Results 1 to 8 of 8

Math Help - Please help with stats side of my nature research!

  1. #1
    Newbie
    Joined
    Feb 2011
    Posts
    7

    Please help with stats side of my nature research!

    Hello,

    My name is Chloe. I am currently conducting a university research study considering if various golf courses can compete with nature reserves as a location for conservation and sustainability. I'm looking at 3 courses and 3 reserves in my area.

    I know this is the under university section but I'm really terrible with maths!

    One branch of primary data I'm collecting is the levels of animal species richness and abundance.

    I have the numbers from my observations but I'm struggling to provide statistical analysis. I want to test for statistical significance between different species observed at both (types) of site. I understand the concept and what it means but all the instructions I've read ask me to choose what I'd accept as a level of error or am I doing a t test or a chi squared test yada yada

    Would someone be willing to help me with the maths of it? And suggest the type of data testing method that would be suitable for my data set? It'd be much appreciated!

    Thankyou

    x Chloe x
    Follow Math Help Forum on Facebook and Google+

  2. #2
    Master Of Puppets
    pickslides's Avatar
    Joined
    Sep 2008
    From
    Melbourne
    Posts
    5,236
    Thanks
    29
    So I hear that you want to test if the observed numbers (or ratios) on these golf courses are similar to what is expected in a nature reserve?

    I could help, how much data do you have?
    Follow Math Help Forum on Facebook and Google+

  3. #3
    Flow Master
    mr fantastic's Avatar
    Joined
    Dec 2007
    From
    Zeitgeist
    Posts
    16,948
    Thanks
    5
    Quote Originally Posted by Bikkembergs View Post
    Hello,

    My name is Chloe. I am currently conducting a university research study considering if various golf courses can compete with nature reserves as a location for conservation and sustainability. I'm looking at 3 courses and 3 reserves in my area.

    I know this is the under university section but I'm really terrible with maths!

    One branch of primary data I'm collecting is the levels of animal species richness and abundance.

    I have the numbers from my observations but I'm struggling to provide statistical analysis. I want to test for statistical significance between different species observed at both (types) of site. I understand the concept and what it means but all the instructions I've read ask me to choose what I'd accept as a level of error or am I doing a t test or a chi squared test yada yada

    Would someone be willing to help me with the maths of it? And suggest the type of data testing method that would be suitable for my data set? It'd be much appreciated!

    Thankyou

    x Chloe x
    Do you have a supervisor for your research project?
    Follow Math Help Forum on Facebook and Google+

  4. #4
    Grand Panjandrum
    Joined
    Nov 2005
    From
    someplace
    Posts
    14,972
    Thanks
    4
    Quote Originally Posted by Bikkembergs View Post
    Hello,

    My name is Chloe. I am currently conducting a university research study considering if various golf courses can compete with nature reserves as a location for conservation and sustainability. I'm looking at 3 courses and 3 reserves in my area.

    I know this is the under university section but I'm really terrible with maths!

    One branch of primary data I'm collecting is the levels of animal species richness and abundance.

    I have the numbers from my observations but I'm struggling to provide statistical analysis. I want to test for statistical significance between different species observed at both (types) of site. I understand the concept and what it means but all the instructions I've read ask me to choose what I'd accept as a level of error or am I doing a t test or a chi squared test yada yada

    Would someone be willing to help me with the maths of it? And suggest the type of data testing method that would be suitable for my data set? It'd be much appreciated!

    Thankyou

    x Chloe x
    When testing for significant difference it is usual to use 95% as the confidence level (that is if there is no real difference you would identify a difference erroneously 5% of the time).

    CB
    Follow Math Help Forum on Facebook and Google+

  5. #5
    Newbie
    Joined
    Feb 2011
    Posts
    7
    Hi,

    Thanks for the replies

    Mr Fantastic - I do, but the statistics documents he gave me I just cant get my head around Plus he's difficult to talk to even when having a normal conversation.

    Pickslides, yes thats generally the idea. Im looking at various other similar studies. One is comparing the animals on golf courses, forests and residential areas. I've extracted the key results info for you to read rather than giving you the full article (My results will be of similar numbers when completed and also observing richness and abundance)

    Total birds observed = 16,585
    Total bird species observed = 138

    Species richness:
    Golf courses X=53.2
    Residential areas X=33.4
    Forests X=48.0

    Stat significance for species richness :
    Between GC and RE = P<0.0001

    Relative abundance of birds:
    Golf courses X=452
    Residential areas X=361
    Forests X=337

    Apparently he calculated the species richness estimates using the Bootstrap method. He calculated the relative site abundances using relative index.


    Once he had these estimates he then compared the species collectively between land types. The mammal estimates using T tests and ANOVAs with Tukey HSD testing for birds.

    He finishes by comparing individual species between land types. Comparing birds using Kruskal Wallis ANOVA for birds and Mann-Whitney U tests for mammals.

    So much information, is this overly complicated? I'm not trying to demonstrate I can interpret statistics via 5 or 6 fancy ways - Once I'd demonstrated the understanding and justification of a statistical test then 1 or 2 would surely suffice?

    Lets go back to his stats. Where has he got these figures from? I cant see the sums he has done to acheive the numbers from 16585 birds over 138 species...? He must have left out some raw data too because he's mentioning richness and abundance figures for mammals too, and he hasnt mentioned the raw figures he observed for mammals.

    Captain Black, where does p<0.0001 fit into 95-5% as a confidence level?

    I thought significance was about reliability? And a difference of >0.05 was significant?

    My head hurts

    Thanks for helping, xChloex
    Follow Math Help Forum on Facebook and Google+

  6. #6
    Master Of Puppets
    pickslides's Avatar
    Joined
    Sep 2008
    From
    Melbourne
    Posts
    5,236
    Thanks
    29
    I am hearing there has been lots of different tests for lots of different data sets.

    This is the case given the distribution of each set of observations.

    When p<0.0001 then there is a signifcant difference between the two data sets.
    Follow Math Help Forum on Facebook and Google+

  7. #7
    Newbie
    Joined
    Feb 2011
    Posts
    7
    Quote Originally Posted by pickslides View Post
    When p<0.0001 then there is a signifcant difference between the two data sets.
    So what does that mean/signify? And what would it mean if it was no significant difference?
    Follow Math Help Forum on Facebook and Google+

  8. #8
    Flow Master
    mr fantastic's Avatar
    Joined
    Dec 2007
    From
    Zeitgeist
    Posts
    16,948
    Thanks
    5
    Quote Originally Posted by Bikkembergs View Post
    So what does that mean/signify? And what would it mean if it was no significant difference?
    It is clear that you have very little understanding of statistics and are currently out of your depth with what this research task requires. You need to discuss this with a live tutor, ideally your supervisor. It is his/her job to help you understand what you need to do and why you need to do it.
    Follow Math Help Forum on Facebook and Google+

Similar Math Help Forum Discussions

  1. Replies: 0
    Last Post: November 13th 2011, 03:32 PM
  2. Normal distribution beams laid side by side
    Posted in the Advanced Statistics Forum
    Replies: 2
    Last Post: March 12th 2011, 04:05 AM
  3. Replies: 0
    Last Post: October 9th 2010, 01:40 PM
  4. Precalculus angle-side-side, please help!!
    Posted in the Pre-Calculus Forum
    Replies: 1
    Last Post: October 14th 2008, 04:53 PM
  5. Replies: 1
    Last Post: September 14th 2008, 01:25 PM

Search Tags


/mathhelpforum @mathhelpforum