LESSON 16: Logarithmic scales and growth rates

FOCUS QUESTION: How can I use logarithmic scales to understand rates of growth?

This lesson uses logarithmic scales combined with linear fits to understand how fast something is growing

In this lesson you will:
  • Use logarithmic scales to display data on multiple scales.
  • Compute rates of change per capita to assess exponential growth.
  • Work with logarithmic transformations and semilog scales.
  • Calculate a linear fit lines after logarithmic transformation.
  • Determine how fast something is growing.
  • Set properties of multiple axes.
 Max Kleiber's hand-drawn graph of body mass vs heat from 1947
The Metaboloic Theory of Ecology (MTE) says that influence of body size and temperature on metabolic rate are fundamental constraints that govern the behavior of ecosystems.

Contents

DATA FOR THIS LESSON

File Description
toRump.txt
toHeel.txt
 These data sets contain typical fetal size as a function of gestational week.
  • The first column contains the week
  • The second column contains the fetal length in cm
  • The third column contains the fetal weight (mass actually) in grams.
  • The toRump.txt data measures length from baby crown to baby rump during early gestation.
  • The toHeel.txt measures the length from baby crown to baby heel during later gestation.
  • The data came from http://www.babycenter.com/average-fetal-length-weight-chart.
    		•
    WorldPopulation.csv This data set contains world population data for the years 10,000BC to 2007 as well as estimates of the population from 2008 to 2050. Data for years before 1950 is calculated as the average of the lower and upper historical estimates of world population for those times. The data set has two columns:
    • The first column is the year
    • The second column is the world population in billions
    The population data came from the International Data Base (IDB) maintained by the US Census Bureau. The datasets and additional information can be found at: http://www.census.gov/ipc/www/idb/worldpopinfo.php.

    SETUP FOR LESSON 16

    EXAMPLE 1: Load the fetal size data

    Create a new cell in which you type and execute:

        load toRump.txt;  % Load the crown-to-rump data
    load toHeel.txt;  % Load the crown-to-heel data

    You should see the following 2 variables in your Workspace browser:

    EXAMPLE 2: Define variables to make code easier to read

    Create a new cell in which you type and execute:

       rWeeks = toRump(:, 1);          % Weeks in the toRump measurements
   hWeeks = toHeel(:, 1);          % Weeks in the toHeel measurements
   rMass = toRump(:, 3)/1000;      % Mass in kg of toRump measurements
   hMass= toHeel(:, 3)/1000;       % Mass in kg of toHeel measurements

    You should see 4 variables in the Workspace Browser:

    EXAMPLE 3: Plot fetal mass as a function of gestational week

    Create a new cell in which you type and execute:

       figure
   hold on
   plot(rWeeks, rMass, 'ko')      % Plot the toRump mass
   plot(hWeeks, hMass, 'rs')      % Plot the toHeel mass
   xlabel('Week');
   ylabel('Mass (kg)');
   title('Fetal growth by gestational age');
   legend({'Crown-to-rump', 'Crown-to-heel'}, 'Location', 'NorthWest')
   hold off

    You should see a new a Figure Window with the following plot:

    EXAMPLE 4: Plot fetal mass as a function of gestational week using a semilog scale

    Create a new cell in which you type and execute:

       figure
   semilogy(rWeeks, rMass, 'ko', hWeeks, hMass, 'rs') % Plot the toRump mass
   xlabel('Week');
   ylabel('Mass (kg)');
   title('Fetal growth by gestational age');
   legend({'Crown-to-rump', 'Crown-to-heel'}, 'Location', 'SouthEast')

    You should see a new a Figure Window with a labeled plot. Notice that semilog labels the y-axis with mass values rather than by the logarithm of the mass values.

    EXAMPLE 5: Estimate fetal mass growth rates using the slope from the linear fit

    Create a new cell in which you type and execute:

       pRump = polyfit(rWeeks, log10(rMass), 1); % Fit weeks 8-20
   pHeel = polyfit(hWeeks, log10(hMass), 1); % Fit weeks 20-43
   corRump = corr(rWeeks, log10(rMass));     % Find correlation
   corHeel = corr(hWeeks, log10(hMass));

    You should see the following 4 variables in your Workspace Browser:

    EXAMPLE 6: Output the estimates of fetal mass growth rates and R^2 for the linear fits

    Create a new cell in which you type and execute:

       fprintf(['Fetal mass growth rates in g/week:\n' ...
            '\t%g weeks 8-20, R^2 = %g\n' ...
            '\t%g weeks 20-43, R^2 = %g\n'], ...
             pRump(1), corRump*corRump, pHeel(1), corHeel*corHeel);

    You should see the following output in the Command Window:

    Fetal mass growth rates in g/week:
	0.209119 weeks 8-20, R^2 = 0.971853
	0.0491613 weeks 20-43, R^2 = 0.972093

    EXAMPLE 7: Read in the world population data and define variables

    Create a new cell in which you type and execute:

       data = csvread('WorldPopulation.csv');
   year = data(:, 1);
   population = data(:, 2);

    You should see the following 3 variables in your Workspace Browser:

    EXAMPLE 8: Plot the world population as a function of time

    Create a new cell in which you type and execute:

       figure
   plot(year, population)
   xlabel('Year');
   ylabel('Population (in billions)')
   title('World population (10,000 BC to 2050)');

    You should see a Figure Window containing a labeled plot. Notice that population appears to be "exponentially growing".

    EXAMPLE 9: Plot year vs. world population on a semilog scale

    Create a new cell in which you type and execute:

       figure
   semilogy(year, population)
   xlabel('Year');
   ylabel('Population (in billions)')
   title('World population (10,000 BC to 2050)');

    You should see a Figure Window containing a labeled plot. Notice that the plot still curves upward after taking the logarithm, indicating that the population is growing faster than exponentially.

