Creative Graphing by using Stata

Edward Tufte, in his elegant and influential books about graphing data (1990, 1997, 2001, 2006), calls for more effort at designing clear, information-packed graphics. Presenting a rich collection of impressively good or humorously awful examples, Tufte shows how successful graphics allow viewers to draw their own comparisons and examine details of relationships between variables.

Declare Survey Data in Stata

Since 2001, the Granite State Poll at the University of New Hampshire has conducted statewide telephone surveys several times each year. Each survey contacts a new sample of about 500 people, asking a variety of opinion questions along with respondent background characteristics. The poll’s political findings attain national importance every four years during New

Design Weights of Survey Data in Stata

The previous section took weight definitions for granted, and indeed many data users begin with a completed survey in which weights have already been calculated by someone else. This and the following sections present examples showing how such calculations are done. Survey researchers apply probability weights to adjust for biases in their sampling methods.

Poststratification Weights of Survey Data in Stata

The previous section gave an example of weights based on the sampling design, which was known before data collection began. A second type of weights might be defined after we have collected the data, and see that despite our best efforts, it appears unrepresentative in some respect. For instance, the sample might have a

1 Comments

Survey-Weighted Tables and Graphs by using Stata

The June 2011 Granite State Poll included six questions related to global warming or climate change. Several questions were factual, but one (warmop) asked what you personally believe. Which of the following three statements do you personally believe? Climate change is happening now, caused mainly by human activities. Climate change is happening now, but

Bar Charts for Multiple Comparisons by using Stata

The catplot bar charts in Figure 4.3 depict a relationship between two categorical variables, each with four categories. If we have more than two variables, or more than a few categories, however, the catplot approach becomes cluttered. A cleaner alternative for making multiple comparisons of categorical variables employs Stata’s horizontal bar chart command hbar.

1 Comments

Summary Statistics for Measurement Variables by using Stata

Dataset electricity.dta contains information on electricity consumption in U.S. states, from the California Energy Commission (2012). To find the mean and standard deviation of per capita electricity use (elcap), type This table also gives the number of nonmissing observations and the variable’s minimum and maximum values. If we had simply typed summarize with no

Exploratory Data Analysis by using Stata

Statistician John Tukey assembled a toolkit of old and new methods for exploratory data analysis (EDA), which involves analyzing data in an exploratory and skeptical way without making unneeded assumptions (see Tukey 1977; also Hoaglin, Mosteller and Tukey 1983, 1985). Box plots, introduced in Chapter 3, are one the most popular EDA methods. Another

Normality Tests and Transformations by using Stata

Many statistical procedures work best when applied to variables that follow normal distributions. The preceding section described exploratory methods to check for approximate normality, extending the graphical tools (histograms, box plots, symmetry plots and quantile-normal plots) presented in Chapter 3. A skewness-kurtosis test, making use of the skewness and kurtosis statistics shown by summarize,

Frequency Tables and Two-Way Cross-Tabulations by using Stata

The summary statistics, graphs and transformations described above apply mainly to measurement variables. Categorical variables require different approaches, often starting with simple one- or two-way tables. For examples using such tables we return to the Granite State Poll data, Granite2011_6.dta. One question (trackus) asked whether people think the U.S. is headed in the right

1 Comments

Multiple Tables and Multi-Way Cross-Tabulations by using Stata

With surveys and other large datasets, we sometimes need frequency distributions of many different variables. Instead of asking for each table separately, for example by typing tabulate tparty, then tabulate obama, and finally tabulate trackus, we could simply use another specialized command, tabl: . tabl tparty obama trackus Or, to produce one-way frequency tables

Tables of Means, Medians and Other Summary Statistics by using Stata

Summary Statistics tabulate produces tables of means and standard deviations within categories of the tabulated variable. For the remaining examples in this chapter, we return to the data on electricity consumption in U.S. states. tabulate gives us one way to view summary statistics of per capita electricity consumption (elcap) for each of the 9

Using Frequency Weights with Stata

summarize, tabulate, table and related commands can be used with frequency weights that indicate the number of replicated observations. For example, here are the mean and other statistics for per capita electricity use across all U.S. states. This mean, 13,318 kWh, tells us the average electricity across the 51 states (including District of Columbia)

One-Sample Tests by using Stata

One-sample t tests have two seemingly different applications: Testing whether a sample mean y differs significantly from an hypothesized value p0 . Testing whether the means of yj and y2 , two variables measured over the same set of observations, differ significantly from each other. This is equivalent to testing whether the mean of

Two-Sample Tests by using Stata

The remainder of this chapter draws examples from a survey of college undergraduates by Ward and Ault (1990). About 19% of these students belong to a fraternity or sorority. On campus, these organizations and their members are commonly referred to as “Greeks” not with any reference to nationality, but because most of the organizations

1 Comments

One-Way Analysis of Variance (ANOVA) by using Stata

Analysis of variance (ANOVA) provides another way, more general than t tests, to test for differences among means. The simplest case, one-way ANOVA, tests whether the means of y differ across categories of x. One-way ANOVA can be performed by a oneway command with the general form oneway measurement categorical. For example, The tabulate

Two- and N-Way Analysis of Variance by using Stata

One-way ANOVA examines how the means of measurement variable y vary across categories of one other variable x. N-way ANOVA generalizes this approach to deal with two or more categorical x variables. For example, we might consider how drinking behavior varies not only by fraternity or sorority membership, but also by gender. We start

Factor Variables and Analysis of Covariance (ANCOVA) by using Stata

anova and many other Stata estimation commands allow independent variables specified in factor variable notation. The prefix i. written before the name of an independent variable tells Stata to include indicator (binary) variables for levels of a categorical variable, as if each category comprised its own dichotomous predictor. Categorical variables marked by the i.

Predicted Values and Error-Bar Charts by using Stata

After anova , the followup command predict calculates predicted values, residuals or standard errors and diagnostic statistics. One use for such statistics is in drawing graphical representations of the model results, such as an error-bar chart. For a simple illustration, we return to the one­way ANOVA of drink by year: . anova drink year

Simple Regression by using Stata

File Nations2.dta contains U.N. human-development indicators for 194 countries: . use C:\data\Nations2.dta, clear Life expectancies (life) exhibit much place-to-place variation. For example, Figure 7.1 shows that they tend to be lower in Africa than elsewhere. To what extent can variations in life expectancy be explained by average education, per capita wealth and other development