Interpreting Geographical Data

Year one statistics exam

  • Summation sign
  • Rounding
  • Central tendency
  • Variability
  • Boxplots
  • Standard deviations
  • Normal distribution
  • Sampling
  • Reliability and standard errors
  • Confidence intervals and t-distribution
  • Colomn, charts and tables
  • Hypothesis testing and one sample t-test
  • Two sample t-test
  • F-test
  • Anova I
  • Anova II
?
  • Created by: Sophie
  • Created on: 04-01-15 13:38
What is a subscript?
When a figure is lower down and in a lower case form from a letter.
1 of 81
What does the sigma, E and numbers mean in a summation equation?
Sigma= sum, E= quantity and the numbers represent the reference number
2 of 81
What is the dummy variable?
It is shown by the subscript of j next to the sigma sign but not in the rest of the equation.
3 of 81
What is rounding down also known as?
Truncation
4 of 81
What do you do when asked to round off?
Your round up or down depending on what distorts the data the most
5 of 81
What is it when we have a convention?
When we do not know whether to round up or down as the are both equal as each other, but generally you round up.
6 of 81
When do you start start counting significant figures?
Following a decimal place and a figure other than 0
7 of 81
What statistics are similar to one another?
Mean and median are normally similar whilst the mode can be very different
8 of 81
What is the best form of mode?
Biomodal
9 of 81
Which statistic is more sensitive to extreme values?
The mean and not the median or mode
10 of 81
Definition of variability
All different values
11 of 81
Definition of central tendancy
A typical value
12 of 81
Definition of range
A value that lies within the values
13 of 81
Definition of error
When cannot measure a value perfectly so automatically introduces uncertainty
14 of 81
What is dispersion also refferred to as?
Variation within the data
15 of 81
What is nominal data?
Where you allocate a score to a category and it indicates a group of data
16 of 81
What is ordinal data?
Where you rank items that you measure depending on which has a more or less of an influence that we want to measure. Intervals are not necessarily equal and there is not true zero point
17 of 81
What is interval data?
Where there are equal intervals of data on a continuous numerical scale, eg: farenheit
18 of 81
What is ratio data?
Where there are equal intervals between the data and an absolute zero, eg: time
19 of 81
What is variability?
The tendency to vary. It is the measure of variation or dispersion
20 of 81
How do you calculate variability?
Range
21 of 81
Why is range a good statistic?
Extreme values are not ignored
22 of 81
Define sample
Statistical methods used to make statements about the poplation
23 of 81
Define inference
The process of moving from info about samples to statement about population
24 of 81
Define confidence
The application of probability levels to statements made about the sample and whether they fit with the true population parameters
25 of 81
Define parameters
Statistics from samples for population
26 of 81
Define statistics
Best guess of the true population parameter
27 of 81
What is the definition of quartiles?
Eliminates the extreme values and is related to the median
28 of 81
What is the weighted average?
When you work out the fraction between the gaps of data, where each quartile is calculated
29 of 81
What do whiskers represent?
Data outside the 50% average, up or down
30 of 81
What is known as an outlier?
If a dataset is more than the IQR up or below
31 of 81
What does a histogram predominately show?
Central tendancy and variation
32 of 81
What can you not add up from the data shown on a histogram?
Range
33 of 81
What is termed as a symmetrical within histograms?
Values in and around the mean
34 of 81
What is known as artefact?
Making sure you analyse the data carefully without thinking it is false as it is not the whole population
35 of 81
What does a Poisson frequency distribution graph show?
Unusual things
36 of 81
Which statement is incorrect about a good measure?
A good measure should increase with sample size increase
37 of 81
What is not a step of working out standard deviations?
The mean is then added to each value
38 of 81
Which key term and definition is incorrect?
Bias- if errors are random, are reliable and give correct conclusions. Favouring aspects as equally as one another.
39 of 81
Which statement is incorrect about multiple samping?
Sampling does not have to be truly random
40 of 81
Which statement best describes a parent distribution?
The real population from which you will sample
41 of 81
What is reliability?
The measure of how similar the sample mean is as an estimate to the population mean
42 of 81
Which statement is incorrect about how we measure reliability?
Unreliability is not proportional to the sample standard deviation divided by the sample size
43 of 81
How do we calculate a confidence interval?
By calculating a range within which we are confident that the true mean lies
44 of 81
Which statement is incorrect about confidence intervals?
The 95% is more wider than the 99%
45 of 81
What do we not need to calculate of confidence interval?
The range
46 of 81
Which statement is not true for the students t-test?
More degrees of freedom makes the curve wider and less degrees of freedom make the curve narrower and more similar to the normal distributions
47 of 81
Which statement is incorrect about determining t?