    EXAMPLE 10: Focus on the population data for 1500-2050

    Create a new cell in which you type and execute:

        yr = year(27:end);                      % Pick out years 1500-2050
    pop = population(27:end).*1e+9;         % Convert to units of people so log of log works
    popGRate = diff(pop)./diff(yr);         % Annual growth rate
    mYr = (yr(1:end-1) + yr(2:end))./ 2;    % The yr midpoints for plotting growth rate
    perCapitaGR = popGRate./pop(1:(end-1)); % Growth rate per person (birth rate)

    You should see the following 5 variables in your Workspace Browser:

    EXAMPLE 11: Plot the year vs the log of the log of the world population

    Create a new cell in which you type and execute:

       figure
   plot(yr, log10(log10(pop)))
   xlabel('Year');
   ylabel('Log_{10}(Log_{10}(Population))')     % Think about label here
   title('World population (1500-2050)')

    You should see a new a Figure Window with a labeled plot. Note: a function whose log of the log appears linear has an exponential growth rate that is itself exponentially growing.

    EXAMPLE 12: Plot log of the log of population versus its growth rate

    Create a new cell in which you type and execute:

       figure
   ax = plotyy(yr, log10(log10(pop)), mYr, perCapitaGR);
   title('World population (1500-2050)')
   box off

   % Set the left axis labels and tick marks manually using the ax(1) handle
   xlabel(ax(1), 'Year');
   ylabel(ax(1), 'Population in billions (loglog scale)')
   set(ax(1), 'YLimMode', 'manual', 'YLim', [log10(8), log10(10)]);
   set(ax(1), 'YTickMode', 'manual', 'YTickLabelMode', 'manual');
   set(ax(1), 'YTick', [log10(8),  log10(9), log10(10)]);
   set(ax(1), 'YTickLabel', [0.1, 1, 10]);

   % Set the right axis labels and tick marks manually using the ax(2) handle
   xlabel(ax(2), '');                             % Turn off x-axis label
   ylabel(ax(2), 'Annual growth rate per capita') % Label right y-axis
   set(ax(2), 'XTickMode', 'manual', 'XTick', []); % Turn off x ticks

    You should see a new a Figure Window with a labeled plot. This example shows how to access the properties of the individual axes for plotyy.

    SUMMARY OF SYNTAX

    MATLAB syntax Description
    Y = exp(X) returns an array Y that is the same size as the array X. Each element of Y is ex where x is the corresponding element in the array X. The constant e, also known as Euler's number, is the base of the natural logarithm and has a value of approximately 2.7183. The function f(x) = ex is the only function whose slope is exactly equal to itself at every value of x. Compute the value of e using exp(1).
    logarithmic scale refers to plotting the logarithm of a variable rather than the variable itself. Log scales are useful for variables that have a large range of values. Log scales in common use include decibals (db) for measuring the power of sound and the Richter scale for measuring the intensity of earthquakes. Typically, the tick marks for a log scale are not equally spaced, but rather are chosen so that the unlogged values are equally spaced. See http://en.wikipedia.org/wiki/Logarithmic_scale for additional explanations and illustrations.
    Y = log(X) returns an array Y that is the same size as the array X. Each element of Y is natural logarithm of the corresponding element of X. The natural logarithm uses Euler's number e as its base. Remember that all of the elements of X must be positive.
    Y = log2(X) returns an array Y that is the same size as the array X. Each element of Y is logarithm base 2 of the corresponding element of X. Remember that all of the elements of X must be positive.
    Y = log10(X) returns an array Y that is the same size as the array X. Each element of Y is logarithm base 10 of the corresponding element of X. The log base 10 is sometimes called the common log. Remember that all of the elements of X must be positive.
    loglog(Y) draws a separate line graph for each column of the array log10(Y). If Y is a vector, loglog draws a single line graph of log10(Y). These values are plotted against the values log10(1), log10(2), log10(3), log10(4), ... . Both axes use a logarithmic scale.
    loglog(X, Y) draws a separate line graph for each column of the array log10(Y). If Y is a vector, loglog draws a single line graph of log10(Y). These values are plotted against the corresponding values of log10(X). Both axes use a logarithmic scale.
    semilogx(Y) draws a separate line graph for each column of the array Y. If Y is a vector, semilogx draws a single line graph of Y. These values are plotted against the values log10(1), log10(2), log10(3), log10(4), ... . Only the x-axis uses a logarithmic scale.
    semilogx(X, Y) draws a separate line graph for each column of the array Y. If Y is a vector, semilogx draws a single line graph of Y. These values are plotted against the corresponding values of log10(X). Only the x-axis uses a logarithmic scale.
    semilogy(Y) draws a separate line graph for each column of the array log10(Y). If Y is a vector, semilogy draws a single line graph of log10(Y). These values are plotted against the values 1, 2, 3, 4, ... . Only the y-axis uses a logarithmic scale.
    semilogy(X, Y) draws a separate line graph for each column of the array log10(X). If Y is a vector, semilogy draws a single line graph of log10(Y). These values are plotted against the corresponding values of X. Only the y-axis uses a logarithmic scale.

    This lesson was written by Kay A. Robbins of the University of Texas at San Antonio and last modified on 31-Dec-2010. Please contact krobbins@cs.utsa.edu with comments or suggestions. The image is a a copy of the hand-drawn graph of Max Kleiber that appeared in Kleiber M. (1947). Body size and metabolic rate. Physiological Reviews 27: 511-541. The image is available on Wikipedia as <http://en.wikipedia.org/wiki/File:Kleiber1947.jpg>.


    Published with MATLAB® 7.14