The scatterplot is the basic tool for graphically displaying bivariate quantitative data.
Some investors think that the performance of the stock market in January is a good predictor of its performance for the entire year. To see if this is true, consider the following data on Standard & Poor's 500 stock index (found in SASDATA.SANDP).
Figure 1 shows a scatterplot of the
percent gain in the S&P index over the year (vertical axis)
versus the percent gain in January (horizontal axis). Each point is
labelled with its corresponding year.
The scatterplot of the S&P data can illustrate the general analysis of scatterplots. You should look for:
For the S&P data, there is association. This shows up as a general
(Larger % gain in January is generally associated with larger %
It is hard to tell if the association is linear, since the spread of
the data is increasing with larger January % gain. This is due
primarily to the 1987 datum in the lower right corner of plot, and to
some extent the 1994 datum. Eliminate those two points, and the
association is strong linear and positive, as Figure 2 shows.
There is some justification for considering the 1987 datum atypical. That was the year of the October stock market crash. The 1994 datum is a mystery to me.
Data smoothers can help identify and simplify patterns in large sets of bivariate data. You have already met one data smoother: the moving average.
Another is the median trace.
Suppose n measurements, are taken on the variables X and Y. Then the Pearson correlation between X and Y computed from these data is
are the standardized data.
If n is the sample size,
has approximately a tn-2 distribution. We can use this fact to obtain a confidence interval for .
Back to the S&P data, the SAS macro CORR gives a 95% confidence
interval for as
(-0.2775, 0.8345). As this interval contains 0, it indicates no significant linear association between JANGAIN and YEARGAIN.
If we remove the 1987 and 1994 data, a different story emerges. Then the Pearson correlation is r=0.9360, and a 95% confidence interval for is (0.6780, 0.9880). Since this interval consists entirely of positive numbers, we conclude that is positive and we estimate its value to be between 0.6780 and 0.9880.
QUESTION: What is ? Does this make sense?
The SLR model attempts to quantify the relationship between a single predictor variable Z and a response variable Y. This reasonably flexible yet simple model has the form
where is a random error term, and X(Z) is a function of Z, such as Z, Z2, or .
By looking at different functions X, we are not confined to linear relationships, but can also model nonlinear ones. The function X is called the regressor. Often, we omit specifying the dependence of the regressor X on the predictor Z, and just write the model as
We want to fit the model to a set of data . As with the C+E model, two options are least absolute errors, which finds values b0 and b1 to minimize
or least squares, which finds values b0 and b1 to minimize
We'll concentrate on least squares. Using calculus, we find the least squares estimators of and to be
The relevant SAS/INSIGHT output for the regression of YEARGAIN on JANGAIN is shown in Figure 3.
It measures the ``average squared prediction error'' when using the regression.
Estimation of Slope and Intercept
Level L confidence intervals for and are
A similar computation with and , gives a 95% confidence interval for as
NOTE: Whether the interval for contains 0 is of particular interest. If it does, it means that we cannot statistically distinguish from 0. This means we have to consider plausible the model for which :
This model, which is just the C+E model, implies that there is no association between Y and X.
The mean response at X=x0 is
The point estimator of is
A level L confidence interval for is
A level L prediction interval for a future observation at X=x0 is
The macro REGPRED will compute confidence intervals for a mean response and prediction intervals for future observations for each data value and for other user-chosen X values.
The SAS macro REGPRED was run on the reduced S&P data, and estimation of the mean response and prediction of a new observation at the value JANGAIN=5 were requested. Both and equal 9.65+(2.36)(5)=21.46. The macro computes a 95% confidence interval for the mean response at JANGAIN=5 as (16.56,26.36), and a 95% prediction interval for a new observation at JANGAIN=5 as (9.08,33.84).
If the standardized responses and regressors are
Then the regression equation fitted by least squares can be written as
Where X' is any value of a regressor variable standardized as described above.
The Regression Effect refers to the phenomenon of the standardized predicted value being closer to 0 than the standardized regressor. Equivalently, the unstandardized predicted value is fewer Y standard deviations from the response mean than the regressor value is in X standard deviations from the regressor mean.
For the S&P data r=0.4295, so for a January gain standard deviations (SX) from , the regression equation estimates a gain for the year of
standard deviations (SY) from .
With 1987 and 1994 removed, the estimate is
which reflects the stronger relation.