The critical value of t is completely different from the tabulated t value
48 of 81
Which is the correct formula for calculating the confidence interval?
CI=2xttabxSE
49 of 81
Which statement is incorrect about reporting CI?
The mean was 6.75 mm at 95% CI and N=100
50 of 81
Which statement is incorrect about how we visually display data?
Maps are used to show trends in data patterns
51 of 81
Which is not an improvement that could be made to colomn charts?
May the chart look as professional as possible
52 of 81
Which statement is incorrect about error bars on Excel?
You can use the option of standard error or standard deviation in Excel
53 of 81
What should tables not show?
The median and mode
54 of 81
Which statement is incorrect about clustered colomn charts?
Clustered coloumn charts show four variables, length which changes continuously, country which has four categories, market which has two levels and also the mean of each
55 of 81
Which is not a difference between chart coloumns and histograms?
The both contains plotting points against axis y and z
56 of 81
What is Occams razor?
If two explanations account for the facts equally well, the simpler one is to be preffered.
57 of 81
Which explanation about hypothesis' is incorrect?
Hypothesis- there is not pattern
58 of 81
Which statement is incorrect about counting the standard errors from the mean (6.72 mean and 7.0 intended value)?
Also need to know the range of values
59 of 81
Why do you use a two tails test?
To work out the probability that we are at least 4 standard errors away from the sample mean, not that we are 4SE to the right of the sample mean.
60 of 81
Why is it a one sample t-test?
100 grains in 1 country
61 of 81
What is the definition of a critical value?
A value that distinguishes significant from non significant differences at a specified level of confidence
62 of 81
Which statement is incorrect as to why should P values not be written on their own?
Give info on only two of these to support P value
63 of 81
Which definition is incorrect?
PARAMETRIC TESTS is where we do not assume the varaibility of the true population and class them differently
64 of 81
Which statement is correct in describing the statistical power?
Whether the test is powerful enough to detect a pattern, if that pattern exists. It is associated with TII errors.
65 of 81
What happens when there is a different but we failed to detect it, Type II error?
Absence of evidence is not the same as evidence of absence.
66 of 81
How can you reduce the number of unknowns in research?
Pilot Study followed by power analysis to see if sample size is too big/small
67 of 81
What are the two differences between the equal and unequal tests of the independent sample tests?
The formula for SEmean is the same for unequal and equal variances
68 of 81
How do we calculate the F test?
F = variance 1 ÷ variance 2. That is, F is simply the ratio of the variances. For this reason, the F-test is often called the ‘variance ratio test’. You use the degrees of freedom samples of the numerator and denominator
69 of 81
?Which statement is incorrect about Levene's Test?
There is a variant of the T-test
70 of 81
Which statement is incorrect about the non parametric tests?
Non-parametric tests typically have lots and more restrictive assumptions
71 of 81
How to solve the problem of too many t-tests?
Reduce the alpha value from below 0.05 so that every test we do has not got a 5% chance of having a TI error because the more tests we do the higher this percentage is
72 of 81
What is the Bonefferoni corection?
Divide the critical significance value by the number of hypothesis tests being done. 0.05 divided by 20 is 0.025
73 of 81
Which statement is incorrect about the FITTED VALUE?
The best our model can do is predict that any given rice grain’s length will not be the mean grain length of rice from the same country – as judged by the grains in our sample.
74 of 81
Why are all models wrongs?
They are simplifications of reality. However, they may still be useful in helping us make sense of our highly complex world.
75 of 81
What is the null model?
It is the null hypothesis that all means are the same so can have the same mean as the overall mean. This is the simplest model we can use, called the null model because it is associated with the null hypothesis
76 of 81
Which is not a feature visually shown by graphs when looking at fitted models and null models?
SST+SSE=SSM (model sum of squares)
77 of 81
What is the COEFFICIENT OF DETERMINATION?
SSMxSST
78 of 81
What does not constitute usefulness in the model?
Sample size
79 of 81
How do you calculate the error of variance?
Error df= N-K to calculate the error variance of SSE/(N-K)
80 of 81
What is model complexity measured by?
Degrees of freedom- the more you use the more complex and the more of the variation it should account for
81 of 81

Other cards in this set

Card 2

Front

What does the sigma, E and numbers mean in a summation equation?

Back

Sigma= sum, E= quantity and the numbers represent the reference number

Card 3

Front

What is the dummy variable?

Back

Preview of the front of card 3

Card 4

Front

What is rounding down also known as?

Back

Preview of the front of card 4

Card 5

Front

What do you do when asked to round off?

Back

Preview of the front of card 5
View more cards

Comments

No comments have yet been made

Similar Geography resources:

See all Geography resources »See all Statistics theory resources »