The name is absent



10

Stata Technical Bulletin

STB-4

Output of a ranova run with one missing value and

four dropped observations appears as

. ranova Varl-

-Var4 in 5/20

Mean

Standard Deviation

Varl

101.2667

14.9450

Var2

103.4667

15.1510

Var3

104.4000

17.0955

Var 4

107.3333

15.9135

Single Factor Repeated Measures ANOVA

Number

of obs in model

= 15

Number of vars = 4

Number

of obs dropped

= 5

Source

I       SS

df

MS        F      Prob > F

______________

Subjects

Ï 13459.9300

14

_______________________________

Treatments

I 284.5800

3

94.8600     7.70    0.0003

Error

I 517.6700

42

12.3255

______________

Total

I 14262.1800

59

________________________________

smv2 Analyzing repeated measurements—some practical alternatives

William H. Rogers, CRC, FAX 310-393-7551

Longitudinal studies (also known as panels or cross-sectional time-series) are some of the most potentially informative
yet complicated studies to analyze. A typical longitudinal study follows individuals over time to monitor the effects of some
experimental treatment. For example, two baseline measures might be taken and then a drug administered to half the sample.
The patients are assessed one, two, and three months later.

One technique for analyzing such data is repeated measures ANOVA, a powerful statistical technique with a well-deserved
reputation for flexibility in addressing the complex relationships found in longitudinal studies. As a result, the technique is often
recommended by well-intentioned theoreticians and authors of texts when, in practice, it is not usable in certain situations because
the data are too messy. The most troublesome aspect of this messiness, from a repeated measures
ANOVA standpoint, is missing
data. One might set out to assess patients one, two, and three months later, but some patients may skip the first assessment,
others the second, and so on.

Longitudinal studies can be successfully analyzed without resorting to repeated measures ANOVA and without discarding
potentially informative incomplete observations. Moreover, the analytic alternatives throw the assumptions into sharper focus,
are more descriptive, and offer more possibilities to connect intuition to analysis.

To demonstrate this, I will present some data that pose interesting substantive questions and reveal some of the complexities
caused by missing data. We will then examine simple cross-sectional regressions and the behavior of changes over time and
finally, we will compute individual “slopes” for each observation and analyze those slopes. When we are through, we will have
a better understanding of this data than if we had been able to apply repeated measures
ANOVA to this data. The message is
that, even had the data been clean enough to apply repeated measures
ANOVA, we might still wish to pursue these alternative,
less exotic techniques.

The data are drawn from a real study (Tarlov et al. 1989). The underlying data consist of thousands of variables including
variables recording marital status and gender, age, race (coded 1 for nonwhites and 0 for whites), and mental health measured at
5 points in time for patients suffering from chronic diseases (either mental or physical). The goal of our analysis is to model the
relationship between the demographic information and mental health. The five time periods are unequally spaced. There are two
measurements at the beginning, 3 months apart. The last three measurements follow 1, 2, and 4 years later. Our data contains

Contains data

from mhifile.dta

Obs : 3869

(max=

= 24749)

MOS Patient Form Data

Vars:     9

1. married

2. iagecont

3. imale

4. inonwht

(max=

=   254)

int
float
int
int

I

7.8.0g

7.10.0g

7.8.0g

7.8.0g

Patient age

Patient is male

Patient is nonwhite

5. mhiθ

float

7.9.0g

Baseline Mental Health

6. mhi3mo

float

7.9.0g

Mental Health at 3 months

7. mhilyr

float

7.9.0g

Mental Health at 1 year

8. mhi2yr

float

7.9.0g

Mental Health at 2 years

9. mhi4yr

float

7.9.0g

Mental Health at 4 years

As a way of getting to know this sample, I begin by presenting a series of marital status tabulations summarizing the mental
health index:



More intriguing information

1. The name is absent
2. A Consistent Nonparametric Test for Causality in Quantile
3. PROPOSED IMMIGRATION POLICY REFORM & FARM LABOR MARKET OUTCOMES
4. The name is absent
5. Passing the burden: corporate tax incidence in open economies
6. HACCP AND MEAT AND POULTRY INSPECTION
7. The name is absent
8. The name is absent
9. The name is absent
10. Globalization and the benefits of trade
11. The Challenge of Urban Regeneration in Deprived European Neighbourhoods - a Partnership Approach
12. The quick and the dead: when reaction beats intention
13. Constructing the Phylomemetic Tree Case of Study: Indonesian Tradition-Inspired Buildings
14. Understanding the (relative) fall and rise of construction wages
15. The name is absent
16. Barriers and Limitations in the Development of Industrial Innovation in the Region
17. Innovation Policy and the Economy, Volume 11
18. The Making of Cultural Policy: A European Perspective
19. Conservation Payments, Liquidity Constraints and Off-Farm Labor: Impact of the Grain for Green Program on Rural Households in China
20. Reversal of Fortune: Macroeconomic Policy, International Finance, and Banking in Japan