Natural resource biometrics EXAM 1 (MU- Halsey)

What is a null hypothesis?

Assumes there is no relationship or difference between variables

What is an example of a null hypothesis?

The new drug has no effect on the risk of a heart attack

What is a type 1 error?

Rejecting null hypothesis when it is true (false positive)

What is a type 2 error?

failing to reject a false null hypothesis when it is not true (false negative)

What is population?

Entire group of individuals

What is a sample?

subset of the population

What are the four ways to sample?

- Simple random: picking individual from group randomly

- Stratified random sampling

-Cluster sampling

-Systematic sampling

Why do we often sample in fractional units?

Because the entire unit is usually too large and often will cost more money

Define Variable

Characteristic that can change from one member of the population to another

Predictor

Explains or predicts an outcome.

Response

The focus of the story, what you're actually measuring

What are the five metrics that make up the five-summary?

minimum, first quartile (Q1), median (Q2), third quartile (Q3), and maximum.

Sample variance

how sample is spread out around data

Sample Standard deviation

how sample is spread around mean

Mean

average

Median

middle value

Mode

value that occurs the most frequently

List and describe the two assumptions for performing most statistical procedures

-distribution of sample means is normally distributed

-variances are homogeneous

Name two ways you can do a visual check for normality

- Histogram

- Qqplot: diagonal line not s or c shaped

Name the test to formally check for heteroscedasticity

Levine's test

What is a normal distribution?

bell curve

What is log-normal distribution?

graph is skewed to left

One sided hypothesis

departure from null is in one direction

Two sided hypothesis

distribution from null is in 2 directions

How do we interpret p-values as it relates to the null hypothesis?

p < 0.05, reject null hypothesis

p is greater than 0.05=fail to reject null hypothesis

Define Degrees of freedom and the impact they have on an analysis

number of independent values that can vary, affects the shape of a probability distribution, influencing the likelihood of different outcomes

Describe Residuals and the impact they have on an analysis

-Difference between observed and predicted value

-Help assess the fit of a model

Identify whether a figure of a line graph is either a positive, negative and no correlation

Positive: line up

No correlation: straight line

Negative: line down

Two Sample t-test

2 groups that are unrelated

Paired t-test

relationship between 2 groups

What does it means when 95% CI for group means overlap on a graph?

Data is not significantly different

Under what circumstances would you would use a non-parametric test over a parametric test?

If data is not normally distributed when sample sizes are too small

Define a model

Representation of natural world but it helps to test a hypothesis

Describe Occam's Razor as it relates to models

Best explanation is the one that makes the fewest assumptions

Give a least one reason why you would use either AICc or QAIC(

When you have an over-dispersion of data

Identify the type of response and predictor variables for regression analysis

-Predictor: continuous

-Response: continuous

List the assumptions for a linear regression

-Linear model correctly describes relationship

-Independent errors

-Normally distributed errors

-Constant variance

Describe the relationship between AIC and information loss

AIC estimates the relative amount of information lost by a given model.

The less information a model loses, the higher the quality of the model

When comparing models with AIC, How do you know which model is the best model

Model with the lowest AIC value

What are the type of response and predictor variables for Analysis of Variance (ANOVA)?

-Predictor: categorical

-Response: continuous

What's the difference between a one way and two-way ANOVA?

-One way: uses one factor

-Two way: uses two factors

What is a post hoc?

Test the equality of at least three group means to see if there is a significant result that not all the group means are equal (will not tell you which ones differ)

What is data dredging?

Analyzing data over and over again with different techniques until significant data is found