EXAM stuff

Question 1

What is chi square

Answer 1

• Test for association or randomness or homogeneity
• Non-parametric test to compare observed results to expected results on the basis of a null hypothesis
• Samples must be random
• Expected frequency must exceed 5
• Calculates a c²-statistic that is compared to a statistical table to determine whether there is a statistically significant difference between the observed and expected frequencies

Question 2

Null hypothesis for chi squatred

Answer 2

There was no significant difference in observed and expected values for L. obtusata of each colour

OR

There was no significant difference in frequency of occurrence between the three colours

Question 3

t tests

Answer 3

• Parametric test to compare the means of two sets of continuous data
• Can be used with large and small sample sizes
• Calculates a t-statistic and P-value that allow us to determine whether there is a statistically significant difference in the two means

Question 4

data screening t test

Answer 4

• Data must be continuous
• i.e. measurements or on an uninterrupted scale
• Data should be normally distributed
• Use plot or normality test (e.g. Kolmogorov Smirnov)
• Variances should be similar between samples
• Use F-test for equality of variance

Question 5

p vlalue t test

Answer 5

• If your P-value is less than 0.05 then there is a statistically significant difference in the means (at P = 0.05) and we can reject a null hypothesis
• If your P-value is greater than 0.05 then there is no statistically significant difference in the means (at P = 0.05) and we can accept a null hypothesis

Question 6

what is a mann-whitney u test?

Answer 6

• Non-parametric test to compare the medians of two sets of discontinuous data
• Can be used with as few as 4 observations in each sample
• Samples can be unequal
• Distribution free so can be used with non-normal data

Question 7

p value mann whitney u

Answer 7

• If your P-value is less than 0.05 then there is a statistically significant difference in the medians (at P = 0.05) and we can reject a null hypothesis
• If your P-value is greater than 0.05 then there is no statistically significant difference in the medians (at P = 0.05) and we can accept a null hypothesis

Question 8

what is an anova?

Answer 8

• One-way analysis of variance
• Parametric test to compare the means of three or more sets of data
• Samples can be unequal
• Calculates a F-statistic and a P-value that allow us to determine whether there is a statistically significant difference between the three (or more) means

Question 9

p value anova

Answer 9

• We determine significance using the P-value
• If your P-value is less than 0.05 then there is a statistically significant difference in the means (at P = 0.05) and we can reject a null hypothesis
• If your P-value is greater than 0.05 then there is no statistically significant difference in the means (at P = 0.05) and we can accept a null hypothesis

Question 10

what is a krustal wallace?

Answer 10

• Non-parametric test to compare the medians of three or more sets of data
• Can be used with as few as 5 observations in each sample
• Samples can be unequal
• Distribution free so can be used with non-normal data

Question 11

krustal wallace p value

Answer 11

• We determine significance using the P-value
• If your P-value is less than 0.05 then there is a statistically significant difference in the medians (at P = 0.05) and we can reject a null hypothesis
• If your P-value is greater than 0.05 then there is no statistically significant difference in the medians (at P = 0.05) and we can accept a null hypothesis

Question 12

What do corralations establish?

Answer 12

• Need to establish
• If there is a relationship
• Nature of the relationship
• If relationship is significant

Question 13

What is a pearsons corralation coefficient?

Answer 13

•Also called Product Moment Correlation Coefficient

•

•Parametric test to determine if there is a linear relationship between two variables

•

•Calculates a r-statistic and a P-value that allow us to determine whether there is a statistically significant relationship between two variables

Question 14

p vlaue pearsons corralation coefficient

Answer 14

• If your P-value is less than 0.05 then there is a statistically significant relationship between the two variables (at P = 0.05) and we can reject a null hypothesis
• If your P-value is greater than 0.05 then there is no statistically significant relationship between the two variables (at P = 0.05) and we can accept a null hypothesis

Question 15

what is a spearmens rank corralation coefficient?