Analysis of categorical data is based on counts, proportions or percentages of data that fall into the various categories defined by the variables.
Some tools used to analyze bivariate categorical data are:
A survey on academic dishonesty was conducted among WPI students in 1993 and again in 1996. One question asked students to respond to the statement ``Under some circumstances academic dishonesty is justified.'' Possible responses were ``Strongly agree'', ``Agree'', ``Disagree'' and ``Strongly disagree''. The 1993 results are shown in the following 2x2 table and in the mosaic plots in Figure 5 and 6:
|Dishonesty Sometimes Justified|
Inference for Categorical Data with Two Categories Methods for comparing two proportions can be used (estimation from chapter 5 and hypothesis tests from chapter 6).
Inference for Categorical Data with More Than Two Categories: One-Way Tables
Suppose the categorical variable has c categories, and that the population proportion in category i is pi. To test
where Yi is the observed frequency in category i, and n is the total number of observations.
Note that for each category the Pearson statistic computes (observed-expected)2/expected and sums over all categories.
Under H0, . Therefore, if x2* is the observed value of X2, the p-value of the test is .
Historically, the distribution of weights of ``5 pound'' dumbbells produced by one manufacturer have been normal with mean 5.01 and standard deviation 0.15 pound. It can be easily shown that 20% of the area under a normal curve lies within standard deviations of the mean, 20% lies between 0.25 and 0.84 standard deviations of the mean, 20% lies between -0.84 and -0.25 standard deviations of the mean, 20% lies beyond 0.84 standard deviations above the mean, and another 20% lies beyond 0.84 standard deviations below the mean.
This means that the boundaries that break the N(5.01,0.152) density into five subregions, each with area 0.2, are 4.884, 4.9725, 5.0475 and 5.136.
A sample of 100 dumbbells from a new production lot shows that 25 lie below 4.884, 23 between 4.884 and 4.9725, 21 between 4.9725 and 5.0475, 18 between 5.0475 and 13 above 5.136. Is this good evidence that the new production lot does not follow the historical weight distribution?
We will perform a test. Let pi be the proportion of dumbbells in the production lot with weights in subinterval i, where subinterval 1 is , subinterval 2 is (4.884,4.9725], and so on. If the production lot follows the historical weight distribution, all pi equal 0.2. This gives our hypotheses:
Since np(0)i=20 for each i, the test statistic is
The p-value is , so we cannot reject H0.
Inference for Categorical Data with More Than Two Categories: Two-Way Tables Suppose a population is partitioned into rc categories, determined by r levels of variable 1 and c levels of variable 2. The population proportion for level i of variable 1 and level j of variable 2 is pij. These can be displayed in the following table:
We want to test
|H0:||row and column variables|
|Ha:||row and column variables|
|are not independent.|
Under H0 the expected cell frequencies are given by
To measure the deviations of the observed frequencies from the expected frequencies under the assumption of independence, we construct the Pearson statistic
where and .
Note that for the test to be valid, we require that .
Example: A polling firm surveyed 269 American adults concerning how leisure time is spent in the home. One question asked them to select which of five leisure activities they were most likely to partake in on a weeknight. The results are broken down by age group in the following table, in which the cell entries are frequency, expected frequency under the hypothesis of independence of age and activity, and Pearson residual.
|Group||TV||Read||to Radio||to Stereo||Game||Totals|
As an example of the computation of table entries, consider the entries in the (1,2) cell (age: 18-25, activity: Read), in which the observed frequency is 3. The marginal number in the 18-25 bracket is 62, while the marginal number in the Read bracket is 40, so , while , so the expected number in the (1,2) cell is 269(62/269)(40/269)=9.22. The Pearson residual is . The value of the chi-square statistic is 38.91, which is computed as the sum of the squares of the Pearson residuals. Comparing this with the chi-square distribution with 16 degrees of freedom, we get a p-value of 0.0011.
Association is NOT Cause and Effect
Two variables may be associated due to a number of reasons, such as:
The Issue of Stationarity
This document was generated using the LaTeX2HTML translator Version 97.1 (release) (July 13th, 1997)
Copyright © 1993, 1994, 1995, 1996, 1997, Nikos Drakos, Computer Based Learning Unit, University of Leeds.
The command line arguments were:
latex2html -split 0 lect7.
The translation was initiated by Joseph D Petruccelli on 11/4/1999