biostats Flashcards

1
Q

What is a sampling error?

A

when the entire sample is not relevant to the entire population

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Three examples of non-sampling errors

A

poor sampling method, measurement/questionnaire error, behavioral effects.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Statistical population

A

all the individuals for which we have an interest concerning some property

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Sample

A

piece of a population

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Census

A

data collected from the entire population

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Descriptive statistics

A

values that we calculate based on the sample. ex: mean, mode, S.D, etc.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Inferential statistics

A

applying probability to sample values to understand something about the population. ex: 95% CI

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Statistic vs. Parameter

A

statistic=sample
parameter=population

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Accuracy

A

closeness of a measurement to its correct value

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Precision

A

closeness of repeated measurements to one another

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Bias

A

when a sampling method tends to produce high or low values relative to the correct value

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Experimental Design

A

Goal is to answer the research question as clearly and as efficiently as possible.
Design must ensure that
1. the right data are collected
2. the sample size is sufficient (n=replicates used)
3. the highest power of the test possible (statistical test that can detect differences when there are differences)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Statistical bias

A

any instance that creates a difference between an expected value and the true value of a population characteristic being estimated, leading to inaccurate results.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Noise

A

natural variation or variability caused by the experimenter, or more simply put, any unexplained variability within a data sample

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

3 ways to decrease noise

A
  1. increase sample size
  2. standardize protocols
  3. control environmental factors
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What is the difference between a replicate and a trial?

A

Replicate: an observation in a treatment. n = number of replicates per treatment. N = number of replicates in an experiment.
Trial: an exact repeat of an entire experiment