an arbitrary zero point (meaning 0 is not actually absence of something, it also has meaning), also quantitative
• Ratio variable has a meaningful 0, can undergo all sort of mathematical manipulations, also quantitative
• Accuracy is how well measurements reflect the true value of something
• Precision refers to how well multiple measured values agree with each other
• Negative controls are procedures not expected to produce results
• Positive controls are procedures with well-understood, usually positive effects
• Simple random sampling: select participants purely randomly
• Cluster random samplingL select "groups" of participants randomly
• Stratified sampling: sort populations into subpopulations, then randomly sample proportionally from those subpopulations
• Snowball sampling: initial participants are found, then they refer researchers to other participants
• Block design is when you group participants first by some category (like gender) than randomize, but you cant control for other variables
• Matched pair design is when each participant has a pair that matches them in target variables that the experimenter might think are meaningful, then this pair is separated into different groups, but it is not always feasible
• Observation studies are usually correlational
• Cross-sectional study studies a sample at one point in time
• Longitudinal studies study one sample over time
• Case-control studies study two groups< one that had something happen in the past and one normal (example with baby death syndrom)
• Quasi-experimental studies are when the intervention was applied but not randomly, also often longitudinal
• Case studies dig deeply into few cases
• Parameter refers to population and statistic to the sample
• Descriptive statistic describes data, but does not seek relationships with it. Refers to measures of central tendency and measures of dispersion
• Discrete data are numerical data restricted to certain values such as 1, 3, 4 (no 5.6)
• Continuous data are not restricted to certain number values (like 63, 62.6, 61.540404)
• Continuous data is plotted on the continuous probability distribution graph which can be either uniform or normal (which is bell shaped, symmetrical and has mean in the center)
• Mean us the average, calculated by adding all data points and dividing by the total number of points. Disadvantage: one outlier can skew all the mean
• Measures of central tendency are mean, median and mode
• Median is the middle value of the ordered set, when we take away those numbers on the side one by one until we get to the middle one
• In the symmetric distribution, mean and median are the same
• Mode is the value that occurs most frequently in the set
• For skewed data with outliers, median is the most appropriate measure of central tendency
• Measures of dispersion describe how spread out the data are, include range, interquartile range and standard deviation and variance
• Range is calculated by substracting the smallest value in a set from the largest value
• Quartiles split data into 4 portions, where Q1 = more than 25%, Q2 = is the same as median, 50% and Q3 is larger than 75%, and Q4 = 100%
• Interquartile range equals Q3 - Q1
• This is a boxplot

  A) Q1

  B) Q3

  C) Median