Graphs/Tables
Type of graph that displays two numerical continuous data
Scatter plot
The measures of spread vs. the measures of location
Standard deviation/variance vs. mean/median/mode
What is the value we use to determine if something is significant?
p value; less than or equal to 0.05
Three ways to reduce bias
Control group, randomization, and blinding
What is a confounding variable?
An alternative variable (not the IV/explanatory variable) that could have an effect on the response variable
Remove gridlines, add axis titles, remove chart title, darken lines, add figure legend
What the 95% Confidence Interval shows
The true mean will not be displayed 5% of the time
Difference between Type 1 and Type 2 error
Type 1: reject null, when null is actually true
Type 2: fail to reject a false null
Three ways to reduce sampling error
Replication, balancing, and blocking
What are the rules for error bars?
- Figure legend should describe what type of error bars are displayed
- Sample size, n, included in legend
- In experiments when comprising controls, use inferential error bars
- Standard error bars doubled will produce 95% CI (if sample size is greater than 10)
Three places tables have lines
Top, underneath statistics labels (darker), and bottom
The measures influenced by sample size
Confidence interval and standard error
The meaning of an alternative hypothesis to be "two-tailed"
The IV could effect the DV in a positive or negative way
Difference between single blind and double blind experiments
Single blind: Only the participants are unaware
Double blind: The participants and the researchers are unaware
What is an experimental artifact?
Aspect of experiment itself that biases experiment
Bar graphs display what kinds of data
Two categorical pieces of data
Measures influenced by extreme values? Measures not influenced by extreme values?
Mean
Median
Definitions of null and alternative hypotheses
Null: IV does not effect DV
Alternative: IV does effect DV
Difference between experimental and correlational design
Experimental: treatments are manipulated and varying explanatory variables are assigned to sample
Correlational: nature is observed as is; uses existing variation explanatory variable
What is a sample of convenience?
Taking a sample of individuals that are easily available. Not a true representation of the population
Information displayed in a figure legend
Title, sample sizes of species, materials/methods, and type of error bars used
When are mean and median the same? When are they different?
Same = normal distribution/symmetric
Different = skewed/asymmetric
The four steps of hypothesis testing
1. State statistical hypothesis
2. Compute test statistic
3. Determine p-value
4. Draw appropriate conclusions
Difference between replication and pseudoreplication
Replication: all values are independent
Pseudoreplication: non independent values analyzed as independent
What is confirmation bias?
Researchers are more likely to record data that supports their prior predictions