Answer 15

•Non-parametric test to determine if there is a relationship between two variables

•

•Use if both variables or one variable is discontinuous

•

•Converts x and y variables into ranks

•

•Calculates a rs-statistic and a P-value that allow us to determine whether there is a statistically significant relationship between two variables

Question 16

spearmens rank p value

Answer 16

• If your P-value is less than 0.05 then there is a statistically significant relationship between the two variables (at P = 0.05) and we can reject a null hypothesis
• If your P-value is greater than 0.05 then there is no statistically significant relationship between the two variables (at P = 0.05) and we can accept a null hypothesis

Question 17

mean median mode

Answer 17

• MEAN - sum of a set of observations divided by number of observations
• MEDIAN - middle value of a ranked set of data
• MODE - value occurring most frequently

Question 18

Three main measures of variability:

Answer 18

•STANDARD DEVIATION - calculated from all observations

• standard degree of variability around the mean

•RANGE - highest and lowest observation

• reported with median

•VARIANCE - square of the standard deviation

Question 19

How to measure standard deviation

Answer 19

1. Subtract the mean from each of your numbers in your sample.
2. Square all of the numbers from each of the subtractions you just did.
3. Add the squared numbers together.
4. Divide the sum of squares by (n-1). - varience
5. Take the square root of the variance. - standard deviation

Question 20

Was there any significant difference between the high fertilisation dose (HF) and extra-high fertilisation dose (XF) for both the low marsh and the high marsh?

Answer 20

There was no significant difference in accretion rates between the HF and XF treatments for either the low marsh (ANOVA, F = 1.5, df = 2, P = 0.35) or the high marsh (ANOVA, F = 4.58, df = 2, P = 0.12).

Question 21

There was no significant difference in accretion rates between the HF and XF treatments for either the low marsh (ANOVA, F = 1.5, df = 2, P = 0.35) or the high marsh (ANOVA, F = 4.58, df = 2, P = 0.12).

Answer 21

Current data is similar to Turner’s data for the control treatment in the low marsh though is slightly lower in the high marsh compared to the previous data.

For the HF treatment, the accretion values for both the high marsh and the low marsh were similar to the data from the previous study.

The major difference occurred for the XF treatment in the low marsh, with much lower accretion rates compared to Turner’s data.

Question 22

How did fertilisation of the low marsh compare to fertilisation of the high marsh?

Answer 22

Fertilisation in the high marsh was initially at a higher level than the low marsh for both the HF (4% compared to 1%) and the XF treatment (5.5% compared to 3%). This trend continued from 1970 to 2010 with the high marsh displaying higher d15N over the study period than the low marsh.

Question 23

Fertilisation in the high marsh was initially at a higher level than the low marsh for both the HF (4% compared to 1%) and the XF treatment (5.5% compared to 3%). This trend continued from 1970 to 2010 with the high marsh displaying higher d15N over the study period than the low marsh.

Answer 23

The d15N values in the fertilised treatments were much higher compared to the control. All fertilised treatments displayed a strong positive relationship between time and d15N. This relationship was not as strong for the control treatments.

Question 24

Determine the average and within sample variability in the number of shoots in each area for each treatment.

Suggest what your findings show about the effect of fertilisation on vegetation abundance in both the low marsh and the high marsh.

Answer 24

Overall, the abundance of Spartina shoots was much higher in the high marsh compared to the low marsh. Within the low marsh, the XF treatment had the greatest abundance of shoots (median = 8.5 ± 19 range) compared to the HF treatment (median = 5.5 ± 11 range) with the control having the lowest abundance (median = 2.5 ± 9 range).

For the high marsh, the same pattern was observed with the XF treatment displaying the greatest abundance of vegetation (median = 17.5 ± 14 range), followed by the HF treatment (median = 26.5 ± 7 range) with the control treatment displaying the lowest abundance (median = 7 ± 7 range).